hliao created this revision.
hliao added reviewers: yaxunl, tra.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.
- In HIP, just as the regular device-only compilation, the device-only
relocatable code compilation should not involve offload bundle.
- In addition, that device-only relocatable code compilation should have the
similar 3 steps, namely preprocessor, compile, and backend, to the regular code
generation with `-emit-llvm`.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D81427
Files:
clang/lib/Driver/Driver.cpp
clang/test/Driver/hip-device-only.hip
Index: clang/test/Driver/hip-device-only.hip
===================================================================
--- /dev/null
+++ clang/test/Driver/hip-device-only.hip
@@ -0,0 +1,144 @@
+// 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: -c -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
+// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITBC %s
+
+// With `-emit-llvm`, the output should be the same as the aforementioned line
+// as `-fgpu-rdc` in HIP implies `-emit-llvm`.
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN: -c -emit-llvm -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
+// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITBC %s
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN: -S -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
+// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITLL %s
+
+// With `-emit-llvm`, the output should be the same as the aforementioned line
+// as `-fgpu-rdc` in HIP implies `-emit-llvm`.
+
+// RUN: %clang -### -target x86_64-linux-gnu \
+// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN: -S -emit-llvm -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
+// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITLL %s
+
+// With `-save-temps`, commane lines for each steps are dumped. For assembly
+// output, there should 3 steps (preprocessor, compile, and backend) per source
+// and per target, totally 12 steps.
+
+// RUN: %clang -### -save-temps -target x86_64-linux-gnu \
+// RUN: -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN: -S -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
+// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN: %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck -check-prefix=SAVETEMP %s
+
+// COMMON: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// EMITBC-SAME: "-emit-llvm-bc"
+// EMITLL-SAME: "-emit-llvm"
+// COMMON-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
+// COMMON-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
+// COMMON-SAME: "-fapply-global-visibility-to-externs"
+// EMITBC-SAME: {{.*}} "-o" {{"a.*bc"}} "-x" "hip"
+// EMITLL-SAME: {{.*}} "-o" {{"a.*ll"}} "-x" "hip"
+// CHECK-SAME: {{.*}} {{".*a.cu"}}
+
+// COMMON: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// EMITBC-SAME: "-emit-llvm-bc"
+// EMITLL-SAME: "-emit-llvm"
+// COMMON-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
+// COMMON-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
+// COMMON-SAME: "-fapply-global-visibility-to-externs"
+// EMITBC-SAME: {{.*}} "-o" {{"a.*bc"}} "-x" "hip"
+// EMITLL-SAME: {{.*}} "-o" {{"a.*ll"}} "-x" "hip"
+// COMMON-SAME: {{.*}} {{".*a.cu"}}
+
+// COMMON: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// EMITBC-SAME: "-emit-llvm-bc"
+// EMITLL-SAME: "-emit-llvm"
+// COMMON-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
+// COMMON-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
+// COMMON-SAME: "-fapply-global-visibility-to-externs"
+// EMITBC-SAME: {{.*}} "-o" {{"b.*bc"}} "-x" "hip"
+// EMITLL-SAME: {{.*}} "-o" {{"b.*ll"}} "-x" "hip"
+// COMMON-SAME: {{.*}} {{".*b.hip"}}
+
+// COMMON: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// COMMON-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// EMITBC-SAME: "-emit-llvm-bc"
+// EMITLL-SAME: "-emit-llvm"
+// COMMON-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
+// COMMON-SAME: "-fcuda-is-device" "-fgpu-rdc" "-fcuda-allow-variadic-functions" "-fvisibility" "hidden"
+// COMMON-SAME: "-fapply-global-visibility-to-externs"
+// EMITBC-SAME: {{.*}} "-o" {{"b.*bc"}} "-x" "hip"
+// EMITLL-SAME: {{.*}} "-o" {{"b.*ll"}} "-x" "hip"
+// COMMON-SAME: {{.*}} {{".*b.hip"}}
+
+// SAVETEMP: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-E"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
+// SAVETEMP-SAME: {{.*}} "-o" [[A_GFX803_CUI:"a.*cui"]] "-x" "hip" {{".*a.cu"}}
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-emit-llvm-bc"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
+// SAVETEMP-SAME: {{.*}} "-o" [[A_GFX803_TMP_BC:"a.*tmp.bc"]] "-x" "hip-cpp-output" [[A_GFX803_CUI]]
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-emit-llvm"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx803"
+// SAVETEMP-SAME: {{.*}} "-o" {{"a.*.ll"}} "-x" "ir" [[A_GFX803_TMP_BC]]
+
+// SAVETEMP: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-E"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
+// SAVETEMP-SAME: {{.*}} "-o" [[A_GFX900_CUI:"a.*cui"]] "-x" "hip" {{".*a.cu"}}
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-emit-llvm-bc"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
+// SAVETEMP-SAME: {{.*}} "-o" [[A_GFX900_TMP_BC:"a.*tmp.bc"]] "-x" "hip-cpp-output" [[A_GFX900_CUI]]
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-emit-llvm"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "a.cu" {{.*}} "-target-cpu" "gfx900"
+// SAVETEMP-SAME: {{.*}} "-o" {{"a.*.ll"}} "-x" "ir" [[A_GFX900_TMP_BC]]
+
+// SAVETEMP: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-E"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
+// SAVETEMP-SAME: {{.*}} "-o" [[B_GFX803_CUI:"b.*cui"]] "-x" "hip" {{".*b.hip"}}
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-emit-llvm-bc"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
+// SAVETEMP-SAME: {{.*}} "-o" [[B_GFX803_TMP_BC:"b.*tmp.bc"]] "-x" "hip-cpp-output" [[B_GFX803_CUI]]
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-emit-llvm"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx803"
+// SAVETEMP-SAME: {{.*}} "-o" {{"b.*.ll"}} "-x" "ir" [[B_GFX803_TMP_BC]]
+
+// SAVETEMP: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-E"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
+// SAVETEMP-SAME: {{.*}} "-o" [[B_GFX900_CUI:"b.*cui"]] "-x" "hip" {{".*b.hip"}}
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-emit-llvm-bc"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
+// SAVETEMP-SAME: {{.*}} "-o" [[B_GFX900_TMP_BC:"b.*tmp.bc"]] "-x" "hip-cpp-output" [[B_GFX900_CUI]]
+// SAVETEMP-NEXT: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa" "-aux-triple" "x86_64-unknown-linux-gnu"
+// SAVETEMP-SAME: "-emit-llvm"
+// SAVETEMP-SAME: {{.*}} "-main-file-name" "b.hip" {{.*}} "-target-cpu" "gfx900"
+// SAVETEMP-SAME: {{.*}} "-o" {{"b.*.ll"}} "-x" "ir" [[B_GFX900_TMP_BC]]
Index: clang/lib/Driver/Driver.cpp
===================================================================
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -2705,9 +2705,7 @@
// backend and assemble phases to output LLVM IR. Except for generating
// non-relocatable device coee, where we generate fat binary for device
// code and pass to host in Backend phase.
- if (CudaDeviceActions.empty() ||
- (CurPhase == phases::Backend && Relocatable) ||
- CurPhase == phases::Assemble)
+ if (CudaDeviceActions.empty())
return ABRT_Success;
assert(((CurPhase == phases::Link && Relocatable) ||
@@ -2781,9 +2779,11 @@
}
// By default, we produce an action for each device arch.
- for (Action *&A : CudaDeviceActions)
- A = C.getDriver().ConstructPhaseAction(C, Args, CurPhase, A,
- AssociatedOffloadKind);
+ if (!Relocatable || CurPhase <= phases::Backend) {
+ for (Action *&A : CudaDeviceActions)
+ A = C.getDriver().ConstructPhaseAction(C, Args, CurPhase, A,
+ AssociatedOffloadKind);
+ }
return (CompileDeviceOnly && CurPhase == FinalPhase) ? ABRT_Ignore_Host
: ABRT_Success;
@@ -3668,7 +3668,10 @@
Args.hasArg(options::OPT_S) ? types::TY_LTO_IR : types::TY_LTO_BC;
return C.MakeAction<BackendJobAction>(Input, Output);
}
- if (Args.hasArg(options::OPT_emit_llvm)) {
+ if (Args.hasArg(options::OPT_emit_llvm) ||
+ (TargetDeviceOffloadKind == Action::OFK_HIP &&
+ Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
+ false))) {
types::ID Output =
Args.hasArg(options::OPT_S) ? types::TY_LLVM_IR : types::TY_LLVM_BC;
return C.MakeAction<BackendJobAction>(Input, Output);
@@ -4588,8 +4591,12 @@
// When using both -save-temps and -emit-llvm, use a ".tmp.bc" suffix for
// the unoptimized bitcode so that it does not get overwritten by the ".bc"
// optimized bitcode output.
- if (!AtTopLevel && C.getArgs().hasArg(options::OPT_emit_llvm) &&
- JA.getType() == types::TY_LLVM_BC)
+ if (!AtTopLevel && JA.getType() == types::TY_LLVM_BC &&
+ (C.getArgs().hasArg(options::OPT_emit_llvm) ||
+ (JA.getOffloadingDeviceKind() == Action::OFK_HIP &&
+ isa<CompileJobAction>(JA) &&
+ C.getArgs().hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
+ false))))
Suffixed += ".tmp";
Suffixed += '.';
Suffixed += Suffix;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
