from:"Aaron Enye Shi via Phabricator via cfe\-commits"

[PATCH] D48493: [HIP] Support flush denorms bitcode

2018-06-22 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 created this revision.
ashi1 added a reviewer: yaxunl.
ashi1 added projects: clang, AMDGPU.
Herald added a subscriber: cfe-commits.

We need to use oclc_daz_opt_on.amdgcn.bc bitcode when option 
fcuda-flush-denormal-to-zero is enabled for HIP.


Repository:
  rC Clang

https://reviews.llvm.org/D48493

Files:
  lib/Driver/ToolChains/HIP.cpp


Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+std::string OCLC_daz_opt;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  OCLC_daz_opt = "oclc_daz_opt_on.amdgcn.bc";
+else
+  OCLC_daz_opt = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   OCLC_daz_opt,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }


Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+std::string OCLC_daz_opt;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  OCLC_daz_opt = "oclc_daz_opt_on.amdgcn.bc";
+else
+  OCLC_daz_opt = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   OCLC_daz_opt,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D52673: [HIP] Remove disabled irif library

2018-10-09 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 168836.
ashi1 added a comment.

The device libraries has been updated, and the hip.amdgcn.bc library is now 
available there.


Repository:
  rC Clang

https://reviews.llvm.org/D52673

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/hip-device-libs.hip


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,8 +21,8 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" 
"{{.*}}irif.amdgcn.bc"
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" 
"{{.*}}hip.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"

Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,15 +82,15 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "hip.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
   for (auto Lib : BCLibs)
 addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);

   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,8 +21,8 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" "{{.*}}irif.amdgcn.bc"
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" "{{.*}}hip.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"

Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,15 +82,15 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "hip.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
   for (auto Lib : BCLibs)
 addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);

   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D52673: [HIP] Remove disabled irif library

2018-10-09 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 168855.
ashi1 marked an inline comment as done.
ashi1 added a comment.

I've moved the hip.amdgcn.bc to the top of the libs. Updated test as well.


https://reviews.llvm.org/D52673

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/hip-device-libs.hip


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,8 +21,9 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" 
"{{.*}}irif.amdgcn.bc"
+// COM-SAME: "{{.*}}hip.amdgcn.bc" "{{.*}}opencl.amdgcn.bc"
+// COM-SAME: "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"

Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -81,16 +81,16 @@
 else
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

-BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+BCLibs.append({"hip.amdgcn.bc", "opencl.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
   for (auto Lib : BCLibs)
 addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);

   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,8 +21,9 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" "{{.*}}irif.amdgcn.bc"
+// COM-SAME: "{{.*}}hip.amdgcn.bc" "{{.*}}opencl.amdgcn.bc"
+// COM-SAME: "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"

Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -81,16 +81,16 @@
 else
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

-BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+BCLibs.append({"hip.amdgcn.bc", "opencl.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
   for (auto Lib : BCLibs)
 addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);

   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D59316: [HIP-Clang] propagate -mllvm options to opt and llc

2019-03-13 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 created this revision.
ashi1 added a reviewer: yaxunl.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

I've updated the HIP ToolChain to pass OPT_mllvm options into OPT and LLC 
stages.

Also added a lit test to verify its properly passed down. All check-clang tests 
passing.


Repository:
  rC Clang

https://reviews.llvm.org/D59316

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/hip-toolchain-mllvm.hip


Index: test/Driver/hip-toolchain-mllvm.hip
===
--- test/Driver/hip-toolchain-mllvm.hip
+++ test/Driver/hip-toolchain-mllvm.hip
@@ -0,0 +1,36 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   -mllvm -amdgpu-function-calls=0 \
+// RUN:   %s 2>&1 | FileCheck %s
+
+// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu" "-emit-llvm-bc"
+// CHECK-SAME: {{.*}} "-target-cpu" "gfx803"
+// CHECK-SAME: {{.*}} "-mllvm" "-amdgpu-function-calls=0" {{.*}}
+
+// CHECK: [[OPT:".*opt"]] {{".*-gfx803-linked.*bc"}} 
"-mtriple=amdgcn-amd-amdhsa"
+// CHECK-SAME: "-mcpu=gfx803" "-amdgpu-function-calls=0"
+// CHECK-SAME: "-o" [[OPT_803_BC:".*-gfx803-optimized.*bc"]]
+
+// CHECK: [[LLC: ".*llc"]] [[OPT_803_BC]]
+// CHECK-SAME: "-mtriple=amdgcn-amd-amdhsa" "-filetype=obj"
+// CHECK-SAME: {{.*}} "-mcpu=gfx803"
+// CHECK-SAME: "-amdgpu-function-calls=0" "-o" {{".*-gfx803-.*o"}}
+
+// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu" "-emit-llvm-bc"
+// CHECK-SAME: {{.*}} "-target-cpu" "gfx900"
+// CHECK-SAME: {{.*}} "-mllvm" "-amdgpu-function-calls=0" {{.*}}
+
+// CHECK: [[OPT]] {{".*-gfx900-linked.*bc"}} "-mtriple=amdgcn-amd-amdhsa"
+// CHECK-SAME: "-mcpu=gfx900" "-amdgpu-function-calls=0"
+// CHECK-SAME: "-o" [[OPT_900_BC:".*-gfx900-optimized.*bc"]]
+
+// CHECK: [[LLC]] [[OPT_900_BC]]
+// CHECK-SAME: "-mtriple=amdgcn-amd-amdhsa" "-filetype=obj"
+// CHECK-SAME: {{.*}} "-mcpu=gfx900"
+// CHECK-SAME: "-amdgpu-function-calls=0" "-o" {{".*-gfx900-.*o"}}
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -140,6 +140,11 @@
   }
   OptArgs.push_back("-mtriple=amdgcn-amd-amdhsa");
   OptArgs.push_back(Args.MakeArgString("-mcpu=" + SubArchName));
+
+  for (const Arg *A : Args.filtered(options::OPT_mllvm)) {
+OptArgs.push_back(A->getValue(0));
+  }
+
   OptArgs.push_back("-o");
   std::string TmpFileName = C.getDriver().GetTemporaryPath(
   OutputFilePrefix.str() + "-optimized", "bc");
@@ -177,6 +182,10 @@
   if(!Features.empty())
 LlcArgs.push_back(Args.MakeArgString(MAttrString));

+  for (const Arg *A : Args.filtered(options::OPT_mllvm)) {
+LlcArgs.push_back(A->getValue(0));
+  }
+
   // Add output filename
   LlcArgs.push_back("-o");
   std::string LlcOutputFileName =


Index: test/Driver/hip-toolchain-mllvm.hip
===
--- test/Driver/hip-toolchain-mllvm.hip
+++ test/Driver/hip-toolchain-mllvm.hip
@@ -0,0 +1,36 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   -mllvm -amdgpu-function-calls=0 \
+// RUN:   %s 2>&1 | FileCheck %s
+
+// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu" "-emit-llvm-bc"
+// CHECK-SAME: {{.*}} "-target-cpu" "gfx803"
+// CHECK-SAME: {{.*}} "-mllvm" "-amdgpu-function-calls=0" {{.*}}
+
+// CHECK: [[OPT:".*opt"]] {{".*-gfx803-linked.*bc"}} "-mtriple=amdgcn-amd-amdhsa"
+// CHECK-SAME: "-mcpu=gfx803" "-amdgpu-function-calls=0"
+// CHECK-SAME: "-o" [[OPT_803_BC:".*-gfx803-optimized.*bc"]]
+
+// CHECK: [[LLC: ".*llc"]] [[OPT_803_BC]]
+// CHECK-SAME: "-mtriple=amdgcn-amd-amdhsa" "-filetype=obj"
+// CHECK-SAME: {{.*}} "-mcpu=gfx803"
+// CHECK-SAME: "-amdgpu-function-calls=0" "-o" {{".*-gfx803-.*o"}}
+
+// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu" "-emit-llvm-bc"
+// CHECK-SAME: {{.*}} "-target-cpu" "gfx900"
+// CHECK-SAME: {{.*}} "-mllvm" "-amdgpu-function-calls=0" {{.*}}
+
+// CHECK: [[OPT]] {{".*-gfx900-linked.*bc"}} "-mtriple=amdgcn-amd-amdhsa"
+// CHECK-SAME: "-mcpu=gfx900" "-amdgpu-function-calls=0"
+// CHECK-SAME: "-o" [[OPT_900_BC:".*-gfx900-optimized.*bc"]]
+
+// CHECK: [[LLC]] [[OPT_900_BC]]
+// CHECK-SAME: "-mtriple=amdgcn-amd-amdhsa" "-filetype=obj"
+// CHECK-SAME: {{.*}} "-mcpu=gfx900"
+// CHECK-SAME: "-amdgpu-function-calls=0" "-o" {{".*-gfx900-.*o"}}
Index: lib/Driver/ToolChains/HIP.cp

[PATCH] D59316: [HIP-Clang] propagate -mllvm options to opt and llc

2019-03-13 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Hi Matt, that solution will need refactoring and testing. Currently, HIP-Clang 
is following the same link flow as HCC


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D59316/new/

https://reviews.llvm.org/D59316



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D60141: [HIP-Clang] Fat binary should not be produced for non GPU code

2019-04-02 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 created this revision.
ashi1 added a reviewer: yaxunl.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Do not produce Fat binary functions for HIP when no device code is present.


Repository:
  rC Clang

https://reviews.llvm.org/D60141

Files:
  lib/CodeGen/CGCUDANV.cpp
  test/CodeGenCUDA/device-stub.cu


Index: test/CodeGenCUDA/device-stub.cu
===
--- test/CodeGenCUDA/device-stub.cu
+++ test/CodeGenCUDA/device-stub.cu
@@ -228,14 +228,21 @@
 // device-side globals, but we still need to register GPU binary.
 // Skip GPU binary string first.
 // CUDANOGLOBALS: @{{.*}} = private constant{{.*}}
-// HIPNOGLOBALS: @{{.*}} = internal constant{{.*}}
+// HIPNOGLOBALS-NOT: @{{.*}} = internal constant{{.*}}
 // NOGLOBALS-NOT: define internal void @__{{.*}}_register_globals
-// NOGLOBALS: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
-// NOGLOBALS: 
call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
+// CUDANOGLOBALS: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
+// CUDANOGLOBALS: 
call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
 // NOGLOBALS-NOT: call void @__[[PREFIX]]_register_globals
-// NOGLOBALS: define internal void @__[[PREFIX]]_module_dtor
-// NOGLOBALS: call void @__[[PREFIX]]UnregisterFatBinary
+// CUDANOGLOBALS: define internal void @__[[PREFIX]]_module_dtor
+// CUDANOGLOBALS: call void @__[[PREFIX]]UnregisterFatBinary
+
+// There should be no fat binary functions when no device-code is found for 
HIP.
+// HIPNOGLOBALS-NOT: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
+// HIPNOGLOBALS-NOT: 
call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
+// HIPNOGLOBALS-NOT: define internal void @__[[PREFIX]]_module_dtor
+// HIPNOGLOBALS-NOT: call void @__[[PREFIX]]UnregisterFatBinary
+

 // There should be no constructors/destructors if we have no GPU binary.
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_register_globals
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_module_ctor
Index: lib/CodeGen/CGCUDANV.cpp
===
--- lib/CodeGen/CGCUDANV.cpp
+++ lib/CodeGen/CGCUDANV.cpp
@@ -472,13 +472,15 @@
   StringRef CudaGpuBinaryFileName = CGM.getCodeGenOpts().CudaGpuBinaryFileName;
   if (CudaGpuBinaryFileName.empty() && !IsHIP)
 return nullptr;
+  if (IsHIP && EmittedKernels.empty() && DeviceVars.empty())
+return nullptr;

   // void __{cuda|hip}_register_globals(void* handle);
   llvm::Function *RegisterGlobalsFunc = makeRegisterGlobalsFn();
   // We always need a function to pass in as callback. Create a dummy
   // implementation if we don't need to register anything.
   if (RelocatableDeviceCode && !RegisterGlobalsFunc)
 RegisterGlobalsFunc = makeDummyFunction(getRegisterGlobalsFnTy());

   // void ** __{cuda|hip}RegisterFatBinary(void *);
   llvm::FunctionCallee RegisterFatbinFunc = CGM.CreateRuntimeFunction(


Index: test/CodeGenCUDA/device-stub.cu
===
--- test/CodeGenCUDA/device-stub.cu
+++ test/CodeGenCUDA/device-stub.cu
@@ -228,14 +228,21 @@
 // device-side globals, but we still need to register GPU binary.
 // Skip GPU binary string first.
 // CUDANOGLOBALS: @{{.*}} = private constant{{.*}}
-// HIPNOGLOBALS: @{{.*}} = internal constant{{.*}}
+// HIPNOGLOBALS-NOT: @{{.*}} = internal constant{{.*}}
 // NOGLOBALS-NOT: define internal void @__{{.*}}_register_globals
-// NOGLOBALS: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
-// NOGLOBALS: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
+// CUDANOGLOBALS: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
+// CUDANOGLOBALS: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
 // NOGLOBALS-NOT: call void @__[[PREFIX]]_register_globals
-// NOGLOBALS: define internal void @__[[PREFIX]]_module_dtor
-// NOGLOBALS: call void @__[[PREFIX]]UnregisterFatBinary
+// CUDANOGLOBALS: define internal void @__[[PREFIX]]_module_dtor
+// CUDANOGLOBALS: call void @__[[PREFIX]]UnregisterFatBinary
+
+// There should be no fat binary functions when no device-code is found for HIP.
+// HIPNOGLOBALS-NOT: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
+// HIPNOGLOBALS-NOT: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
+// HIPNOGLOBALS-NOT: define internal void @__[[PREFIX]]_module_dtor
+// HIPNOGLOBALS-NOT: call void @__[[PREFIX]]UnregisterFatBinary
+

 // There should be no constructors/destructors if we have no GPU binary.
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_register_globals
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_module_ctor
Index: lib/CodeGen/CGCUDANV.cpp
===
--- lib/CodeGen/CGCUDANV.cpp
+++ lib/CodeGen/CGCUDANV.cpp
@@ -472,13 +472,15 @@
   StringRef CudaGpuBinaryFileName =

[PATCH] D60141: [HIP-Clang] Fat binary should not be produced for non GPU code

2019-04-02 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Hi Artem, I had just committed the change. IS this change OK or should I revert 
it?


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D60141/new/

https://reviews.llvm.org/D60141



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D60141: [HIP-Clang] Fat binary should not be produced for non GPU code

2019-04-03 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Thank you, I submitted a clang-formatted fix for the if statement.


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D60141/new/

https://reviews.llvm.org/D60141



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D60513: [HIP] Use -mlink-builtin-bitcode to link device library

2019-04-10 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.
This revision is now accepted and ready to land.

LGTM


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D60513/new/

https://reviews.llvm.org/D60513



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D52673: [HIP] Remove disabled irif library

2018-09-28 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 created this revision.
ashi1 added reviewers: yaxunl, b-sumner, scchan.
Herald added a subscriber: cfe-commits.

Device Libraries has removed irif.amdgcn.bc, so we need to remove this 
requirement from HIP Toolchains. Also a few header functions need to be updated.


Repository:
  rC Clang

https://reviews.llvm.org/D52673

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/hip-device-libs.hip


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,7 +21,7 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" 
"{{.*}}irif.amdgcn.bc"
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,7 +82,7 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,7 +21,7 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" "{{.*}}irif.amdgcn.bc"
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,7 +82,7 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D52673: [HIP] Remove disabled irif library

2018-10-01 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 167741.
ashi1 added a comment.

Added diff with full context. Also, I need to find replacements for few 
functions in HIP github before this can be submitted.


https://reviews.llvm.org/D52673

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/hip-device-libs.hip


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,8 +21,8 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" 
"{{.*}}irif.amdgcn.bc"
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"

Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,15 +82,15 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
   for (auto Lib : BCLibs)
 addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);

   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,8 +21,8 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" "{{.*}}irif.amdgcn.bc"
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"

Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,15 +82,15 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
   for (auto Lib : BCLibs)
 addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);

   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D52673: [HIP] Remove disabled irif library

2018-10-04 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 168384.
ashi1 edited the summary of this revision.
Herald added a subscriber: jfb.

https://reviews.llvm.org/D52673

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/hip-device-libs.hip


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,8 +21,8 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" 
"{{.*}}irif.amdgcn.bc"
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" 
"{{.*}}hip.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"

Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,15 +82,15 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "hip.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
   for (auto Lib : BCLibs)
 addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);

   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,8 +21,8 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
-// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" "{{.*}}irif.amdgcn.bc"
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" "{{.*}}hip.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"

Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,15 +82,15 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "hip.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
   for (auto Lib : BCLibs)
 addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);

   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D52673: [HIP] Remove disabled irif library

2018-10-04 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

I've added a hip.amdgcn.bc library for the fence functions that were originally 
in irif library.


https://reviews.llvm.org/D52673



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D57977: [HIP] compile option code-object-v3 propagate to llc

2019-02-08 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 created this revision.
ashi1 added reviewers: yaxunl, kzhuravl.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

This patch allows the compile option -mcode-object-v3 to be set by default, 
unless the -mno-code-object-v3 is added to the compile options.


Repository:
  rC Clang

https://reviews.llvm.org/D57977

Files:
  lib/Driver/ToolChains/HIP.cpp


Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -157,12 +157,20 @@
 Compilation &C, const JobAction &JA, const InputInfoList &Inputs,
 const llvm::opt::ArgList &Args, llvm::StringRef SubArchName,
 llvm::StringRef OutputFilePrefix, const char *InputFileName) const {
+
+  llvm::StringRef CodeObjectVersion;
+  // Add Code Object Version
+  if (Args.hasArg(options::OPT_mno_code_object_v3))
+CodeObjectVersion = "-mattr=-code-object-v3";
+  else
+CodeObjectVersion = "-mattr=+code-object-v3";
+
   // Construct llc command.
   // FIXME: -disable-promote-alloca-to-lds is a workaround for issues in
   // AMDGPUPromoteAlloca pass which cause invalid memory access in PyTorch.
   // Remove this once the issue is fixed.
   ArgStringList LlcArgs{InputFileName, "-mtriple=amdgcn-amd-amdhsa",
-"-filetype=obj", "-mattr=-code-object-v3",
+"-filetype=obj", Args.MakeArgString(CodeObjectVersion),
 "-disable-promote-alloca-to-lds",
 Args.MakeArgString("-mcpu=" + SubArchName), "-o"};
   std::string LlcOutputFileName =


Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -157,12 +157,20 @@
 Compilation &C, const JobAction &JA, const InputInfoList &Inputs,
 const llvm::opt::ArgList &Args, llvm::StringRef SubArchName,
 llvm::StringRef OutputFilePrefix, const char *InputFileName) const {
+
+  llvm::StringRef CodeObjectVersion;
+  // Add Code Object Version
+  if (Args.hasArg(options::OPT_mno_code_object_v3))
+CodeObjectVersion = "-mattr=-code-object-v3";
+  else
+CodeObjectVersion = "-mattr=+code-object-v3";
+
   // Construct llc command.
   // FIXME: -disable-promote-alloca-to-lds is a workaround for issues in
   // AMDGPUPromoteAlloca pass which cause invalid memory access in PyTorch.
   // Remove this once the issue is fixed.
   ArgStringList LlcArgs{InputFileName, "-mtriple=amdgcn-amd-amdhsa",
-"-filetype=obj", "-mattr=-code-object-v3",
+"-filetype=obj", Args.MakeArgString(CodeObjectVersion),
 "-disable-promote-alloca-to-lds",
 Args.MakeArgString("-mcpu=" + SubArchName), "-o"};
   std::string LlcOutputFileName =
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D57977: [HIP] compile option code-object-v3 propagate to llc

2019-02-12 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 186519.
ashi1 added a comment.
Herald added a subscriber: jdoerfert.

Changed patch to us handleTargetFeatures, to consume all -m options passed into 
clang.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57977/new/

https://reviews.llvm.org/D57977

Files:
  lib/Driver/ToolChains/HIP.cpp


Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -162,9 +162,26 @@
   // AMDGPUPromoteAlloca pass which cause invalid memory access in PyTorch.
   // Remove this once the issue is fixed.
   ArgStringList LlcArgs{InputFileName, "-mtriple=amdgcn-amd-amdhsa",
-"-filetype=obj", "-mattr=-code-object-v3",
+"-filetype=obj",
 "-disable-promote-alloca-to-lds",
-Args.MakeArgString("-mcpu=" + SubArchName), "-o"};
+Args.MakeArgString("-mcpu=" + SubArchName)};
+
+  // Extract all the -m options
+  std::vector Features;
+  handleTargetFeaturesGroup(
+Args, Features, options::OPT_m_amdgpu_Features_Group);
+
+  // Add features to mattr such as code-object-v3 and xnack
+  std::string MAttrString = "-mattr=";
+  for(auto OneFeature : Features) {
+MAttrString.append(Args.MakeArgString(OneFeature));
+if (OneFeature != Features.back())
+  MAttrString.append(",");
+  }
+  LlcArgs.push_back(Args.MakeArgString(MAttrString));
+
+  // Add output filename
+  LlcArgs.push_back("-o");
   std::string LlcOutputFileName =
   C.getDriver().GetTemporaryPath(OutputFilePrefix, "o");
   const char *LlcOutputFile =


Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -162,9 +162,26 @@
   // AMDGPUPromoteAlloca pass which cause invalid memory access in PyTorch.
   // Remove this once the issue is fixed.
   ArgStringList LlcArgs{InputFileName, "-mtriple=amdgcn-amd-amdhsa",
-"-filetype=obj", "-mattr=-code-object-v3",
+"-filetype=obj",
 "-disable-promote-alloca-to-lds",
-Args.MakeArgString("-mcpu=" + SubArchName), "-o"};
+Args.MakeArgString("-mcpu=" + SubArchName)};
+
+  // Extract all the -m options
+  std::vector Features;
+  handleTargetFeaturesGroup(
+Args, Features, options::OPT_m_amdgpu_Features_Group);
+
+  // Add features to mattr such as code-object-v3 and xnack
+  std::string MAttrString = "-mattr=";
+  for(auto OneFeature : Features) {
+MAttrString.append(Args.MakeArgString(OneFeature));
+if (OneFeature != Features.back())
+  MAttrString.append(",");
+  }
+  LlcArgs.push_back(Args.MakeArgString(MAttrString));
+
+  // Add output filename
+  LlcArgs.push_back("-o");
   std::string LlcOutputFileName =
   C.getDriver().GetTemporaryPath(OutputFilePrefix, "o");
   const char *LlcOutputFile =
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D57977: [HIP] compile option code-object-v3 propagate to llc

2019-02-12 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 186528.
ashi1 added a comment.

I've added a lit test to check for options such as -mxnack/-mno-xnack, 
-msram-ecc/-mno-sram-ecc, -mcode-object-v3/-mno-code-object-v3


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57977/new/

https://reviews.llvm.org/D57977

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/hip-toolchain-features.hip


Index: test/Driver/hip-toolchain-features.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-features.hip
@@ -0,0 +1,48 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -mcode-object-v3 2>&1 | FileCheck %s -check-prefix=COV3
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -mno-code-object-v3 2>&1 | FileCheck %s -check-prefix=NOCOV3
+
+// COV3: {{.*}}clang{{.*}}"-target-feature" "+code-object-v3"
+// NOCOV3: {{.*}}clang{{.*}}"-target-feature" "-code-object-v3"
+
+
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -mxnack 2>&1 | FileCheck %s -check-prefix=XNACK
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -mno-xnack 2>&1 | FileCheck %s -check-prefix=NOXNACK
+
+// XNACK: {{.*}}clang{{.*}}"-target-feature" "+xnack"
+// NOXNACK: {{.*}}clang{{.*}}"-target-feature" "-xnack"
+
+
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -msram-ecc 2>&1 | FileCheck %s -check-prefix=SRAM
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -mno-sram-ecc 2>&1 | FileCheck %s -check-prefix=NOSRAM
+
+// SRAM: {{.*}}clang{{.*}}"-target-feature" "+sram-ecc"
+// NOSRAM: {{.*}}clang{{.*}}"-target-feature" "-sram-ecc"
+
+
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -mcode-object-v3 -mxnack -msram-ecc \
+// RUN:   2>&1 | FileCheck %s -check-prefix=ALL3
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -mno-code-object-v3 -mno-xnack -mno-sram-ecc \
+// RUN:   2>&1 | FileCheck %s -check-prefix=NOALL3
+
+// ALL3: {{.*}}clang{{.*}}"-target-feature" "+code-object-v3" 
"-target-feature" "+xnack" "-target-feature" "+sram-ecc"
+// NOALL3: {{.*}}clang{{.*}}"-target-feature" "-code-object-v3" 
"-target-feature" "-xnack" "-target-feature" "-sram-ecc"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -162,9 +162,26 @@
   // AMDGPUPromoteAlloca pass which cause invalid memory access in PyTorch.
   // Remove this once the issue is fixed.
   ArgStringList LlcArgs{InputFileName, "-mtriple=amdgcn-amd-amdhsa",
-"-filetype=obj", "-mattr=-code-object-v3",
+"-filetype=obj",
 "-disable-promote-alloca-to-lds",
-Args.MakeArgString("-mcpu=" + SubArchName), "-o"};
+Args.MakeArgString("-mcpu=" + SubArchName)};
+
+  // Extract all the -m options
+  std::vector Features;
+  handleTargetFeaturesGroup(
+Args, Features, options::OPT_m_amdgpu_Features_Group);
+
+  // Add features to mattr such as code-object-v3 and xnack
+  std::string MAttrString = "-mattr=";
+  for(auto OneFeature : Features) {
+MAttrString.append(Args.MakeArgString(OneFeature));
+if (OneFeature != Features.back())
+  MAttrString.append(",");
+  }
+  LlcArgs.push_back(Args.MakeArgString(MAttrString));
+
+  // Add output filename
+  LlcArgs.push_back("-o");
   std::string LlcOutputFileName =
   C.getDriver().GetTemporaryPath(OutputFilePrefix, "o");
   const char *LlcOutputFile =


Index: test/Driver/hip-toolchain-features.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-features.hip
@@ -0,0 +1,48 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -mcode-object-v3 2>&1 | FileCheck %s -check-prefix=COV3
+// RUN: %clang -### -c -target x86_64-linux-gnu -fgpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -mno-code-object-v3 2>&1 | FileCheck %s -check-prefix=NOCOV3
+
+// CO

[PATCH] D57977: [HIP] compile option code-object-v3 propagate to llc

2019-02-12 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Yes, but it will need this PR: 
https://github.com/ROCm-Developer-Tools/HIP/pull/910
So that the default is set.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57977/new/

https://reviews.llvm.org/D57977



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D57977: [HIP] compile option code-object-v3 propagate to llc

2019-02-19 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

This was submitted again with the fix. Thanks!


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57977/new/

https://reviews.llvm.org/D57977



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D64364: [HIP] Add GPU arch gfx1010, gfx1011, and gfx1012

2019-07-10 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.
This revision is now accepted and ready to land.

LGTM!


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D64364/new/

https://reviews.llvm.org/D64364



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D56321: [HIP][DRIVER][OFFLOAD] Do not unbundle unsupported file types

2019-01-04 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 created this revision.
ashi1 added a reviewer: yaxunl.
Herald added a subscriber: cfe-commits.

The offload bundler action should not unbundle the input file types that does 
not match the action type. This fixes an issue where .so files are unbundled 
when the action type is object files.


Repository:
  rC Clang

https://reviews.llvm.org/D56321

Files:
  lib/Driver/Driver.cpp
  test/Driver/hip-offload.hip


Index: test/Driver/hip-offload.hip
===
--- test/Driver/hip-offload.hip
+++ test/Driver/hip-offload.hip
@@ -0,0 +1,11 @@
+// RUN: touch %t.o
+// RUN: %clang --hip-link -ccc-print-bindings -target x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %t.o %S/Inputs/in.so \
+// RUN: 2>&1 | FileCheck %s
+
+// CHECK: # "amdgcn-amd-amdhsa" - "offload bundler", inputs: ["[[IN:.*o]]"], 
outputs: ["[[OBJ1:.*o]]", "[[OBJ2:.*o]]", "[[OBJ3:.*o]]"]
+// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ2]]"], 
output: "[[IMG2:.*out]]"
+// CHECK-NOT: offload bundler
+// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ3]]"], 
output: "[[IMG3:.*out]]"
+// CHECK-NOT: offload bundler
+// CHECK: # "x86_64-unknown-linux-gnu" - "GNU::Linker", inputs: ["[[OBJ1]]", 
"{{.*}}/Inputs/in.so", "[[IMG2]]", "[[IMG3]]"], output: "a.out"
Index: lib/Driver/Driver.cpp
===
--- lib/Driver/Driver.cpp
+++ lib/Driver/Driver.cpp
@@ -2323,6 +2323,18 @@
   // If this is an unbundling action use it as is for each CUDA toolchain.
   if (auto *UA = dyn_cast(HostAction)) {
 CudaDeviceActions.clear();
+auto *IA = cast(UA->getInputs().back());
+std::string FileName = IA->getInputArg().getAsString(Args);
+// Check if the type of the file is the same as the action. Do not
+// unbundle it if it is not. Do not unbundle .so files, for example,
+// which are not object files.
+if (IA->getType() == types::TY_Object &&
+(!llvm::sys::path::has_extension(FileName) ||
+ types::lookupTypeForExtension(
+ llvm::sys::path::extension(FileName).drop_front()) !=
+ types::TY_Object))
+  return ABRT_Inactive;
+
 for (auto Arch : GpuArchList) {
   CudaDeviceActions.push_back(UA);
   UA->registerDependentActionInfo(ToolChains[0], 
CudaArchToString(Arch),


Index: test/Driver/hip-offload.hip
===
--- test/Driver/hip-offload.hip
+++ test/Driver/hip-offload.hip
@@ -0,0 +1,11 @@
+// RUN: touch %t.o
+// RUN: %clang --hip-link -ccc-print-bindings -target x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %t.o %S/Inputs/in.so \
+// RUN: 2>&1 | FileCheck %s
+
+// CHECK: # "amdgcn-amd-amdhsa" - "offload bundler", inputs: ["[[IN:.*o]]"], outputs: ["[[OBJ1:.*o]]", "[[OBJ2:.*o]]", "[[OBJ3:.*o]]"]
+// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ2]]"], output: "[[IMG2:.*out]]"
+// CHECK-NOT: offload bundler
+// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ3]]"], output: "[[IMG3:.*out]]"
+// CHECK-NOT: offload bundler
+// CHECK: # "x86_64-unknown-linux-gnu" - "GNU::Linker", inputs: ["[[OBJ1]]", "{{.*}}/Inputs/in.so", "[[IMG2]]", "[[IMG3]]"], output: "a.out"
Index: lib/Driver/Driver.cpp
===
--- lib/Driver/Driver.cpp
+++ lib/Driver/Driver.cpp
@@ -2323,6 +2323,18 @@
   // If this is an unbundling action use it as is for each CUDA toolchain.
   if (auto *UA = dyn_cast(HostAction)) {
 CudaDeviceActions.clear();
+auto *IA = cast(UA->getInputs().back());
+std::string FileName = IA->getInputArg().getAsString(Args);
+// Check if the type of the file is the same as the action. Do not
+// unbundle it if it is not. Do not unbundle .so files, for example,
+// which are not object files.
+if (IA->getType() == types::TY_Object &&
+(!llvm::sys::path::has_extension(FileName) ||
+ types::lookupTypeForExtension(
+ llvm::sys::path::extension(FileName).drop_front()) !=
+ types::TY_Object))
+  return ABRT_Inactive;
+
 for (auto Arch : GpuArchList) {
   CudaDeviceActions.push_back(UA);
   UA->registerDependentActionInfo(ToolChains[0], CudaArchToString(Arch),
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D56321: [HIP][DRIVER][OFFLOAD] Do not unbundle unsupported file types

2019-01-04 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 180289.

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D56321/new/

https://reviews.llvm.org/D56321

Files:
  lib/Driver/Driver.cpp
  test/Driver/hip-link-shared-library.hip


Index: test/Driver/hip-link-shared-library.hip
===
--- test/Driver/hip-link-shared-library.hip
+++ test/Driver/hip-link-shared-library.hip
@@ -0,0 +1,11 @@
+// RUN: touch %t.o
+// RUN: %clang --hip-link -ccc-print-bindings -target x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %t.o %S/Inputs/in.so \
+// RUN: 2>&1 | FileCheck %s
+
+// CHECK: # "amdgcn-amd-amdhsa" - "offload bundler", inputs: ["[[IN:.*o]]"], 
outputs: ["[[OBJ1:.*o]]", "[[OBJ2:.*o]]", "[[OBJ3:.*o]]"]
+// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ2]]"], 
output: "[[IMG2:.*out]]"
+// CHECK-NOT: offload bundler
+// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ3]]"], 
output: "[[IMG3:.*out]]"
+// CHECK-NOT: offload bundler
+// CHECK: # "x86_64-unknown-linux-gnu" - "GNU::Linker", inputs: ["[[OBJ1]]", 
"{{.*}}/Inputs/in.so", "[[IMG2]]", "[[IMG3]]"], output: "a.out"
Index: lib/Driver/Driver.cpp
===
--- lib/Driver/Driver.cpp
+++ lib/Driver/Driver.cpp
@@ -2323,6 +2323,18 @@
   // If this is an unbundling action use it as is for each CUDA toolchain.
   if (auto *UA = dyn_cast(HostAction)) {
 CudaDeviceActions.clear();
+auto *IA = cast(UA->getInputs().back());
+std::string FileName = IA->getInputArg().getAsString(Args);
+// Check if the type of the file is the same as the action. Do not
+// unbundle it if it is not. Do not unbundle .so files, for example,
+// which are not object files.
+if (IA->getType() == types::TY_Object &&
+(!llvm::sys::path::has_extension(FileName) ||
+ types::lookupTypeForExtension(
+ llvm::sys::path::extension(FileName).drop_front()) !=
+ types::TY_Object))
+  return ABRT_Inactive;
+
 for (auto Arch : GpuArchList) {
   CudaDeviceActions.push_back(UA);
   UA->registerDependentActionInfo(ToolChains[0], 
CudaArchToString(Arch),


Index: test/Driver/hip-link-shared-library.hip
===
--- test/Driver/hip-link-shared-library.hip
+++ test/Driver/hip-link-shared-library.hip
@@ -0,0 +1,11 @@
+// RUN: touch %t.o
+// RUN: %clang --hip-link -ccc-print-bindings -target x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %t.o %S/Inputs/in.so \
+// RUN: 2>&1 | FileCheck %s
+
+// CHECK: # "amdgcn-amd-amdhsa" - "offload bundler", inputs: ["[[IN:.*o]]"], outputs: ["[[OBJ1:.*o]]", "[[OBJ2:.*o]]", "[[OBJ3:.*o]]"]
+// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ2]]"], output: "[[IMG2:.*out]]"
+// CHECK-NOT: offload bundler
+// CHECK: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ3]]"], output: "[[IMG3:.*out]]"
+// CHECK-NOT: offload bundler
+// CHECK: # "x86_64-unknown-linux-gnu" - "GNU::Linker", inputs: ["[[OBJ1]]", "{{.*}}/Inputs/in.so", "[[IMG2]]", "[[IMG3]]"], output: "a.out"
Index: lib/Driver/Driver.cpp
===
--- lib/Driver/Driver.cpp
+++ lib/Driver/Driver.cpp
@@ -2323,6 +2323,18 @@
   // If this is an unbundling action use it as is for each CUDA toolchain.
   if (auto *UA = dyn_cast(HostAction)) {
 CudaDeviceActions.clear();
+auto *IA = cast(UA->getInputs().back());
+std::string FileName = IA->getInputArg().getAsString(Args);
+// Check if the type of the file is the same as the action. Do not
+// unbundle it if it is not. Do not unbundle .so files, for example,
+// which are not object files.
+if (IA->getType() == types::TY_Object &&
+(!llvm::sys::path::has_extension(FileName) ||
+ types::lookupTypeForExtension(
+ llvm::sys::path::extension(FileName).drop_front()) !=
+ types::TY_Object))
+  return ABRT_Inactive;
+
 for (auto Arch : GpuArchList) {
   CudaDeviceActions.push_back(UA);
   UA->registerDependentActionInfo(ToolChains[0], CudaArchToString(Arch),
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D56321: [HIP][DRIVER][OFFLOAD] Do not unbundle unsupported file types

2019-01-04 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

I've commit the changes, but forgot to tag the proper Diff link in the commit 
message. I just updated it.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D56321/new/

https://reviews.llvm.org/D56321



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D68300: [HIP] Add option -fno-link-builtin-bitcode to disable linking device lib

2019-10-02 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

LGTM thank you




Comment at: include/clang/Driver/Options.td:606
+def flink_builtin_bitcode : Flag<["-"], "flink-builtin-bitcode">,
+  Flags<[CC1Option]>, HelpText<"Link builtin bitcode for HIP device 
compilation.">;
+def fno_link_builtin_bitcode : Flag<["-"], "fno-link-builtin-bitcode">;

Since this is a more generic approach, we won't need to specify HIP ?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D68300/new/

https://reviews.llvm.org/D68300



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D68300: [HIP] Use option -nogpulib to disable linking device lib

2019-10-03 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.

LGTM - Thanks for generalizing


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D68300/new/

https://reviews.llvm.org/D68300



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D48493: [HIP] Support flush denorms bitcode

2018-06-27 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 153124.
ashi1 added a comment.

I've changed the string to a more meaningful name, and also added a lit test to 
check that oclc_daz_opt_on.amdgcn.bc is used.


https://reviews.llvm.org/D48493

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/irif.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/ockl.amdgcn.bc
  
test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_correctly_rounded_sqrt_on.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_daz_opt_off.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_daz_opt_on.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_finite_only_off.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_isa_version_803.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_isa_version_900.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_unsafe_math_off.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/ocml.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/opencl.amdgcn.bc
  test/Driver/hip-toolchain-flush-denorms.hip


Index: test/Driver/hip-toolchain-flush-denorms.hip
===
--- test/Driver/hip-toolchain-flush-denorms.hip
+++ test/Driver/hip-toolchain-flush-denorms.hip
@@ -0,0 +1,20 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx803-linked-{{.*}}bc"
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }


Index: test/Driver/hip-toolchain-flush-denorms.hip
===
--- test/Driver/hip-toolchain-flush-denorms.hip
+++ test/Driver/hip-toolchain-flush-denorms.hip
@@ -0,0 +1,20 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx803-linked-{{.*}}bc"
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
___
cfe-commits mailing li

[PATCH] D48493: [HIP] Support flush denorms bitcode

2018-06-27 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 153127.
ashi1 added a comment.

Added diff with full context.


https://reviews.llvm.org/D48493

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/irif.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/ockl.amdgcn.bc
  
test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_correctly_rounded_sqrt_on.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_daz_opt_off.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_daz_opt_on.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_finite_only_off.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_isa_version_803.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_isa_version_900.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_unsafe_math_off.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/ocml.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/opencl.amdgcn.bc
  test/Driver/hip-toolchain-flush-denorms.hip


Index: test/Driver/hip-toolchain-flush-denorms.hip
===
--- test/Driver/hip-toolchain-flush-denorms.hip
+++ test/Driver/hip-toolchain-flush-denorms.hip
@@ -0,0 +1,20 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx803-linked-{{.*}}bc"
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,16 +75,22 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
   for (auto Lib : BCLibs)
 addBCLib(C, Args, CmdArgs, LibraryPaths, Lib);

   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   std::string TmpName =


Index: test/Driver/hip-toolchain-flush-denorms.hip
===
--- test/Driver/hip-toolchain-flush-denorms.hip
+++ test/Driver/hip-toolchain-flush-denorms.hip
@@ -0,0 +1,20 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx803-linked-{{.*}}bc"
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,16 +75,22 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});

[PATCH] D48493: [HIP] Support flush denorms bitcode

2018-06-27 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 153131.
ashi1 added a comment.

Fix diff file


https://reviews.llvm.org/D48493

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/irif.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/ockl.amdgcn.bc
  
test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_correctly_rounded_sqrt_on.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_daz_opt_off.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_daz_opt_on.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_finite_only_off.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_isa_version_803.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_isa_version_900.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/oclc_unsafe_math_off.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/ocml.amdgcn.bc
  test/Driver/Inputs/hip_multiple_inputs/dev_lib/opencl.amdgcn.bc
  test/Driver/hip-toolchain-flush-denorms.hip


Index: test/Driver/hip-toolchain-flush-denorms.hip
===
--- test/Driver/hip-toolchain-flush-denorms.hip
+++ test/Driver/hip-toolchain-flush-denorms.hip
@@ -0,0 +1,20 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx803-linked-{{.*}}bc"
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }


Index: test/Driver/hip-toolchain-flush-denorms.hip
===
--- test/Driver/hip-toolchain-flush-denorms.hip
+++ test/Driver/hip-toolchain-flush-denorms.hip
@@ -0,0 +1,20 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx803-linked-{{.*}}bc"
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D48493: [HIP] Support flush denorms bitcode

2018-06-27 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 153136.
ashi1 added a comment.

I've updated. Moved the bitcode files into hip_dev_lib and added test for both 
on and off flush denorms to zero option.


https://reviews.llvm.org/D48493

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/Inputs/hip_dev_lib/irif.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/ockl.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_correctly_rounded_sqrt_on.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_daz_opt_off.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_daz_opt_on.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_finite_only_off.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_isa_version_803.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_isa_version_900.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_unsafe_math_off.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/ocml.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/opencl.amdgcn.bc
  test/Driver/hip-toolchain-flush-denorms-off.hip
  test/Driver/hip-toolchain-flush-denorms-on.hip


Index: test/Driver/hip-toolchain-flush-denorms-on.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-flush-denorms-on.hip
@@ -0,0 +1,15 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: test/Driver/hip-toolchain-flush-denorms-off.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-flush-denorms-off.hip
@@ -0,0 +1,14 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"hip.amdgcn.bc", "opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }


Index: test/Driver/hip-toolchain-flush-denorms-on.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-flush-denorms-on.hip
@@ -0,0 +1,15 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: test/Driver/hip-toolchain-flush-denorms-off.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-flush-denorms-off.hip
@@ -0,0 +1,14 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVe

[PATCH] D48493: [HIP] Support flush denorms bitcode

2018-06-27 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 153140.

https://reviews.llvm.org/D48493

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/Inputs/hip_dev_lib/irif.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/ockl.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_correctly_rounded_sqrt_on.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_daz_opt_off.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_daz_opt_on.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_finite_only_off.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_isa_version_803.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_isa_version_900.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_unsafe_math_off.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/ocml.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/opencl.amdgcn.bc
  test/Driver/hip-toolchain-flush-denorms-off.hip
  test/Driver/hip-toolchain-flush-denorms-on.hip


Index: test/Driver/hip-toolchain-flush-denorms-on.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-flush-denorms-on.hip
@@ -0,0 +1,15 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: test/Driver/hip-toolchain-flush-denorms-off.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-flush-denorms-off.hip
@@ -0,0 +1,14 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"hip.amdgcn.bc", "opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }


Index: test/Driver/hip-toolchain-flush-denorms-on.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-flush-denorms-on.hip
@@ -0,0 +1,15 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: test/Driver/hip-toolchain-flush-denorms-off.hip
===
--- /dev/null
+++ test/Driver/hip-toolchain-flush-denorms-off.hip
@@ -0,0 +1,14 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+
+// CHECK: [[LLVM_LINK:"*.llvm-link"]]
+// CHECK-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
+// CHECK-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+

[PATCH] D48493: [HIP] Support flush denorms bitcode

2018-06-27 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 153146.
ashi1 added a comment.

Merged checks for flush denorm on and off into single test hip-device-libs.hip


https://reviews.llvm.org/D48493

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/Inputs/hip_dev_lib/irif.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/ockl.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_correctly_rounded_sqrt_on.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_daz_opt_off.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_daz_opt_on.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_finite_only_off.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_isa_version_803.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_isa_version_900.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/oclc_unsafe_math_off.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/ocml.amdgcn.bc
  test/Driver/Inputs/hip_dev_lib/opencl.amdgcn.bc
  test/Driver/hip-device-libs.hip


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -0,0 +1,27 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// Test flush-denormals-to-zero enabled uses oclc_daz_opt_on
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s --check-prefixes=COM,FLUSHD
+
+// Test flush-denormals-to-zero disabled uses oclc_daz_opt_off
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s --check-prefixes=COM,NOFLUSHD
+
+
+// COM: [[LLVM_LINK:"*.llvm-link"]]
+// FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
+// COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
+
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_daz_opt_off.amdgcn.bc",
+   FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
"oclc_unsafe_math_off.amdgcn.bc", ISAVerBC});
   }


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -0,0 +1,27 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// Test flush-denormals-to-zero enabled uses oclc_daz_opt_on
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   -fcuda-flush-denormals-to-zero \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s --check-prefixes=COM,FLUSHD
+
+// Test flush-denormals-to-zero disabled uses oclc_daz_opt_off
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_dev_lib \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s --check-prefixes=COM,NOFLUSHD
+
+
+// COM: [[LLVM_LINK:"*.llvm-link"]]
+// FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
+// NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
+// COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
+
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -75,10 +75,16 @@
 std::string ISAVerBC =
 "oclc_isa_version_" + SubArchName.drop_front(3).str() + ".amdgcn.bc";

+llvm::StringRef FlushDenormalControlBC;
+if (Args.hasArg(options::OPT_fcuda_flush_denormals_to_zero))
+  FlushDenormalControlBC = "oclc_daz_opt_on.amdgcn.bc";
+else
+  FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";
+
 BCLibs.append({"opencl.amdgcn.bc",
"ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
-   "oclc_

[PATCH] D48667: [HIP] Fix ordering of device-lib linking

2018-06-27 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 created this revision.
ashi1 added reviewers: yaxunl, b-sumner.
ashi1 added projects: clang, AMDGPU.
Herald added a subscriber: cfe-commits.

Should link the bitcodes with caller functions before callee functions.


Repository:
  rC Clang

https://reviews.llvm.org/D48667

Files:
  lib/Driver/ToolChains/HIP.cpp


Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,7 +82,7 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",


Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,7 +82,7 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D48667: [HIP] Fix ordering of device-lib linking

2018-06-27 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 updated this revision to Diff 153154.
ashi1 added a comment.

Updated diff with a lit test.


https://reviews.llvm.org/D48667

Files:
  lib/Driver/ToolChains/HIP.cpp
  test/Driver/hip-device-libs.hip


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,6 +21,7 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" 
"{{.*}}irif.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,7 +82,7 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",


Index: test/Driver/hip-device-libs.hip
===
--- test/Driver/hip-device-libs.hip
+++ test/Driver/hip-device-libs.hip
@@ -21,6 +21,7 @@


 // COM: [[LLVM_LINK:"*.llvm-link"]]
+// COM-SAME: {{.*}} "{{.*}}ocml.amdgcn.bc" "{{.*}}ockl.amdgcn.bc" "{{.*}}irif.amdgcn.bc"
 // FLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_on.amdgcn.bc"
 // NOFLUSHD-SAME: {{.*}} "{{.*}}oclc_daz_opt_off.amdgcn.bc"
 // COM-SAME: {{.*}} "-o" "{{.*}}-gfx900-linked-{{.*bc}}"
Index: lib/Driver/ToolChains/HIP.cpp
===
--- lib/Driver/ToolChains/HIP.cpp
+++ lib/Driver/ToolChains/HIP.cpp
@@ -82,7 +82,7 @@
   FlushDenormalControlBC = "oclc_daz_opt_off.amdgcn.bc";

 BCLibs.append({"opencl.amdgcn.bc",
-   "ockl.amdgcn.bc", "irif.amdgcn.bc", "ocml.amdgcn.bc",
+   "ocml.amdgcn.bc", "ockl.amdgcn.bc", "irif.amdgcn.bc",
"oclc_finite_only_off.amdgcn.bc",
FlushDenormalControlBC,
"oclc_correctly_rounded_sqrt_on.amdgcn.bc",
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D68665: [HIP] Fix -save-temps

2019-10-09 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.

LGTM


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D68665/new/

https://reviews.llvm.org/D68665



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D81627: [HIP] Do not call opt/llc for -fno-gpu-rdc

2020-06-15 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.

LGTM, thank you for splitting the cuda-phases from hip-phases, and opening up a 
follow-up patch for RDC case.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D81627/new/

https://reviews.llvm.org/D81627



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D81861: [HIP] Do not use llvm-link/opt/llc for -fgpu-rdc

2020-06-15 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Thank you for this patch, it looks good, and I have a few minor 
questions/comments.




Comment at: clang/test/Driver/hip-phases.hip:34
+// RDC-DAG: [[P6:[0-9]+]]: backend, {[[P5]]}, ir, (device-[[T]], [[ARCH]])
+// RDC-DAG: [[P10:[0-9]+]]: linker, {[[P6]]}, image, (device-hip, [[ARCH]])
 

should also use device-[[T]]? I think there are several locations here using 
device-hip instead of device[[T]].



Comment at: clang/test/Driver/hip-phases.hip:253
+// L2-DAG: [[P0:[0-9]+]]: input, "{{.*}}obj1.o", object, (host-[[T:hip]])
+// RL2-DAG: [[P1:[0-9]+]]: clang-offload-unbundler, {[[P0]]}, object, 
(host-[[T:hip]])
+// L2-DAG: [[P2:[0-9]+]]: input, "{{.*}}obj2.o", object, (host-[[T:hip]])

[[T]] is defined everytime here, should probably use [[T]] in subsequent checks?



Comment at: clang/test/Driver/hip-save-temps.hip:58
+
+// -fgpu-rdc link
+// RUN: touch %T/obj1.o

Should this link test be moved into a separate file? Also to cover without -o? 
I may also be adding more tests to this case for static lib generation too.



Comment at: clang/test/Driver/hip-toolchain-rdc.hip:10
 // RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/lib2 \
-// RUN:   -fuse-ld=lld -fgpu-rdc \
+// RUN:   -fuse-ld=lld -fgpu-rdc -nogpuinc \
 // RUN:   %S/Inputs/hip_multiple_inputs/a.cu \

What is the difference between this file and hip-toolchain-rdc-separate.hip?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D81861/new/

https://reviews.llvm.org/D81861



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D81861: [HIP] Do not use llvm-link/opt/llc for -fgpu-rdc

2020-06-15 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.
This revision is now accepted and ready to land.

LGTM, ready to submit if @tra and @arsenm are okay with this patch.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D81861/new/

https://reviews.llvm.org/D81861



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D83145: [HIP] Use default triple in llvm-mc for system ld

2020-07-07 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rGc64bb3f7367a: [HIP] Use default triple in llvm-mc for system 
ld (authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D83145/new/

https://reviews.llvm.org/D83145

Files:
  clang/lib/Driver/ToolChains/HIP.cpp
  clang/test/Driver/hip-link-save-temps.hip
  clang/test/Driver/hip-toolchain-rdc-separate.hip
  clang/test/Driver/hip-toolchain-rdc-static-lib.hip
  clang/test/Driver/hip-toolchain-rdc.hip


Index: clang/test/Driver/hip-toolchain-rdc.hip
===
--- clang/test/Driver/hip-toolchain-rdc.hip
+++ clang/test/Driver/hip-toolchain-rdc.hip
@@ -90,8 +90,7 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-triple" "amdgcn-amd-amdhsa"
-// CHECK-SAME: "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
 
 // output the executable
 // CHECK: [[LD:".*ld.*"]] {{.*}}"-o" "a.out" {{.*}} [[A_OBJ_HOST]] 
[[B_OBJ_HOST]] [[OBJBUNDLE]]
Index: clang/test/Driver/hip-toolchain-rdc-static-lib.hip
===
--- clang/test/Driver/hip-toolchain-rdc-static-lib.hip
+++ clang/test/Driver/hip-toolchain-rdc-static-lib.hip
@@ -78,7 +78,6 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-triple" "amdgcn-amd-amdhsa"
-// CHECK-SAME: "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
 
 // CHECK: [[AR:".*llvm-ar.*"]] "rcsD" "{{.*}}.out" [[A_OBJ_HOST]] 
[[B_OBJ_HOST]] [[OBJBUNDLE]]
Index: clang/test/Driver/hip-toolchain-rdc-separate.hip
===
--- clang/test/Driver/hip-toolchain-rdc-separate.hip
+++ clang/test/Driver/hip-toolchain-rdc-separate.hip
@@ -122,8 +122,7 @@
 // LINK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // LINK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// LINK: {{".*llvm-mc.*"}} "-triple" "amdgcn-amd-amdhsa" "-o"
-// LINK-SAME: "[[OBJBUNDLE:.*o]]" "{{.*}}.mcin" "--filetype=obj"
+// LINK: {{".*llvm-mc.*"}} "-o" "[[OBJBUNDLE:.*o]]" "{{.*}}.mcin" 
"--filetype=obj"
 
 // LINK: [[LD:".*ld.*"]] {{.*}} "-o" "a.out" {{.*}} "[[A_OBJ_HOST]]"
 // LINK-SAME: "[[B_OBJ_HOST]]" "[[OBJBUNDLE]]"
Index: clang/test/Driver/hip-link-save-temps.hip
===
--- clang/test/Driver/hip-link-save-temps.hip
+++ clang/test/Driver/hip-link-save-temps.hip
@@ -45,8 +45,7 @@
 // CHECK-SAME: "-o" "a.out-hip-amdgcn-amd-amdhsa-gfx900" 
"obj1-hip-amdgcn-amd-amdhsa-gfx900.o" "obj2-hip-amdgcn-amd-amdhsa-gfx900.o"
 // CHECK: "{{.*lld.*}}" {{.*}} "-plugin-opt=-amdgpu-internalize-symbols"
 // CHECK-SAME: "-o" "a.out-hip-amdgcn-amd-amdhsa-gfx906" 
"obj1-hip-amdgcn-amd-amdhsa-gfx906.o" "obj2-hip-amdgcn-amd-amdhsa-gfx906.o"
-// CHECK: {{".*llvm-mc.*"}} "-triple" "amdgcn-amd-amdhsa" "-o"
-// CHECK-SAME: "[[OBJBUNDLE:.*.o]]" "{{.*}}.mcin" "--filetype=obj"
+// CHECK: {{".*llvm-mc.*"}} "-o" "[[OBJBUNDLE:.*.o]]" "{{.*}}.mcin" 
"--filetype=obj"
 // OUT: "{{.*ld.*}}" {{.*}} "-o" "executable" {{.*}} "[[OBJBUNDLE]]"
 // NOUT: "{{.*ld.*}}" {{.*}} "-o" "a.out" {{.*}} "[[OBJBUNDLE]]"
 // SLO: "{{.*llvm-ar.*}}" "rcsD" "libTest.a" {{.*}} "[[OBJBUNDLE]]"
Index: clang/lib/Driver/ToolChains/HIP.cpp
===
--- clang/lib/Driver/ToolChains/HIP.cpp
+++ clang/lib/Driver/ToolChains/HIP.cpp
@@ -193,8 +193,7 @@
 
   Objf << ObjBuffer;
 
-  ArgStringList McArgs{"-triple", Args.MakeArgString(TC.getTripleString()),
-   "-o",  Output.getFilename(),
+  ArgStringList McArgs{"-o",  Output.getFilename(),
McinFile,  "--filetype=obj"};
   const char *Mc = Args.MakeArgString(TC.GetProgramPath("llvm-mc"));
   C.addCommand(std::make_unique(JA, *this, 
ResponseFileSupport::None(),


Index: clang/test/Driver/hip-toolchain-rdc.hip
===
--- clang/test/Driver/hip-toolchain-rdc.hip
+++ clang/test/Driver/hip-toolchain-rdc.hip
@@ -90,8 +90,7 @@
 // CHECK-SAME: "-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" "-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-triple" "amdgcn-amd-amdhsa"
-// CHECK-S

[PATCH] D83145: [HIP] Use default triple in llvm-mc for system ld

2020-07-07 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was not accepted when it landed; it landed in state "Needs 
Review".
This revision was automatically updated to reflect the committed changes.
Closed by commit rGc64bb3f7367a: [HIP] Use default triple in llvm-mc for system 
ld (authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D83145/new/

https://reviews.llvm.org/D83145

Files:
  clang/lib/Driver/ToolChains/HIP.cpp
  clang/test/Driver/hip-link-save-temps.hip
  clang/test/Driver/hip-toolchain-rdc-separate.hip
  clang/test/Driver/hip-toolchain-rdc-static-lib.hip
  clang/test/Driver/hip-toolchain-rdc.hip


Index: clang/test/Driver/hip-toolchain-rdc.hip
===
--- clang/test/Driver/hip-toolchain-rdc.hip
+++ clang/test/Driver/hip-toolchain-rdc.hip
@@ -90,8 +90,7 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-triple" "amdgcn-amd-amdhsa"
-// CHECK-SAME: "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
 
 // output the executable
 // CHECK: [[LD:".*ld.*"]] {{.*}}"-o" "a.out" {{.*}} [[A_OBJ_HOST]] 
[[B_OBJ_HOST]] [[OBJBUNDLE]]
Index: clang/test/Driver/hip-toolchain-rdc-static-lib.hip
===
--- clang/test/Driver/hip-toolchain-rdc-static-lib.hip
+++ clang/test/Driver/hip-toolchain-rdc-static-lib.hip
@@ -78,7 +78,6 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-triple" "amdgcn-amd-amdhsa"
-// CHECK-SAME: "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
 
 // CHECK: [[AR:".*llvm-ar.*"]] "rcsD" "{{.*}}.out" [[A_OBJ_HOST]] 
[[B_OBJ_HOST]] [[OBJBUNDLE]]
Index: clang/test/Driver/hip-toolchain-rdc-separate.hip
===
--- clang/test/Driver/hip-toolchain-rdc-separate.hip
+++ clang/test/Driver/hip-toolchain-rdc-separate.hip
@@ -122,8 +122,7 @@
 // LINK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // LINK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// LINK: {{".*llvm-mc.*"}} "-triple" "amdgcn-amd-amdhsa" "-o"
-// LINK-SAME: "[[OBJBUNDLE:.*o]]" "{{.*}}.mcin" "--filetype=obj"
+// LINK: {{".*llvm-mc.*"}} "-o" "[[OBJBUNDLE:.*o]]" "{{.*}}.mcin" 
"--filetype=obj"
 
 // LINK: [[LD:".*ld.*"]] {{.*}} "-o" "a.out" {{.*}} "[[A_OBJ_HOST]]"
 // LINK-SAME: "[[B_OBJ_HOST]]" "[[OBJBUNDLE]]"
Index: clang/test/Driver/hip-link-save-temps.hip
===
--- clang/test/Driver/hip-link-save-temps.hip
+++ clang/test/Driver/hip-link-save-temps.hip
@@ -45,8 +45,7 @@
 // CHECK-SAME: "-o" "a.out-hip-amdgcn-amd-amdhsa-gfx900" 
"obj1-hip-amdgcn-amd-amdhsa-gfx900.o" "obj2-hip-amdgcn-amd-amdhsa-gfx900.o"
 // CHECK: "{{.*lld.*}}" {{.*}} "-plugin-opt=-amdgpu-internalize-symbols"
 // CHECK-SAME: "-o" "a.out-hip-amdgcn-amd-amdhsa-gfx906" 
"obj1-hip-amdgcn-amd-amdhsa-gfx906.o" "obj2-hip-amdgcn-amd-amdhsa-gfx906.o"
-// CHECK: {{".*llvm-mc.*"}} "-triple" "amdgcn-amd-amdhsa" "-o"
-// CHECK-SAME: "[[OBJBUNDLE:.*.o]]" "{{.*}}.mcin" "--filetype=obj"
+// CHECK: {{".*llvm-mc.*"}} "-o" "[[OBJBUNDLE:.*.o]]" "{{.*}}.mcin" 
"--filetype=obj"
 // OUT: "{{.*ld.*}}" {{.*}} "-o" "executable" {{.*}} "[[OBJBUNDLE]]"
 // NOUT: "{{.*ld.*}}" {{.*}} "-o" "a.out" {{.*}} "[[OBJBUNDLE]]"
 // SLO: "{{.*llvm-ar.*}}" "rcsD" "libTest.a" {{.*}} "[[OBJBUNDLE]]"
Index: clang/lib/Driver/ToolChains/HIP.cpp
===
--- clang/lib/Driver/ToolChains/HIP.cpp
+++ clang/lib/Driver/ToolChains/HIP.cpp
@@ -193,8 +193,7 @@
 
   Objf << ObjBuffer;
 
-  ArgStringList McArgs{"-triple", Args.MakeArgString(TC.getTripleString()),
-   "-o",  Output.getFilename(),
+  ArgStringList McArgs{"-o",  Output.getFilename(),
McinFile,  "--filetype=obj"};
   const char *Mc = Args.MakeArgString(TC.GetProgramPath("llvm-mc"));
   C.addCommand(std::make_unique(JA, *this, 
ResponseFileSupport::None(),


Index: clang/test/Driver/hip-toolchain-rdc.hip
===
--- clang/test/Driver/hip-toolchain-rdc.hip
+++ clang/test/Driver/hip-toolchain-rdc.hip
@@ -90,8 +90,7 @@
 // CHECK-SAME: "-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" "-outputs=[[BUNDLE:.

[PATCH] D79830: Add support of __builtin_expect_with_probability

2020-06-22 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added subscribers: yaxunl, ashi1.
ashi1 added a comment.

Hi, I am getting a compiler error due to this patch. I am using cmake command: 
cmake ../llvm -DCMAKE_BUILD_TYPE=Release 
-DLLVM_ENABLE_PROJECTS="clang;lld;clang-tools-extra" 
-DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" -DLLVM_ENABLE_ASSERTIONS=1 . Could you 
please take a look?

**Error:**
/root/llvm-project/llvm/lib/Transforms/Scalar/LowerExpectIntrinsic.cpp: In 
function 'std::tuple 
getBranchWeight(llvm::Intrinsic::ID, llvm::CallInst*, int)':
/root/llvm-project/llvm/lib/Transforms/Scalar/LowerExpectIntrinsic.cpp:62:53: 
error: converting to 'std::tuple' from initializer 
list would use explicit constructor 'constexpr std::tuple<_T1, 
_T2>::tuple(_U1&&, _U2&&) [with _U1 = llvm:🆑:opt&; _U2 = 
llvm:🆑:opt&;  = void; _T1 = unsigned int; 
_T2 = unsigned int]'

  return {LikelyBranchWeight, UnlikelyBranchWeight};
  ^

/root/llvm-project/llvm/lib/Transforms/Scalar/LowerExpectIntrinsic.cpp:74:33: 
error: converting to 'std::tuple' from initializer 
list would use explicit constructor 'constexpr std::tuple<_T1, 
_T2>::tuple(_U1&&, _U2&&) [with _U1 = unsigned int&; _U2 = unsigned int&; 
 = void; _T1 = unsigned int; _T2 = unsigned int]'

  return {LikelyBW, UnlikelyBW};
  ^


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D79830/new/

https://reviews.llvm.org/D79830



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D81963: [HIP] Move HIP Linking Logic into HIP ToolChain

2020-06-22 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rG77df5a8283ed: [HIP] Move HIP Linking Logic into HIP 
ToolChain (authored by ashi1).
Herald added a subscriber: cfe-commits.

Changed prior to commit:
  https://reviews.llvm.org/D81963?vs=271210&id=272525#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D81963/new/

https://reviews.llvm.org/D81963

Files:
  clang/lib/Driver/Driver.cpp
  clang/lib/Driver/ToolChains/CommonArgs.cpp
  clang/lib/Driver/ToolChains/CommonArgs.h
  clang/lib/Driver/ToolChains/Gnu.cpp
  clang/lib/Driver/ToolChains/HIP.cpp
  clang/lib/Driver/ToolChains/HIP.h
  clang/test/Driver/hip-binding.hip
  clang/test/Driver/hip-link-save-temps.hip
  clang/test/Driver/hip-link-shared-library.hip
  clang/test/Driver/hip-phases.hip
  clang/test/Driver/hip-save-temps.hip
  clang/test/Driver/hip-toolchain-rdc-separate.hip
  clang/test/Driver/hip-toolchain-rdc.hip

Index: clang/test/Driver/hip-toolchain-rdc.hip
===
--- clang/test/Driver/hip-toolchain-rdc.hip
+++ clang/test/Driver/hip-toolchain-rdc.hip
@@ -12,7 +12,23 @@
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck %s
 
-// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// emit objects for host side path
+// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-emit-obj"
+// CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
+// CHECK-SAME: {{.*}} "-o" [[A_OBJ_HOST:".*o"]] "-x" "hip"
+// CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
+
+// CHECK: [[CLANG]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-emit-obj"
+// CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
+// CHECK-SAME: {{.*}} "-o" [[B_OBJ_HOST:".*o"]] "-x" "hip"
+// CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
+
+// generate image for device side path on gfx803
+// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
 // CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
@@ -21,7 +37,7 @@
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" [[A_BC1:".*bc"]] "-x" "hip"
-// CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
+// CHECK-SAME: {{.*}} [[A_SRC]]
 
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
@@ -32,7 +48,7 @@
 // CHECK-SAME: "{{.*}}lib1.bc" "{{.*}}lib2.bc"
 // CHECK-SAME: "-target-cpu" "gfx803"
 // CHECK-SAME: {{.*}} "-o" [[B_BC1:".*bc"]] "-x" "hip"
-// CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
+// CHECK-SAME: {{.*}} [[B_SRC]]
 
 // CHECK-NOT: "*.llvm-link"
 // CHECK-NOT: ".*opt"
@@ -40,6 +56,7 @@
 // CHECK: {{".*lld.*"}} {{.*}} "-mllvm" "-amdgpu-internalize-symbols"
 // CHECK-SAME: "-o" "[[IMG_DEV1:.*.out]]" [[A_BC1]] [[B_BC1]]
 
+// generate image for device side path on gfx900
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: "-emit-llvm-bc"
@@ -66,23 +83,13 @@
 // CHECK: {{".*lld.*"}} {{.*}} "-mllvm" "-amdgpu-internalize-symbols"
 // CHECK-SAME: "-o" "[[IMG_DEV2:.*.out]]" [[A_BC2]] [[B_BC2]]
 
-// CHECK: [[CLANG]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
-// CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
-// CHECK-SAME: "-emit-obj"
-// CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
-// CHECK-SAME: {{.*}} "-o" [[A_OBJ_HOST:".*o"]] "-x" "hip"
-// CHECK-SAME: {{.*}} [[A_SRC]]
-
-// CHECK: [[CLANG]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
-// CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
-// CHECK-SAME: "-emit-obj"
-// CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
-// CHECK-SAME: {{.*}} "-o" [[B_OBJ_HOST:".*o"]] "-x" "hip"
-// CHECK-SAME: {{.*}} [[B_SRC]]
-
+// combine images generated into hip fat binary object
 // CHECK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
 // CHECK-SAME: "-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" "-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[LD:".*ld.*"]] {{.*}} [[A_OBJ_HOST]] [[B_OBJ_HOST]]
-// CHECK-SAME: {{.*}} "-T" "{{.*}}.lk"
+// CHECK: [[MC:".*llvm-mc"]] "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+
+// output the executable
+// CHECK: [[LD:".*ld.*"]] {{.*}}"-o" "a.out" {{.*}} [[A_OBJ_HOST]] [[B_OBJ_HOST]] [[OBJBUNDLE]]
Index: clang/test/Driver/hip-toolchain-rdc-separate.hip
===
--- clang/test/Driver/hip-toolchain-rdc-separate.hip
+++ clang/test/Driver/hip-toolchain-rdc-separate.hip
@@ -86,12 +86,22 @@
 
 // LINK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
 // LINK-SAME: "-targets=host-x86_64-unknown-linux-gnu,hip-amdgcn-amd-amdhsa

[PATCH] D78759: Add Statically Linked Libraries

2020-06-22 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rG4bafb0adcf38: Add Statically Linked Libraries (authored by 
ashi1).
Herald added a subscriber: cfe-commits.

Changed prior to commit:
  https://reviews.llvm.org/D78759?vs=271220&id=272526#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D78759/new/

https://reviews.llvm.org/D78759

Files:
  clang/include/clang/Driver/Action.h
  clang/include/clang/Driver/Driver.h
  clang/include/clang/Driver/Options.td
  clang/include/clang/Driver/ToolChain.h
  clang/lib/Driver/Action.cpp
  clang/lib/Driver/Driver.cpp
  clang/lib/Driver/ToolChain.cpp
  clang/lib/Driver/ToolChains/Gnu.cpp
  clang/lib/Driver/ToolChains/Gnu.h
  clang/lib/Driver/ToolChains/Linux.cpp
  clang/lib/Driver/ToolChains/Linux.h
  clang/test/Driver/bindings.c
  clang/test/Driver/hip-link-save-temps.hip
  clang/test/Driver/hip-link-static-library.hip
  clang/test/Driver/hip-toolchain-rdc-static-lib.hip

Index: clang/test/Driver/hip-toolchain-rdc-static-lib.hip
===
--- /dev/null
+++ clang/test/Driver/hip-toolchain-rdc-static-lib.hip
@@ -0,0 +1,84 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   --emit-static-lib -nogpulib \
+// RUN:   -fuse-ld=lld -fgpu-rdc -nogpuinc \
+// RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck %s
+
+// emit objects for host side path
+// CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-emit-obj"
+// CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
+// CHECK-SAME: {{.*}} "-o" [[A_OBJ_HOST:".*o"]] "-x" "hip"
+// CHECK-SAME: {{.*}} [[A_SRC:".*a.cu"]]
+
+// CHECK: [[CLANG]] "-cc1" "-triple" "x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-aux-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-emit-obj"
+// CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
+// CHECK-SAME: {{.*}} "-o" [[B_OBJ_HOST:".*o"]] "-x" "hip"
+// CHECK-SAME: {{.*}} [[B_SRC:".*b.hip"]]
+
+// generate image for device side path on gfx803
+// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-emit-llvm-bc"
+// CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
+// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
+// CHECK-SAME: "-target-cpu" "gfx803"
+// CHECK-SAME: {{.*}} "-o" [[A_BC1:".*bc"]] "-x" "hip"
+// CHECK-SAME: {{.*}} [[A_SRC]]
+
+// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-emit-llvm-bc"
+// CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
+// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
+// CHECK-SAME: "-target-cpu" "gfx803"
+// CHECK-SAME: {{.*}} "-o" [[B_BC1:".*bc"]] "-x" "hip"
+// CHECK-SAME: {{.*}} [[B_SRC]]
+
+// CHECK-NOT: "*.llvm-link"
+// CHECK-NOT: ".*opt"
+// CHECK-NOT: ".*llc"
+// CHECK: [[LLD: ".*lld"]] {{.*}} "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] [[B_BC1]]
+
+// generate image for device side path on gfx900
+// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-emit-llvm-bc"
+// CHECK-SAME: {{.*}} "-main-file-name" "a.cu"
+// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
+// CHECK-SAME: "-target-cpu" "gfx900"
+// CHECK-SAME: {{.*}} "-o" [[A_BC2:".*bc"]] "-x" "hip"
+// CHECK-SAME: {{.*}} [[A_SRC]]
+
+// CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// CHECK-SAME: "-emit-llvm-bc"
+// CHECK-SAME: {{.*}} "-main-file-name" "b.hip"
+// CHECK-SAME: "-fcuda-is-device" "-fgpu-rdc"
+// CHECK-SAME: "-target-cpu" "gfx900"
+// CHECK-SAME: {{.*}} "-o" [[B_BC2:".*bc"]] "-x" "hip"
+// CHECK-SAME: {{.*}} [[B_SRC]]
+
+// CHECK-NOT: "*.llvm-link"
+// CHECK-NOT: ".*opt"
+// CHECK-NOT: ".*llc"
+// CHECK: [[LLD]] {{.*}} "-o" "[[IMG_DEV2:.*out]]" [[A_BC2]] [[B_BC2]]
+
+// combine images generated into hip fat binary object
+// CHECK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"
+// CHECK-SAME: "-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
+// CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" "-outputs=[[BUNDLE:.*hipfb]]"
+
+// CHECK: [[MC:".*llvm-mc"]] "-triple" "amdgcn-amd-amdhsa"
+// CHECK-SAME: "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+
+// CHECK: [[AR:".*llvm-ar.*"]] "rcsD" "{{.*}}.out" [[A_OBJ_HOST]] [[B_OBJ_HOST]] [[OBJBUNDLE]]
Index: clang/test/Driver/hip-link-static-library.hip
===
--- /dev/null
+++ clang/test/Driver/hip-link-static-library.hip
@@ -0,0 +1,27 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES:

[PATCH] D78655: [CUDA][HIP] Let non-caputuring lambda be host device

2020-06-25 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added inline comments.



Comment at: clang/test/CodeGenCUDA/lambda.cu:53
+// DEV:  call void @_ZZ12test_resolvevENKUlvE_clEv
+// DEV-LABE: define internal void @_ZZ12test_resolvevENKUlvE_clEv
+// DEV:  call i32 @_Z10overloadedIiET_v

There is a typo here, DEV-LABEL


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D78655/new/

https://reviews.llvm.org/D78655



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D78759: Add Statically Linked Libraries

2020-06-29 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Hi Jon, I may have committed this in combination with D81963 
 as the parent commit. It should have waited 
for a LGTM from someone outside our org.

Please let me know unaddressed comments on this change, and I will fix them 
asap. Sorry about the confusion.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D78759/new/

https://reviews.llvm.org/D78759



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D85442: [HIP] Ignore invalid ar linker options

2020-08-06 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rG96c2d5e99e32: [HIP] Ignore invalid ar linker options 
(authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D85442/new/

https://reviews.llvm.org/D85442

Files:
  clang/lib/Driver/ToolChains/Gnu.cpp
  clang/test/Driver/hip-link-static-library.hip


Index: clang/test/Driver/hip-link-static-library.hip
===
--- clang/test/Driver/hip-link-static-library.hip
+++ clang/test/Driver/hip-link-static-library.hip
@@ -25,3 +25,14 @@
 
 // NORDC-NOT: offload bundler
 // NORDC: # "x86_64-unknown-linux-gnu" - "GNU::StaticLibTool", inputs: 
["{{.*o}}"], output: "a.out"
+
+// RUN: %clang --hip-link -### -target x86_64-linux-gnu \
+// RUN:   --emit-static-lib -lgcc \
+// RUN:   -Wl,--enable-new-dtags -Wl,--rpath=/opt \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 -fgpu-rdc %t.o\
+// RUN: 2>&1 | FileCheck -check-prefix=NOFLAG %s
+
+// NOFLAG-NOT: .*lgcc
+// NOFLAG-NOT: .*enable-new-dtags
+// NOFLAG-NOT: .*rpath=/opt
+// NOFLAG: "{{.*}}llvm-ar{{.*}}" "rcsD" "{{.*}}.out" "{{.*o}}" "{{.*o}}"
Index: clang/lib/Driver/ToolChains/Gnu.cpp
===
--- clang/lib/Driver/ToolChains/Gnu.cpp
+++ clang/lib/Driver/ToolChains/Gnu.cpp
@@ -341,12 +341,17 @@
   // Silence warnings when linking C code with a C++ '-stdlib' argument.
   Args.ClaimAllArgs(options::OPT_stdlib_EQ);
 
-  // GNU ar tool command "ar   ".
+  // ar tool command "llvm-ar   ".
   ArgStringList CmdArgs;
   // Create and insert file members with a deterministic index.
   CmdArgs.push_back("rcsD");
   CmdArgs.push_back(Output.getFilename());
-  AddLinkerInputs(getToolChain(), Inputs, Args, CmdArgs, JA);
+
+  for (const auto &II : Inputs) {
+if (II.isFilename()) {
+   CmdArgs.push_back(II.getFilename());
+}
+  }
 
   // Delete old output archive file if it already exists before generating a 
new
   // archive file.


Index: clang/test/Driver/hip-link-static-library.hip
===
--- clang/test/Driver/hip-link-static-library.hip
+++ clang/test/Driver/hip-link-static-library.hip
@@ -25,3 +25,14 @@
 
 // NORDC-NOT: offload bundler
 // NORDC: # "x86_64-unknown-linux-gnu" - "GNU::StaticLibTool", inputs: ["{{.*o}}"], output: "a.out"
+
+// RUN: %clang --hip-link -### -target x86_64-linux-gnu \
+// RUN:   --emit-static-lib -lgcc \
+// RUN:   -Wl,--enable-new-dtags -Wl,--rpath=/opt \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 -fgpu-rdc %t.o\
+// RUN: 2>&1 | FileCheck -check-prefix=NOFLAG %s
+
+// NOFLAG-NOT: .*lgcc
+// NOFLAG-NOT: .*enable-new-dtags
+// NOFLAG-NOT: .*rpath=/opt
+// NOFLAG: "{{.*}}llvm-ar{{.*}}" "rcsD" "{{.*}}.out" "{{.*o}}" "{{.*o}}"
Index: clang/lib/Driver/ToolChains/Gnu.cpp
===
--- clang/lib/Driver/ToolChains/Gnu.cpp
+++ clang/lib/Driver/ToolChains/Gnu.cpp
@@ -341,12 +341,17 @@
   // Silence warnings when linking C code with a C++ '-stdlib' argument.
   Args.ClaimAllArgs(options::OPT_stdlib_EQ);
 
-  // GNU ar tool command "ar   ".
+  // ar tool command "llvm-ar   ".
   ArgStringList CmdArgs;
   // Create and insert file members with a deterministic index.
   CmdArgs.push_back("rcsD");
   CmdArgs.push_back(Output.getFilename());
-  AddLinkerInputs(getToolChain(), Inputs, Args, CmdArgs, JA);
+
+  for (const auto &II : Inputs) {
+if (II.isFilename()) {
+   CmdArgs.push_back(II.getFilename());
+}
+  }
 
   // Delete old output archive file if it already exists before generating a new
   // archive file.
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D106070: [HIP] Remove workaround in __clang_hip_runtime_wrapper.h

2021-07-15 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.
This revision is now accepted and ready to land.

LGTM!


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D106070/new/

https://reviews.llvm.org/D106070

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D106069: [HIP] Add test with_fopenmp.hip

2021-07-15 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.
This revision is now accepted and ready to land.

LGTM!


Repository:
  rT test-suite

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D106069/new/

https://reviews.llvm.org/D106069

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D106463: [HIP] Fix no matching constructor for init of shared_ptr and malloc

2021-07-22 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG9ce931bd7185: [HIP] Fix no matching constructor for init of 
shared_ptr and malloc (authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D106463/new/

https://reviews.llvm.org/D106463

Files:
  clang/lib/Headers/__clang_hip_runtime_wrapper.h


Index: clang/lib/Headers/__clang_hip_runtime_wrapper.h
===
--- clang/lib/Headers/__clang_hip_runtime_wrapper.h
+++ clang/lib/Headers/__clang_hip_runtime_wrapper.h
@@ -46,6 +46,28 @@
 }
 #endif //__cplusplus
 
+#if !defined(__HIPCC_RTC__)
+#include 
+#include 
+#include 
+#else
+typedef __SIZE_TYPE__ size_t;
+// Define macros which are needed to declare HIP device API's without standard
+// C/C++ headers. This is for readability so that these API's can be written
+// the same way as non-hipRTC use case. These macros need to be popped so that
+// they do not pollute users' name space.
+#pragma push_macro("NULL")
+#pragma push_macro("uint32_t")
+#pragma push_macro("uint64_t")
+#pragma push_macro("CHAR_BIT")
+#pragma push_macro("INT_MAX")
+#define NULL (void *)0
+#define uint32_t __UINT32_TYPE__
+#define uint64_t __UINT64_TYPE__
+#define CHAR_BIT __CHAR_BIT__
+#define INT_MAX __INTMAX_MAX__
+#endif // __HIPCC_RTC__
+
 typedef __SIZE_TYPE__ __hip_size_t;
 
 #ifdef __cplusplus
@@ -64,11 +86,11 @@
 #else
 __attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   __builtin_trap();
-  return nullptr;
+  return (void *)0;
 }
 __attribute__((weak)) inline __device__ void *free(void *__ptr) {
   __builtin_trap();
-  return nullptr;
+  return (void *)0;
 }
 #endif
 
@@ -76,28 +98,6 @@
 } // extern "C"
 #endif //__cplusplus
 
-#if !defined(__HIPCC_RTC__)
-#include 
-#include 
-#include 
-#else
-typedef __SIZE_TYPE__ size_t;
-// Define macros which are needed to declare HIP device API's without standard
-// C/C++ headers. This is for readability so that these API's can be written
-// the same way as non-hipRTC use case. These macros need to be popped so that
-// they do not pollute users' name space.
-#pragma push_macro("NULL")
-#pragma push_macro("uint32_t")
-#pragma push_macro("uint64_t")
-#pragma push_macro("CHAR_BIT")
-#pragma push_macro("INT_MAX")
-#define NULL (void *)0
-#define uint32_t __UINT32_TYPE__
-#define uint64_t __UINT64_TYPE__
-#define CHAR_BIT __CHAR_BIT__
-#define INT_MAX __INTMAX_MAX__
-#endif // __HIPCC_RTC__
-
 #include <__clang_hip_libdevice_declares.h>
 #include <__clang_hip_math.h>
 


Index: clang/lib/Headers/__clang_hip_runtime_wrapper.h
===
--- clang/lib/Headers/__clang_hip_runtime_wrapper.h
+++ clang/lib/Headers/__clang_hip_runtime_wrapper.h
@@ -46,6 +46,28 @@
 }
 #endif //__cplusplus
 
+#if !defined(__HIPCC_RTC__)
+#include 
+#include 
+#include 
+#else
+typedef __SIZE_TYPE__ size_t;
+// Define macros which are needed to declare HIP device API's without standard
+// C/C++ headers. This is for readability so that these API's can be written
+// the same way as non-hipRTC use case. These macros need to be popped so that
+// they do not pollute users' name space.
+#pragma push_macro("NULL")
+#pragma push_macro("uint32_t")
+#pragma push_macro("uint64_t")
+#pragma push_macro("CHAR_BIT")
+#pragma push_macro("INT_MAX")
+#define NULL (void *)0
+#define uint32_t __UINT32_TYPE__
+#define uint64_t __UINT64_TYPE__
+#define CHAR_BIT __CHAR_BIT__
+#define INT_MAX __INTMAX_MAX__
+#endif // __HIPCC_RTC__
+
 typedef __SIZE_TYPE__ __hip_size_t;
 
 #ifdef __cplusplus
@@ -64,11 +86,11 @@
 #else
 __attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   __builtin_trap();
-  return nullptr;
+  return (void *)0;
 }
 __attribute__((weak)) inline __device__ void *free(void *__ptr) {
   __builtin_trap();
-  return nullptr;
+  return (void *)0;
 }
 #endif
 
@@ -76,28 +98,6 @@
 } // extern "C"
 #endif //__cplusplus
 
-#if !defined(__HIPCC_RTC__)
-#include 
-#include 
-#include 
-#else
-typedef __SIZE_TYPE__ size_t;
-// Define macros which are needed to declare HIP device API's without standard
-// C/C++ headers. This is for readability so that these API's can be written
-// the same way as non-hipRTC use case. These macros need to be popped so that
-// they do not pollute users' name space.
-#pragma push_macro("NULL")
-#pragma push_macro("uint32_t")
-#pragma push_macro("uint64_t")
-#pragma push_macro("CHAR_BIT")
-#pragma push_macro("INT_MAX")
-#define NULL (void *)0
-#define uint32_t __UINT32_TYPE__
-#define uint64_t __UINT64_TYPE__
-#define CHAR_BIT __CHAR_BIT__
-#define INT_MAX __INTMAX_MAX__
-#endif // __HIPCC_RTC__
-
 #include <__clang_hip_libdevice_declares.h>
 #include <__clang_hip_math.h>
 
___

[PATCH] D88377: Diagnose invalid target ID for AMDGPU toolchain for assembler

2020-09-28 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Could you please add full context? Mostly looks good to me.




Comment at: clang/lib/Driver/ToolChains/HIP.cpp:243
 
-  // Allow using target ID in --offload-arch.
-  StringRef GpuArch = translateTargetID(DriverArgs, CC1Args);
+  StringRef GpuArch = getGPUArch(DriverArgs);
   assert(!GpuArch.empty() && "Must have an explicit GPU arch.");

Why move the checking logic to the end if getGPUArch doesn't do any checking?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D88377/new/

https://reviews.llvm.org/D88377

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D87324: [HIP] Add gfx1030 and gfx1031

2020-09-08 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.

LGTM, looks like its already in clang/include/clang/Basic/Cuda.h and 
clang/lib/Basic/Targets/AMDGPU.cpp.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D87324/new/

https://reviews.llvm.org/D87324

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D87461: Disable sanitizer options for AMDGPU

2020-09-10 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.
This revision is now accepted and ready to land.

LGTM


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D87461/new/

https://reviews.llvm.org/D87461

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D90409: [HIP] Math Headers to use type promotion

2020-11-03 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rGca5b31502c82: [HIP] Math Headers to use type promotion 
(authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D90409/new/

https://reviews.llvm.org/D90409

Files:
  clang/lib/Headers/__clang_hip_cmath.h

Index: clang/lib/Headers/__clang_hip_cmath.h
===
--- clang/lib/Headers/__clang_hip_cmath.h
+++ clang/lib/Headers/__clang_hip_cmath.h
@@ -16,6 +16,8 @@
 
 #if defined(__cplusplus)
 #include 
+#include 
+#include 
 #endif
 #include 
 #include 
@@ -205,6 +207,72 @@
 
 template  struct __hip_enable_if { typedef __T type; };
 
+// decltype is only available in C++11 and above.
+#if __cplusplus >= 201103L
+// __hip_promote
+namespace __hip {
+
+template  struct __numeric_type {
+  static void __test(...);
+  static _Float16 __test(_Float16);
+  static float __test(float);
+  static double __test(char);
+  static double __test(int);
+  static double __test(unsigned);
+  static double __test(long);
+  static double __test(unsigned long);
+  static double __test(long long);
+  static double __test(unsigned long long);
+  static double __test(double);
+
+  typedef decltype(__test(std::declval<_Tp>())) type;
+  static const bool value = !std::is_same::value;
+};
+
+template <> struct __numeric_type { static const bool value = true; };
+
+template ::value &&__numeric_type<_A2>::value
+  &&__numeric_type<_A3>::value>
+class __promote_imp {
+public:
+  static const bool value = false;
+};
+
+template 
+class __promote_imp<_A1, _A2, _A3, true> {
+private:
+  typedef typename __promote_imp<_A1>::type __type1;
+  typedef typename __promote_imp<_A2>::type __type2;
+  typedef typename __promote_imp<_A3>::type __type3;
+
+public:
+  typedef decltype(__type1() + __type2() + __type3()) type;
+  static const bool value = true;
+};
+
+template  class __promote_imp<_A1, _A2, void, true> {
+private:
+  typedef typename __promote_imp<_A1>::type __type1;
+  typedef typename __promote_imp<_A2>::type __type2;
+
+public:
+  typedef decltype(__type1() + __type2()) type;
+  static const bool value = true;
+};
+
+template  class __promote_imp<_A1, void, void, true> {
+public:
+  typedef typename __numeric_type<_A1>::type type;
+  static const bool value = true;
+};
+
+template 
+class __promote : public __promote_imp<_A1, _A2, _A3> {};
+
+} // namespace __hip
+#endif //__cplusplus >= 201103L
+
 // __HIP_OVERLOAD1 is used to resolve function calls with integer argument to
 // avoid compilation error due to ambibuity. e.g. floor(5) is resolved with
 // floor(double).
@@ -219,6 +287,18 @@
 // __HIP_OVERLOAD2 is used to resolve function calls with mixed float/double
 // or integer argument to avoid compilation error due to ambibuity. e.g.
 // max(5.0f, 6.0) is resolved with max(double, double).
+#if __cplusplus >= 201103L
+#define __HIP_OVERLOAD2(__retty, __fn) \
+  template   \
+  __DEVICE__ typename __hip_enable_if< \
+  std::numeric_limits<__T1>::is_specialized && \
+  std::numeric_limits<__T2>::is_specialized,   \
+  typename __hip::__promote<__T1, __T2>::type>::type   \
+  __fn(__T1 __x, __T2 __y) {   \
+typedef typename __hip::__promote<__T1, __T2>::type __result_type; \
+return __fn((__result_type)__x, (__result_type)__y);   \
+  }
+#else
 #define __HIP_OVERLOAD2(__retty, __fn) \
   template   \
   __DEVICE__   \
@@ -228,6 +308,7 @@
   __fn(__T1 __x, __T2 __y) {   \
 return __fn((double)__x, (double)__y); \
   }
+#endif
 
 __HIP_OVERLOAD1(double, abs)
 __HIP_OVERLOAD1(double, acos)
@@ -296,6 +377,18 @@
 __HIP_OVERLOAD2(double, min)
 
 // Additional Overloads that don't quite match HIP_OVERLOAD.
+#if __cplusplus >= 201103L
+template 
+__DEVICE__ typename __hip_enable_if<
+std::numeric_limits<__T1>::is_specialized &&
+std::numeric_limits<__T2>::is_specialized &&
+std::numeric_limits<__T3>::is_specialized,
+typename __hip::__promote<__T1, __T2, __T3>::type>::type
+fma(__T1 __x, __T2 __y, __T3 __z) {
+  typedef typename __hip::__promote<__T1, __T2, __T3>::type __result_type;
+  return ::fma((__result_type)__x, (__result_type)__y, (__result_type)__z);
+}
+#else
 template 
 __DEVICE__
 typename __hip_enable_if::is_specialized &&
@@ -305,6 +398,7 @@
 fma(__T1 __x, __T2 __y, __T3 __z) {
   return ::fma((double)__

[PATCH] D88377: Diagnose invalid target ID for AMDGPU toolchain for assembler

2020-10-02 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.
This revision is now accepted and ready to land.

LGTM


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D88377/new/

https://reviews.llvm.org/D88377

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D92342: [HIP] Fix HIP test on windows due to lld suffix

2020-11-30 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rGf89e9c8201ea: [HIP] Fix HIP test on windows due to lld 
suffix (authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D92342/new/

https://reviews.llvm.org/D92342

Files:
  clang/test/Driver/hip-toolchain-rdc-static-lib.hip
  clang/test/Driver/hip-toolchain-rdc.hip


Index: clang/test/Driver/hip-toolchain-rdc.hip
===
--- clang/test/Driver/hip-toolchain-rdc.hip
+++ clang/test/Driver/hip-toolchain-rdc.hip
@@ -95,7 +95,7 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
+// CHECK: [[MC:".*llvm-mc.*"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
 
 // output the executable
 // CHECK: [[LD:".*ld.*"]] {{.*}}"-o" "a.out" {{.*}} [[A_OBJ_HOST]] 
[[B_OBJ_HOST]] [[OBJBUNDLE]]
Index: clang/test/Driver/hip-toolchain-rdc-static-lib.hip
===
--- clang/test/Driver/hip-toolchain-rdc-static-lib.hip
+++ clang/test/Driver/hip-toolchain-rdc-static-lib.hip
@@ -47,7 +47,7 @@
 // CHECK-NOT: "*.llvm-link"
 // CHECK-NOT: ".*opt"
 // CHECK-NOT: ".*llc"
-// CHECK: [[LLD: ".*lld"]] {{.*}} "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] [[B_BC1]]
+// CHECK: [[LLD: ".*lld.*"]] {{.*}} "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] 
[[B_BC1]]
 
 // generate image for device side path on gfx900
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
@@ -78,6 +78,6 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
+// CHECK: [[MC:".*llvm-mc.*"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
 
 // CHECK: [[AR:".*llvm-ar.*"]] "rcsD" "{{.*}}.out" [[A_OBJ_HOST]] 
[[B_OBJ_HOST]] [[OBJBUNDLE]]


Index: clang/test/Driver/hip-toolchain-rdc.hip
===
--- clang/test/Driver/hip-toolchain-rdc.hip
+++ clang/test/Driver/hip-toolchain-rdc.hip
@@ -95,7 +95,7 @@
 // CHECK-SAME: "-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" "-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+// CHECK: [[MC:".*llvm-mc.*"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
 
 // output the executable
 // CHECK: [[LD:".*ld.*"]] {{.*}}"-o" "a.out" {{.*}} [[A_OBJ_HOST]] [[B_OBJ_HOST]] [[OBJBUNDLE]]
Index: clang/test/Driver/hip-toolchain-rdc-static-lib.hip
===
--- clang/test/Driver/hip-toolchain-rdc-static-lib.hip
+++ clang/test/Driver/hip-toolchain-rdc-static-lib.hip
@@ -47,7 +47,7 @@
 // CHECK-NOT: "*.llvm-link"
 // CHECK-NOT: ".*opt"
 // CHECK-NOT: ".*llc"
-// CHECK: [[LLD: ".*lld"]] {{.*}} "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] [[B_BC1]]
+// CHECK: [[LLD: ".*lld.*"]] {{.*}} "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] [[B_BC1]]
 
 // generate image for device side path on gfx900
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
@@ -78,6 +78,6 @@
 // CHECK-SAME: "-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" "-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+// CHECK: [[MC:".*llvm-mc.*"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
 
 // CHECK: [[AR:".*llvm-ar.*"]] "rcsD" "{{.*}}.out" [[A_OBJ_HOST]] [[B_OBJ_HOST]] [[OBJBUNDLE]]
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D92342: [HIP] Fix HIP test on windows due to lld suffix

2020-12-01 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

In D92342#2425271 , @RKSimon wrote:

> @ashi1 This is causing build failures - please can you take a look ? 
> http://lab.llvm.org:8011/#/builders/14/builds/2514
>
>   :17:66: note: possible intended match here
>"/b/1/clang-x86_64-debian-new-pass-manager-fast/llvm.obj/bin/llvm-ar" 
> "rcsD" "a.out" "/tmp/a-88f827.o" "/tmp/b-11b5fe.o" "/tmp/a-72b91c.o"

Thank you, I'm working on pushing a patch ASAP, otherwise I will revert.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D92342/new/

https://reviews.llvm.org/D92342

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D92418: [hip] Fix host object creation from fatbin

2020-12-01 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Looks good to me, were you able to run staging on this patch?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D92418/new/

https://reviews.llvm.org/D92418

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D92130: [HIP] cmath promote long double args to double

2020-12-03 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rGba2612ce01ea: [HIP] cmath demote long double args to double 
(authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D92130/new/

https://reviews.llvm.org/D92130

Files:
  clang/lib/Headers/__clang_hip_cmath.h


Index: clang/lib/Headers/__clang_hip_cmath.h
===
--- clang/lib/Headers/__clang_hip_cmath.h
+++ clang/lib/Headers/__clang_hip_cmath.h
@@ -224,6 +224,8 @@
   static double __test(long long);
   static double __test(unsigned long long);
   static double __test(double);
+  // No support for long double, use double instead.
+  static double __test(long double);
 
   typedef decltype(__test(std::declval<_Tp>())) type;
   static const bool value = !std::is_same::value;


Index: clang/lib/Headers/__clang_hip_cmath.h
===
--- clang/lib/Headers/__clang_hip_cmath.h
+++ clang/lib/Headers/__clang_hip_cmath.h
@@ -224,6 +224,8 @@
   static double __test(long long);
   static double __test(unsigned long long);
   static double __test(double);
+  // No support for long double, use double instead.
+  static double __test(long double);
 
   typedef decltype(__test(std::declval<_Tp>())) type;
   static const bool value = !std::is_same::value;
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D92130: [HIP] cmath promote long double args to double

2020-12-03 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

In D92130#2423801 , @tra wrote:

> LGTM in general. Will defer to Sam as it's HIP.
>
> Nit:
>
>> long double, promote them to double, and use the fp64
>
> I'd say `long double` -> `double` qualifies as a demotion.

Thanks, I've changed the commit description to demote.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D92130/new/

https://reviews.llvm.org/D92130

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D102403: [HIP] Add __builtin_amdgcn_groupstaticsize

2021-05-13 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG6a67e05a26eb: [HIP] Add __builtin_amdgcn_groupstaticsize 
(authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D102403/new/

https://reviews.llvm.org/D102403

Files:
  clang/include/clang/Basic/BuiltinsAMDGPU.def
  clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl
  clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
  clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
  clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl


Index: clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
===
--- clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
+++ clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
@@ -145,3 +145,10 @@
 {
   *out = __builtin_amdgcn_perm(a, b, s);
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out)
+{
+  *out = __builtin_amdgcn_groupstaticsize();
+}
Index: clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
===
--- clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
+++ clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
@@ -3,6 +3,7 @@
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S 
-emit-llvm -o - %s | FileCheck %s
 
 #pragma OPENCL EXTENSION cl_khr_fp16 : enable
+typedef unsigned int uint;
 typedef unsigned long ulong;
 
 // CHECK-LABEL: @test_fmed3_f16
@@ -18,3 +19,10 @@
 {
   *out = __builtin_amdgcn_s_memtime();
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out)
+{
+  *out = __builtin_amdgcn_groupstaticsize();
+}
Index: clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
===
--- clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
+++ clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
@@ -30,3 +30,10 @@
 {
   *out = __builtin_amdgcn_s_memtime();
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out)
+{
+  *out = __builtin_amdgcn_groupstaticsize();
+}
Index: clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl
===
--- clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl
+++ clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl
@@ -62,3 +62,9 @@
 int test_is_private_global(const global int* ptr) {
   return __builtin_amdgcn_is_private(ptr);
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out) {
+  *out = __builtin_amdgcn_groupstaticsize();
+}
Index: clang/include/clang/Basic/BuiltinsAMDGPU.def
===
--- clang/include/clang/Basic/BuiltinsAMDGPU.def
+++ clang/include/clang/Basic/BuiltinsAMDGPU.def
@@ -65,6 +65,7 @@
 BUILTIN(__builtin_amdgcn_ds_gws_sema_br, "vUiUi", "n")
 BUILTIN(__builtin_amdgcn_ds_gws_sema_p, "vUi", "n")
 BUILTIN(__builtin_amdgcn_fence, "vUicC*", "n")
+BUILTIN(__builtin_amdgcn_groupstaticsize, "Ui", "n")
 
 BUILTIN(__builtin_amdgcn_atomic_inc32, "UZiUZiD*UZiUicC*", "n")
 BUILTIN(__builtin_amdgcn_atomic_inc64, "UWiUWiD*UWiUicC*", "n")


Index: clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
===
--- clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
+++ clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
@@ -145,3 +145,10 @@
 {
   *out = __builtin_amdgcn_perm(a, b, s);
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out)
+{
+  *out = __builtin_amdgcn_groupstaticsize();
+}
Index: clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
===
--- clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
+++ clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
@@ -3,6 +3,7 @@
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck %s
 
 #pragma OPENCL EXTENSION cl_khr_fp16 : enable
+typedef unsigned int uint;
 typedef unsigned long ulong;
 
 // CHECK-LABEL: @test_fmed3_f16
@@ -18,3 +19,10 @@
 {
   *out = __builtin_amdgcn_s_memtime();
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out)
+{
+  *out = __builtin_amdgcn_groupstaticsize();
+}
Index: clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
===
--- clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
+++ clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
@@ -30

[PATCH] D102427: [HIP] Clean up llvm intrinsics using __asm

2021-05-13 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGa249ffa42137: [HIP] Clean up llvm intrinsics using __asm 
(authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D102427/new/

https://reviews.llvm.org/D102427

Files:
  clang/lib/Headers/__clang_hip_libdevice_declares.h


Index: clang/lib/Headers/__clang_hip_libdevice_declares.h
===
--- clang/lib/Headers/__clang_hip_libdevice_declares.h
+++ clang/lib/Headers/__clang_hip_libdevice_declares.h
@@ -138,14 +138,22 @@
 __device__ __attribute__((const)) float __ocml_fma_rtp_f32(float, float, 
float);
 __device__ __attribute__((const)) float __ocml_fma_rtz_f32(float, float, 
float);
 
-__device__ __attribute__((const)) float
-__llvm_amdgcn_cos_f32(float) __asm("llvm.amdgcn.cos.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rcp_f32(float) __asm("llvm.amdgcn.rcp.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rsq_f32(float) __asm("llvm.amdgcn.rsq.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_sin_f32(float) __asm("llvm.amdgcn.sin.f32");
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_cos_f32(float __x) {
+  return __builtin_amdgcn_cosf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rcp_f32(float __x) {
+  return __builtin_amdgcn_rcpf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rsq_f32(float __x) {
+  return __builtin_amdgcn_rsqf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_sin_f32(float __x) {
+  return __builtin_amdgcn_sinf(__x);
+}
 // END INTRINSICS
 // END FLOAT
 
@@ -269,10 +277,14 @@
 __device__ __attribute__((const)) double __ocml_fma_rtz_f64(double, double,
 double);
 
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rcp_f64(double) __asm("llvm.amdgcn.rcp.f64");
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rsq_f64(double) __asm("llvm.amdgcn.rsq.f64");
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rcp_f64(double __x) {
+  return __builtin_amdgcn_rcp(__x);
+}
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rsq_f64(double __x) {
+  return __builtin_amdgcn_rsq(__x);
+}
 
 __device__ __attribute__((const)) _Float16 __ocml_ceil_f16(_Float16);
 __device__ _Float16 __ocml_cos_f16(_Float16);


Index: clang/lib/Headers/__clang_hip_libdevice_declares.h
===
--- clang/lib/Headers/__clang_hip_libdevice_declares.h
+++ clang/lib/Headers/__clang_hip_libdevice_declares.h
@@ -138,14 +138,22 @@
 __device__ __attribute__((const)) float __ocml_fma_rtp_f32(float, float, float);
 __device__ __attribute__((const)) float __ocml_fma_rtz_f32(float, float, float);
 
-__device__ __attribute__((const)) float
-__llvm_amdgcn_cos_f32(float) __asm("llvm.amdgcn.cos.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rcp_f32(float) __asm("llvm.amdgcn.rcp.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rsq_f32(float) __asm("llvm.amdgcn.rsq.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_sin_f32(float) __asm("llvm.amdgcn.sin.f32");
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_cos_f32(float __x) {
+  return __builtin_amdgcn_cosf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rcp_f32(float __x) {
+  return __builtin_amdgcn_rcpf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rsq_f32(float __x) {
+  return __builtin_amdgcn_rsqf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_sin_f32(float __x) {
+  return __builtin_amdgcn_sinf(__x);
+}
 // END INTRINSICS
 // END FLOAT
 
@@ -269,10 +277,14 @@
 __device__ __attribute__((const)) double __ocml_fma_rtz_f64(double, double,
 double);
 
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rcp_f64(double) __asm("llvm.amdgcn.rcp.f64");
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rsq_f64(double) __asm("llvm.amdgcn.rsq.f64");
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rcp_f64(double __x) {
+  return __builtin_amdgcn_rcp(__x);
+}
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rsq_f64(double __x) {
+  return __builtin_amdgcn_rsq(__x);
+}
 
 __device__ __attribute__((const)) _Float16 __ocml_ceil_f16(_Float16);
 __device__ _Float16 __ocml_cos_f16(_Float16);
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D102508: [HIP] Add test libstd_functional

2021-05-14 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Looks good, let me verify on HIP builder.


Repository:
  rT test-suite

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D102508/new/

https://reviews.llvm.org/D102508

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D102508: [HIP] Add test libstd_functional

2021-05-14 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

In D102508#2759906 , @yaxunl wrote:

> In D102508#2759905 , @ashi1 wrote:
>
>> Looks good, let me verify on HIP builder.
>
> It depends on https://reviews.llvm.org/D102507

Okay, let's wait for that to merge first. Thanks.


Repository:
  rT test-suite

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D102508/new/

https://reviews.llvm.org/D102508

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D100794: [HIP] Support overloaded math functions for hipRTC

2021-05-21 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added inline comments.



Comment at: clang/lib/Headers/__clang_hip_cmath.h:20
 #include 
 #include 
 #include 

we may not need to `#include` limits and/or type_traits if we replaced them 
with `__hip::is_integral` and `__hip::is_arithmetic`.



Comment at: clang/lib/Headers/__clang_hip_cmath.h:587
 #endif
-#endif
+#endif // !defined(__HIPCC_RTC__)
 

I don't think this `#endif` is for `!defined(__HIPCC_RTC__)`. It should be for 
`_LIBCPP_BEGIN_NAMESPACE_STD`.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D100794/new/

https://reviews.llvm.org/D100794

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D104062: [HIP] Fix --hip-version flag with 0 as component

2021-06-11 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rGf2cc0427b13e: [HIP] Fix --hip-version flag with 0 as 
component (authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D104062/new/

https://reviews.llvm.org/D104062

Files:
  clang/lib/Driver/ToolChains/AMDGPU.cpp
  clang/test/Driver/hip-version.hip


Index: clang/test/Driver/hip-version.hip
===
--- clang/test/Driver/hip-version.hip
+++ clang/test/Driver/hip-version.hip
@@ -36,6 +36,16 @@
 
 // SPECIFIED2: Found HIP installation: {{.*Driver}}, version 3.7.0
 
+// RUN: %clang -v --rocm-path=%S --hip-version=4.0.21025 2>&1 \
+// RUN:   | FileCheck -check-prefixes=SPECIFIED3 %s
+
+// SPECIFIED3: Found HIP installation: {{.*Driver}}, version 4.0.21025
+
+// RUN: %clang -v --rocm-path=%S --hip-version=4 2>&1 \
+// RUN:   | FileCheck -check-prefixes=SPECIFIED4 %s
+
+// SPECIFIED4: Found HIP installation: {{.*Driver}}, version 4.0.0
+
 // RUN: not %clang -v --rocm-path=%S --hip-version=x.y 2>&1 \
 // RUN:   | FileCheck -check-prefixes=INVALID %s
 
Index: clang/lib/Driver/ToolChains/AMDGPU.cpp
===
--- clang/lib/Driver/ToolChains/AMDGPU.cpp
+++ clang/lib/Driver/ToolChains/AMDGPU.cpp
@@ -316,8 +316,8 @@
   HIPPathArg = Args.getLastArgValue(clang::driver::options::OPT_hip_path_EQ);
   if (auto *A = Args.getLastArg(clang::driver::options::OPT_hip_version_EQ)) {
 HIPVersionArg = A->getValue();
-unsigned Major = 0;
-unsigned Minor = 0;
+unsigned Major = ~0U;
+unsigned Minor = ~0U;
 SmallVector Parts;
 HIPVersionArg.split(Parts, '.');
 if (Parts.size())
@@ -328,7 +328,9 @@
   VersionPatch = Parts[2].str();
 if (VersionPatch.empty())
   VersionPatch = "0";
-if (Major == 0 || Minor == 0)
+if (Major != ~0U && Minor == ~0U)
+  Minor = 0;
+if (Major == ~0U || Minor == ~0U)
   D.Diag(diag::err_drv_invalid_value)
   << A->getAsString(Args) << HIPVersionArg;
 


Index: clang/test/Driver/hip-version.hip
===
--- clang/test/Driver/hip-version.hip
+++ clang/test/Driver/hip-version.hip
@@ -36,6 +36,16 @@
 
 // SPECIFIED2: Found HIP installation: {{.*Driver}}, version 3.7.0
 
+// RUN: %clang -v --rocm-path=%S --hip-version=4.0.21025 2>&1 \
+// RUN:   | FileCheck -check-prefixes=SPECIFIED3 %s
+
+// SPECIFIED3: Found HIP installation: {{.*Driver}}, version 4.0.21025
+
+// RUN: %clang -v --rocm-path=%S --hip-version=4 2>&1 \
+// RUN:   | FileCheck -check-prefixes=SPECIFIED4 %s
+
+// SPECIFIED4: Found HIP installation: {{.*Driver}}, version 4.0.0
+
 // RUN: not %clang -v --rocm-path=%S --hip-version=x.y 2>&1 \
 // RUN:   | FileCheck -check-prefixes=INVALID %s
 
Index: clang/lib/Driver/ToolChains/AMDGPU.cpp
===
--- clang/lib/Driver/ToolChains/AMDGPU.cpp
+++ clang/lib/Driver/ToolChains/AMDGPU.cpp
@@ -316,8 +316,8 @@
   HIPPathArg = Args.getLastArgValue(clang::driver::options::OPT_hip_path_EQ);
   if (auto *A = Args.getLastArg(clang::driver::options::OPT_hip_version_EQ)) {
 HIPVersionArg = A->getValue();
-unsigned Major = 0;
-unsigned Minor = 0;
+unsigned Major = ~0U;
+unsigned Minor = ~0U;
 SmallVector Parts;
 HIPVersionArg.split(Parts, '.');
 if (Parts.size())
@@ -328,7 +328,9 @@
   VersionPatch = Parts[2].str();
 if (VersionPatch.empty())
   VersionPatch = "0";
-if (Major == 0 || Minor == 0)
+if (Major != ~0U && Minor == ~0U)
+  Minor = 0;
+if (Major == ~0U || Minor == ~0U)
   D.Diag(diag::err_drv_invalid_value)
   << A->getAsString(Args) << HIPVersionArg;
 
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D104677: [OpenMP][AMDGCN] Apply fix for isnan, isinf and isfinite for amdgcn.

2021-06-22 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

Looks OK to me, please address other review comments. Thanks.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D104677/new/

https://reviews.llvm.org/D104677

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D104904: [OpenMP][AMDGCN] Initial math headers support

2021-06-28 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

A few small comments, otherwise LGTM on the HIP header side.




Comment at: clang/lib/Headers/__clang_hip_cmath.h:30
+#ifdef __OPENMP_AMDGCN__
+#define __DEVICE__ static __attribute__((always_inline, nothrow))
+#define __CONSTEXPR__ constexpr

Does OpenMP not require `__device__` attribute here? I know constexpr defines 
`__device__` on HIP, does OMP do the same?



Comment at: clang/lib/Headers/__clang_hip_cmath.h:32
+#define __CONSTEXPR__ constexpr
+#define __constant__ __attribute__((constant))
+#else

I don't think this is the right place to define `__constant__`? It's unused in 
this header, and may get forgotten. Would it be better to define it in the 
openmp wrapper or does cmath define it in OpenMP?



Comment at: 
clang/lib/Headers/openmp_wrappers/__clang_openmp_device_functions.h:47
+#define __OPENMP_AMDGCN__
+#define __device__
+/// Include declarations for libdevice functions.

Would it be better to push and pop these macros, in case it was defined outside 
of here?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D104904/new/

https://reviews.llvm.org/D104904

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D105707: [HIP] Move std headers after device malloc/free

2021-07-09 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGccb10266f56b: [HIP] Move std headers after device 
malloc/free (authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D105707/new/

https://reviews.llvm.org/D105707

Files:
  clang/lib/Headers/__clang_hip_runtime_wrapper.h
  clang/test/Headers/hip-header.hip

Index: clang/test/Headers/hip-header.hip
===
--- clang/test/Headers/hip-header.hip
+++ clang/test/Headers/hip-header.hip
@@ -115,3 +115,19 @@
 
   return r ;
 }
+
+// Check that device malloc and free do not conflict with std headers.
+#include 
+// CHECK-LABEL: define{{.*}}@_Z11test_malloc
+// CHECK: call {{.*}}i8* @malloc(i64
+// CHECK: define weak {{.*}}i8* @malloc(i64
+__device__ void test_malloc(void *a) {
+  a = malloc(42);
+}
+
+// CHECK-LABEL: define{{.*}}@_Z9test_free
+// CHECK: call {{.*}}i8* @free(i8*
+// CHECK: define weak {{.*}}i8* @free(i8*
+__device__ void test_free(void *a) {
+  free(a);
+}
Index: clang/lib/Headers/__clang_hip_runtime_wrapper.h
===
--- clang/lib/Headers/__clang_hip_runtime_wrapper.h
+++ clang/lib/Headers/__clang_hip_runtime_wrapper.h
@@ -18,28 +18,6 @@
 
 #if __HIP__
 
-#if !defined(__HIPCC_RTC__)
-#include 
-#include 
-#include 
-#else
-typedef __SIZE_TYPE__ size_t;
-// Define macros which are needed to declare HIP device API's without standard
-// C/C++ headers. This is for readability so that these API's can be written
-// the same way as non-hipRTC use case. These macros need to be popped so that
-// they do not pollute users' name space.
-#pragma push_macro("NULL")
-#pragma push_macro("uint32_t")
-#pragma push_macro("uint64_t")
-#pragma push_macro("CHAR_BIT")
-#pragma push_macro("INT_MAX")
-#define NULL (void *)0
-#define uint32_t __UINT32_TYPE__
-#define uint64_t __UINT64_TYPE__
-#define CHAR_BIT __CHAR_BIT__
-#define INT_MAX __INTMAX_MAX__
-#endif // __HIPCC_RTC__
-
 #define __host__ __attribute__((host))
 #define __device__ __attribute__((device))
 #define __global__ __attribute__((global))
@@ -68,24 +46,58 @@
 }
 #endif //__cplusplus
 
+typedef __SIZE_TYPE__ __hip_size_t;
+
+#ifdef __cplusplus
+extern "C" {
+#endif //__cplusplus
+
 #if __HIP_ENABLE_DEVICE_MALLOC__
-extern "C" __device__ void *__hip_malloc(size_t __size);
-extern "C" __device__ void *__hip_free(void *__ptr);
-static inline __device__ void *malloc(size_t __size) {
+__device__ void *__hip_malloc(__hip_size_t __size);
+__device__ void *__hip_free(void *__ptr);
+__attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   return __hip_malloc(__size);
 }
-static inline __device__ void *free(void *__ptr) { return __hip_free(__ptr); }
+__attribute__((weak)) inline __device__ void *free(void *__ptr) {
+  return __hip_free(__ptr);
+}
 #else
-static inline __device__ void *malloc(size_t __size) {
+__attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   __builtin_trap();
   return nullptr;
 }
-static inline __device__ void *free(void *__ptr) {
+__attribute__((weak)) inline __device__ void *free(void *__ptr) {
   __builtin_trap();
   return nullptr;
 }
 #endif
 
+#ifdef __cplusplus
+} // extern "C"
+#endif //__cplusplus
+
+#if !defined(__HIPCC_RTC__)
+#include 
+#include 
+#include 
+#else
+typedef __SIZE_TYPE__ size_t;
+// Define macros which are needed to declare HIP device API's without standard
+// C/C++ headers. This is for readability so that these API's can be written
+// the same way as non-hipRTC use case. These macros need to be popped so that
+// they do not pollute users' name space.
+#pragma push_macro("NULL")
+#pragma push_macro("uint32_t")
+#pragma push_macro("uint64_t")
+#pragma push_macro("CHAR_BIT")
+#pragma push_macro("INT_MAX")
+#define NULL (void *)0
+#define uint32_t __UINT32_TYPE__
+#define uint64_t __UINT64_TYPE__
+#define CHAR_BIT __CHAR_BIT__
+#define INT_MAX __INTMAX_MAX__
+#endif // __HIPCC_RTC__
+
 #include <__clang_hip_libdevice_declares.h>
 #include <__clang_hip_math.h>
 
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D70980: [HIP] Remove opencl.amdgcn.lib

2019-12-03 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.
This revision is now accepted and ready to land.

LGTM


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D70980/new/

https://reviews.llvm.org/D70980



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D98278: [test] Add ability to get error messages from CMake for errc substitution

2021-03-18 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 added a comment.

In D98278#2618936 , @zero9178 wrote:

> In D98278#2616932 , @mstorsjo wrote:
>
>> In D98278#2616916 , @zero9178 wrote:
>>
>>> Add GetErrcMessages.cmake, which contains a cmake function to automatically 
>>> get the error messages of various posix error codes needed by lit by 
>>> running a small C++ program.
>>> Currently ENOENT, EISDIR, EINVAL and EACCES are supplied. 
>>> These error messages are then currently supplied to clang, llvm and lld as 
>>> the errc_messages config parameter.
>>>
>>> Regarding Cross compiling: the function uses try_run which when cross 
>>> compiling may use the CMAKE_CROSSCOMPILING_EMULATOR to run the code.
>>
>> How does it behave if such a thing isn't hooked up? Ideally it'd fall back 
>> silently and these parts of tests would just fail, but not block things 
>> overall.
>
> It will fall back to using Python's strerror, potentially failing if pythons 
> strerror would not return the same strings (only the case for MSVC I believe).

Hi, this patch is causing a failure when cmake runs `try_run()` with a 
`CMAKE_TOOLCHAIN_FILE` defined. It seems related to having a fall back if the 
try_run fails.
Here is the error, and the build uses MSVC. What do you think we could do about 
this? Thanks.

  [06:48:06][Step 1/4] CMake Error: TRY_RUN() invoked in cross-compiling mode, 
please set the following cache variables appropriately:
  [06:48:06][Step 1/4]errc_exit_code (advanced)
  [06:48:06][Step 1/4]errc_exit_code__TRYRUN_OUTPUT (advanced)
  [06:48:06][Step 1/4] For details see /TryRunResults.cmake


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D98278/new/

https://reviews.llvm.org/D98278

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D99738: [HIP] remove overloaded abs in header

2021-04-01 Thread Aaron Enye Shi via Phabricator via cfe-commits

ashi1 accepted this revision.
ashi1 added a comment.
This revision is now accepted and ready to land.

LGTM, thank you.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D99738/new/

https://reviews.llvm.org/D99738

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D100045: [HIP] Fix rocm-detect.hip test path

2021-04-07 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rGdf59850038d8: [HIP] Fix rocm-detect.hip test path (authored 
by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Changed prior to commit:
  https://reviews.llvm.org/D100045?vs=335838&id=335860#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D100045/new/

https://reviews.llvm.org/D100045

Files:
  clang/test/Driver/rocm-detect.hip


Index: clang/test/Driver/rocm-detect.hip
===
--- clang/test/Driver/rocm-detect.hip
+++ clang/test/Driver/rocm-detect.hip
@@ -81,7 +81,7 @@
 
 // SPACK: ROCm installation search path (Spack 4.0.0): [[DIR:.*]]
 // SPACK: ROCm installation search path: [[CLANG:.*]]
-// SPACK: ROCm installation search path: [[CLANG]]/lib/clang/{{[0-9.]+}}
+// SPACK: ROCm installation search path: 
[[CLANG]]/{{(llvm/)?}}lib/clang/{{[0-9.]+}}
 // SPACK: ROCm installation search path: /opt/rocm
 // SPACK: InstalledDir: 
[[DIR]]/llvm-amdgpu-4.0.0-ieagcs7inf7runpyfvepqkurasoglq4z/bin
 // SPACK: Found HIP installation: 
[[DIR]]/hip-4.0.0-5f63slrursbrvfe2txrrjkynbsywsob5, version 4.0.20214-a2917cd


Index: clang/test/Driver/rocm-detect.hip
===
--- clang/test/Driver/rocm-detect.hip
+++ clang/test/Driver/rocm-detect.hip
@@ -81,7 +81,7 @@
 
 // SPACK: ROCm installation search path (Spack 4.0.0): [[DIR:.*]]
 // SPACK: ROCm installation search path: [[CLANG:.*]]
-// SPACK: ROCm installation search path: [[CLANG]]/lib/clang/{{[0-9.]+}}
+// SPACK: ROCm installation search path: [[CLANG]]/{{(llvm/)?}}lib/clang/{{[0-9.]+}}
 // SPACK: ROCm installation search path: /opt/rocm
 // SPACK: InstalledDir: [[DIR]]/llvm-amdgpu-4.0.0-ieagcs7inf7runpyfvepqkurasoglq4z/bin
 // SPACK: Found HIP installation: [[DIR]]/hip-4.0.0-5f63slrursbrvfe2txrrjkynbsywsob5, version 4.0.20214-a2917cd
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D93062: [HIP] Add signbit(long double) decl

2021-01-14 Thread Aaron Enye Shi via Phabricator via cfe-commits

This revision was automatically updated to reflect the committed changes.
Closed by commit rGbe40c12040a0: [HIP] Add signbit(long double) decl (authored 
by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D93062/new/

https://reviews.llvm.org/D93062

Files:
  clang/lib/Headers/__clang_cuda_math_forward_declares.h


Index: clang/lib/Headers/__clang_cuda_math_forward_declares.h
===
--- clang/lib/Headers/__clang_cuda_math_forward_declares.h
+++ clang/lib/Headers/__clang_cuda_math_forward_declares.h
@@ -160,6 +160,9 @@
 __DEVICE__ float scalbln(float, long);
 __DEVICE__ double scalbn(double, int);
 __DEVICE__ float scalbn(float, int);
+#ifdef _MSC_VER
+__DEVICE__ bool signbit(long double);
+#endif
 __DEVICE__ bool signbit(double);
 __DEVICE__ bool signbit(float);
 __DEVICE__ double sin(double);


Index: clang/lib/Headers/__clang_cuda_math_forward_declares.h
===
--- clang/lib/Headers/__clang_cuda_math_forward_declares.h
+++ clang/lib/Headers/__clang_cuda_math_forward_declares.h
@@ -160,6 +160,9 @@
 __DEVICE__ float scalbln(float, long);
 __DEVICE__ double scalbn(double, int);
 __DEVICE__ float scalbn(float, int);
+#ifdef _MSC_VER
+__DEVICE__ bool signbit(long double);
+#endif
 __DEVICE__ bool signbit(double);
 __DEVICE__ bool signbit(float);
 __DEVICE__ double sin(double);
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

71 matches

Mail list logo