r345198 - Add gfx909 to GPU Arch

2018-10-24 Thread Tim Renouf via cfe-commits 
Author: tpr
Date: Wed Oct 24 14:19:02 2018
New Revision: 345198

URL: http://llvm.org/viewvc/llvm-project?rev=345198&view=rev
Log:
Add gfx909 to GPU Arch

Subscribers: jholewinski, cfe-commits

Differential Revision: https://reviews.llvm.org/D53558

Modified:
cfe/trunk/include/clang/Basic/Cuda.h
cfe/trunk/lib/Basic/Cuda.cpp
cfe/trunk/lib/Basic/Targets/NVPTX.cpp

Modified: cfe/trunk/include/clang/Basic/Cuda.h
URL: 
http://llvm.org/viewvc/llvm-project/cfe/trunk/include/clang/Basic/Cuda.h?rev=345198&r1=345197&r2=345198&view=diff
==
--- cfe/trunk/include/clang/Basic/Cuda.h (original)
+++ cfe/trunk/include/clang/Basic/Cuda.h Wed Oct 24 14:19:02 2018
@@ -64,6 +64,7 @@ enum class CudaArch {
   GFX902,
   GFX904,
   GFX906,
+  GFX909,
   LAST,
 };
 const char *CudaArchToString(CudaArch A);

Modified: cfe/trunk/lib/Basic/Cuda.cpp
URL: 
http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Basic/Cuda.cpp?rev=345198&r1=345197&r2=345198&view=diff
==
--- cfe/trunk/lib/Basic/Cuda.cpp (original)
+++ cfe/trunk/lib/Basic/Cuda.cpp Wed Oct 24 14:19:02 2018
@@ -94,6 +94,8 @@ const char *CudaArchToString(CudaArch A)
 return "gfx904";
   case CudaArch::GFX906: // TBA
 return "gfx906";
+  case CudaArch::GFX909: // TBA
+return "gfx909";
   }
   llvm_unreachable("invalid enum");
 }
@@ -130,6 +132,7 @@ CudaArch StringToCudaArch(llvm::StringRe
   .Case("gfx902", CudaArch::GFX902)
   .Case("gfx904", CudaArch::GFX904)
   .Case("gfx906", CudaArch::GFX906)
+  .Case("gfx909", CudaArch::GFX909)
   .Default(CudaArch::UNKNOWN);
 }
 
@@ -241,6 +244,7 @@ CudaVirtualArch VirtualArchForCudaArch(C
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVirtualArch::COMPUTE_AMDGCN;
   }
   llvm_unreachable("invalid enum");
@@ -287,6 +291,7 @@ CudaVersion MinVersionForCudaArch(CudaAr
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVersion::CUDA_70;
   }
   llvm_unreachable("invalid enum");

Modified: cfe/trunk/lib/Basic/Targets/NVPTX.cpp
URL: 
http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Basic/Targets/NVPTX.cpp?rev=345198&r1=345197&r2=345198&view=diff
==
--- cfe/trunk/lib/Basic/Targets/NVPTX.cpp (original)
+++ cfe/trunk/lib/Basic/Targets/NVPTX.cpp Wed Oct 24 14:19:02 2018
@@ -190,6 +190,7 @@ void NVPTXTargetInfo::getTargetDefines(c
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
   case CudaArch::LAST:
 break;
   case CudaArch::UNKNOWN:


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

[clang] 666ef0d - [AMDGPU] Add gfx602, gfx705, gfx805 targets

2020-10-10 Thread Tim Renouf via cfe-commits 

Author: Tim Renouf
Date: 2020-10-10T17:22:22+01:00
New Revision: 666ef0db208bb3880115bdc133e72e954ed55300

URL: 
https://github.com/llvm/llvm-project/commit/666ef0db208bb3880115bdc133e72e954ed55300
DIFF: 
https://github.com/llvm/llvm-project/commit/666ef0db208bb3880115bdc133e72e954ed55300.diff

LOG: [AMDGPU] Add gfx602, gfx705, gfx805 targets

At AMD, in an internal audit of our code, we found some corner cases
where we were not quite differentiating targets enough for some old
hardware. This commit is part of fixing that by adding three new
targets:

* The "Oland" and "Hainan" variants of gfx601 are now split out into
  gfx602. LLPC (in the GPUOpen driver) and other front-ends could use
  that to avoid using the shaderZExport workaround on gfx602.

* One variant of gfx703 is now split out into gfx705. LLPC and other
  front-ends could use that to avoid using the
  shaderSpiCsRegAllocFragmentation workaround on gfx705.

* The "TongaPro" variant of gfx802 is now split out into gfx805.
  TongaPro has a faster 64-bit shift than its former friends in gfx802,
  and a subtarget feature could be set up for that to take advantage of
  it. This commit does not make that change; it just adds the target.

V2: Add clang changes. Put TargetParser list in order.
V3: AMDGCNGPUs table in TargetParser.cpp needs to be in GPUKind order,
so fix the GPUKind order.

Differential Revision: https://reviews.llvm.org/D88916

Change-Id: Ia901a7157eb2f73ccd9f25dbacec38427312377d

Added: 


Modified: 
clang/include/clang/Basic/Cuda.h
clang/lib/Basic/Cuda.cpp
clang/lib/Basic/Targets/AMDGPU.cpp
clang/lib/Basic/Targets/NVPTX.cpp
clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
clang/test/CodeGenOpenCL/amdgpu-features.cl
clang/test/Driver/amdgpu-macros.cl
clang/test/Driver/amdgpu-mcpu.cl
clang/test/Driver/cuda-arch-translation.cu
clang/test/Misc/target-invalid-cpu-note.c
llvm/docs/AMDGPUUsage.rst
llvm/include/llvm/BinaryFormat/ELF.h
llvm/include/llvm/Support/TargetParser.h
llvm/lib/Object/ELFObjectFile.cpp
llvm/lib/ObjectYAML/ELFYAML.cpp
llvm/lib/Support/TargetParser.cpp
llvm/lib/Target/AMDGPU/AMDGPU.td
llvm/lib/Target/AMDGPU/GCNProcessors.td
llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
llvm/tools/llvm-readobj/ELFDumper.cpp

Removed: 




diff  --git a/clang/include/clang/Basic/Cuda.h 
b/clang/include/clang/Basic/Cuda.h
index 93394f31abdc..417d40c28adf 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -57,14 +57,17 @@ enum class CudaArch {
   SM_80,
   GFX600,
   GFX601,
+  GFX602,
   GFX700,
   GFX701,
   GFX702,
   GFX703,
   GFX704,
+  GFX705,
   GFX801,
   GFX802,
   GFX803,
+  GFX805,
   GFX810,
   GFX900,
   GFX902,

diff  --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index 7de42c1b90e5..42a8a097b1fd 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -73,15 +73,18 @@ CudaArchToStringMap arch_names[] = {
 SM(75),  // Turing
 SM(80),  // Ampere
 GFX(600), // tahiti
-GFX(601), // pitcairn, verde, oland,hainan
+GFX(601), // pitcairn, verde
+GFX(602), // oland, hainan
 GFX(700), // kaveri
 GFX(701), // hawaii
 GFX(702), // 290,290x,R390,R390x
 GFX(703), // kabini mullins
 GFX(704), // bonaire
+GFX(705),
 GFX(801), // carrizo
 GFX(802), // tonga,iceland
 GFX(803), // fiji,polaris10
+GFX(805), // tongapro
 GFX(810), // stoney
 GFX(900), // vega, instinct
 GFX(902), GFX(904), GFX(906), GFX(908), GFX(909),

diff  --git a/clang/lib/Basic/Targets/AMDGPU.cpp 
b/clang/lib/Basic/Targets/AMDGPU.cpp
index ba9be72af971..42db207b9ce5 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -228,6 +228,7 @@ bool AMDGPUTargetInfo::initFeatureMap(
   Features["gfx9-insts"] = true;
   LLVM_FALLTHROUGH;
 case GK_GFX810:
+case GK_GFX805:
 case GK_GFX803:
 case GK_GFX802:
 case GK_GFX801:
@@ -236,6 +237,7 @@ bool AMDGPUTargetInfo::initFeatureMap(
   Features["dpp"] = true;
   Features["s-memrealtime"] = true;
   LLVM_FALLTHROUGH;
+case GK_GFX705:
 case GK_GFX704:
 case GK_GFX703:
 case GK_GFX702:
@@ -244,6 +246,7 @@ bool AMDGPUTargetInfo::initFeatureMap(
   Features["ci-insts"] = true;
   Features["flat-address-space"] = true;
   LLVM_FALLTHROUGH;
+case GK_GFX602:
 case GK_GFX601:
 case GK_GFX600:
   break;

diff  --git a/clang/lib/Basic/Targets/NVPTX.cpp 
b/clang/lib/Basic/Targets/NVPTX.cpp
index aae89477e97d..3780f1cc250c 100644
--- a/clang/lib/B

[clang] 89d41f3 - [AMDGPU] Add gfx1033 target

2020-11-03 Thread Tim Renouf via cfe-commits 

Author: Tim Renouf
Date: 2020-11-03T16:27:48Z
New Revision: 89d41f3a2b820c17edeb86a2e9d458ca69eca34e

URL: 
https://github.com/llvm/llvm-project/commit/89d41f3a2b820c17edeb86a2e9d458ca69eca34e
DIFF: 
https://github.com/llvm/llvm-project/commit/89d41f3a2b820c17edeb86a2e9d458ca69eca34e.diff

LOG: [AMDGPU] Add gfx1033 target

Differential Revision: https://reviews.llvm.org/D90447

Change-Id: If2650fc7f31bbdd49c76e74a9ca8e3734d769761

Added: 


Modified: 
clang/include/clang/Basic/Cuda.h
clang/lib/Basic/Cuda.cpp
clang/lib/Basic/Targets/AMDGPU.cpp
clang/lib/Basic/Targets/NVPTX.cpp
clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
clang/test/CodeGenOpenCL/amdgpu-features.cl
clang/test/Driver/amdgpu-macros.cl
clang/test/Driver/amdgpu-mcpu.cl
llvm/docs/AMDGPUUsage.rst
llvm/include/llvm/BinaryFormat/ELF.h
llvm/include/llvm/Support/TargetParser.h
llvm/lib/Object/ELFObjectFile.cpp
llvm/lib/ObjectYAML/ELFYAML.cpp
llvm/lib/Support/TargetParser.cpp
llvm/lib/Target/AMDGPU/GCNProcessors.td
llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
llvm/test/MC/AMDGPU/gfx1011_dlops.s
llvm/test/MC/AMDGPU/gfx1030_err.s
llvm/test/MC/AMDGPU/gfx1030_new.s
llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
llvm/tools/llvm-readobj/ELFDumper.cpp

Removed: 




diff  --git a/clang/include/clang/Basic/Cuda.h 
b/clang/include/clang/Basic/Cuda.h
index 887030e2c49f..b3a2e99fe931 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -82,6 +82,7 @@ enum class CudaArch {
   GFX1030,
   GFX1031,
   GFX1032,
+  GFX1033,
   LAST,
 };
 

diff  --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index 5977084b5cc1..d9f79a1a10d5 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -88,7 +88,7 @@ CudaArchToStringMap arch_names[] = {
 GFX(810), // stoney
 GFX(900), // vega, instinct
 GFX(902), GFX(904), GFX(906), GFX(908), GFX(909), GFX(90c),
-GFX(1010), GFX(1011), GFX(1012), GFX(1030), GFX(1031)
+GFX(1010), GFX(1011), GFX(1012), GFX(1030), GFX(1031), GFX(1032), GFX(1033)
 // clang-format on
 };
 #undef SM

diff  --git a/clang/lib/Basic/Targets/AMDGPU.cpp 
b/clang/lib/Basic/Targets/AMDGPU.cpp
index 5ee887d464c6..4d6a9a5e0b51 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -174,6 +174,7 @@ bool AMDGPUTargetInfo::initFeatureMap(
   // XXX - What does the member GPU mean if device name string passed here?
   if (isAMDGCN(getTriple())) {
 switch (llvm::AMDGPU::parseArchAMDGCN(CPU)) {
+case GK_GFX1033:
 case GK_GFX1032:
 case GK_GFX1031:
 case GK_GFX1030:

diff  --git a/clang/lib/Basic/Targets/NVPTX.cpp 
b/clang/lib/Basic/Targets/NVPTX.cpp
index 7a8ae0d7ce72..b7f0dce33d2b 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -207,6 +207,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions 
&Opts,
   case CudaArch::GFX1030:
   case CudaArch::GFX1031:
   case CudaArch::GFX1032:
+  case CudaArch::GFX1033:
   case CudaArch::LAST:
 break;
   case CudaArch::UNUSED:

diff  --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp 
b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 6fe99ed89dab..a3540bd30ab3 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4647,6 +4647,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
   case CudaArch::GFX1030:
   case CudaArch::GFX1031:
   case CudaArch::GFX1032:
+  case CudaArch::GFX1033:
   case CudaArch::UNUSED:
   case CudaArch::UNKNOWN:
 break;
@@ -4714,6 +4715,7 @@ static std::pair 
getSMsBlocksPerSM(CodeGenModule &CGM) {
   case CudaArch::GFX1030:
   case CudaArch::GFX1031:
   case CudaArch::GFX1032:
+  case CudaArch::GFX1033:
   case CudaArch::UNUSED:
   case CudaArch::UNKNOWN:
 break;

diff  --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl 
b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 67ddf6c70df1..813b39d9ec7b 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -19,6 +19,7 @@
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1030 -S -emit-llvm -o - %s | 
FileCheck --check-prefix=GFX1030 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1031 -S -emit-llvm -o - %s | 
FileCheck --check-prefix=GFX1031 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1032 -S -emit-llvm -o - %s | 
FileCheck --check-prefix=GFX1032 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1033 -S -emit-llvm -o - %s | 
FileCh

[clang] ee3e642 - [AMDGPU] Add gfx90c target

2020-11-03 Thread Tim Renouf via cfe-commits 

Author: Tim Renouf
Date: 2020-11-03T16:27:43Z
New Revision: ee3e642627575bc8fb0a7008f8a02c891e172b7b

URL: 
https://github.com/llvm/llvm-project/commit/ee3e642627575bc8fb0a7008f8a02c891e172b7b
DIFF: 
https://github.com/llvm/llvm-project/commit/ee3e642627575bc8fb0a7008f8a02c891e172b7b.diff

LOG: [AMDGPU] Add gfx90c target

This differentiates the Ryzen 4000/4300/4500/4700 series APUs that were
previously included in gfx909.

Differential Revision: https://reviews.llvm.org/D90419

Change-Id: Ia901a7157eb2f73ccd9f25dbacec38427312377d

Added: 


Modified: 
clang/include/clang/Basic/Cuda.h
clang/lib/Basic/Cuda.cpp
clang/lib/Basic/Targets/AMDGPU.cpp
clang/lib/Basic/Targets/NVPTX.cpp
clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
clang/test/CodeGenOpenCL/amdgpu-features.cl
clang/test/Driver/amdgpu-macros.cl
clang/test/Driver/amdgpu-mcpu.cl
llvm/docs/AMDGPUUsage.rst
llvm/include/llvm/BinaryFormat/ELF.h
llvm/include/llvm/Support/TargetParser.h
llvm/lib/Object/ELFObjectFile.cpp
llvm/lib/ObjectYAML/ELFYAML.cpp
llvm/lib/Support/TargetParser.cpp
llvm/lib/Target/AMDGPU/AMDGPU.td
llvm/lib/Target/AMDGPU/GCNProcessors.td
llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
llvm/tools/llvm-readobj/ELFDumper.cpp

Removed: 




diff  --git a/clang/include/clang/Basic/Cuda.h 
b/clang/include/clang/Basic/Cuda.h
index 501e47b0e2c2..887030e2c49f 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -75,6 +75,7 @@ enum class CudaArch {
   GFX906,
   GFX908,
   GFX909,
+  GFX90c,
   GFX1010,
   GFX1011,
   GFX1012,

diff  --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index 42a8a097b1fd..5977084b5cc1 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -87,7 +87,7 @@ CudaArchToStringMap arch_names[] = {
 GFX(805), // tongapro
 GFX(810), // stoney
 GFX(900), // vega, instinct
-GFX(902), GFX(904), GFX(906), GFX(908), GFX(909),
+GFX(902), GFX(904), GFX(906), GFX(908), GFX(909), GFX(90c),
 GFX(1010), GFX(1011), GFX(1012), GFX(1030), GFX(1031)
 // clang-format on
 };

diff  --git a/clang/lib/Basic/Targets/AMDGPU.cpp 
b/clang/lib/Basic/Targets/AMDGPU.cpp
index 0b3aebdfa15c..5ee887d464c6 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -222,6 +222,7 @@ bool AMDGPUTargetInfo::initFeatureMap(
   Features["dot1-insts"] = true;
   Features["dot2-insts"] = true;
   LLVM_FALLTHROUGH;
+case GK_GFX90C:
 case GK_GFX909:
 case GK_GFX904:
 case GK_GFX902:

diff  --git a/clang/lib/Basic/Targets/NVPTX.cpp 
b/clang/lib/Basic/Targets/NVPTX.cpp
index 26c5b26beeef..7a8ae0d7ce72 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -200,6 +200,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions 
&Opts,
   case CudaArch::GFX906:
   case CudaArch::GFX908:
   case CudaArch::GFX909:
+  case CudaArch::GFX90c:
   case CudaArch::GFX1010:
   case CudaArch::GFX1011:
   case CudaArch::GFX1012:

diff  --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp 
b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 08903a1444c2..6fe99ed89dab 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4640,6 +4640,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
   case CudaArch::GFX906:
   case CudaArch::GFX908:
   case CudaArch::GFX909:
+  case CudaArch::GFX90c:
   case CudaArch::GFX1010:
   case CudaArch::GFX1011:
   case CudaArch::GFX1012:
@@ -4706,6 +4707,7 @@ static std::pair 
getSMsBlocksPerSM(CodeGenModule &CGM) {
   case CudaArch::GFX906:
   case CudaArch::GFX908:
   case CudaArch::GFX909:
+  case CudaArch::GFX90c:
   case CudaArch::GFX1010:
   case CudaArch::GFX1011:
   case CudaArch::GFX1012:

diff  --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl 
b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 6a27c047d58c..67ddf6c70df1 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -12,6 +12,7 @@
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx906 -S -emit-llvm -o - %s | 
FileCheck --check-prefix=GFX906 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx908 -S -emit-llvm -o - %s | 
FileCheck --check-prefix=GFX908 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx909 -S -emit-llvm -o - %s | 
FileCheck --check-prefix=GFX909 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx90c -S -emit-llvm -o - %s | 
FileCheck --check-prefix=GFX90C %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1010 -S -emit-llvm -o - %s | 
FileCheck --check-prefix=GFX1010 %s
 // RUN: %clang_cc1 -t