maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/Driver/cuda-arch-translation.cu

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

100 lines
5.9 KiB
Plaintext
Raw Normal View History

[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// Tests that "sm_XX" gets correctly converted to "compute_YY" when we invoke
// fatbinary.
//
// REQUIRES: clang-driver
// REQUIRES: x86-registered-target
// REQUIRES: nvptx-registered-target
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 %s 2>&1 \
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// RUN: | FileCheck -check-prefixes=COMMON,SM20 %s
[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_21 %s 2>&1 \
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// RUN: | FileCheck -check-prefixes=COMMON,SM21 %s
[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_30 %s 2>&1 \
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// RUN: | FileCheck -check-prefixes=COMMON,SM30 %s
[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_32 %s 2>&1 \
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// RUN: | FileCheck -check-prefixes=COMMON,SM32 %s
[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_35 %s 2>&1 \
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// RUN: | FileCheck -check-prefixes=COMMON,SM35 %s
[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_37 %s 2>&1 \
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// RUN: | FileCheck -check-prefixes=COMMON,SM37 %s
[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_50 %s 2>&1 \
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// RUN: | FileCheck -check-prefixes=COMMON,SM50 %s
[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_52 %s 2>&1 \
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// RUN: | FileCheck -check-prefixes=COMMON,SM52 %s
[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_53 %s 2>&1 \
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// RUN: | FileCheck -check-prefixes=COMMON,SM53 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_60 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,SM60 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_61 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,SM61 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_62 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,SM62 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=sm_70 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,SM70 %s
[CUDA] Add amdgpu sub archs Patch by Greg Rodgers. Revised and lit tests added by Yaxun Liu. Differential Revision: https://reviews.llvm.org/D45277 llvm-svn: 329232
2018-04-05 05:19:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx600 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX600 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx601 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX601 %s
[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
2020-10-07 01:23:59 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx602 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX602 %s
[CUDA] Add amdgpu sub archs Patch by Greg Rodgers. Revised and lit tests added by Yaxun Liu. Differential Revision: https://reviews.llvm.org/D45277 llvm-svn: 329232
2018-04-05 05:19:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx700 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX700 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx701 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX701 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx702 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX702 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx703 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX703 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx704 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX704 %s
[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
2020-10-07 01:23:59 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx705 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX705 %s
[CUDA] Add amdgpu sub archs Patch by Greg Rodgers. Revised and lit tests added by Yaxun Liu. Differential Revision: https://reviews.llvm.org/D45277 llvm-svn: 329232
2018-04-05 05:19:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx801 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX801 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx802 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX802 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx803 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX803 %s
[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
2020-10-07 01:23:59 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx805 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX805 %s
[CUDA] Add amdgpu sub archs Patch by Greg Rodgers. Revised and lit tests added by Yaxun Liu. Differential Revision: https://reviews.llvm.org/D45277 llvm-svn: 329232
2018-04-05 05:19:27 +08:00
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx810 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX810 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx900 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX900 %s
// RUN: %clang -### -target x86_64-linux-gnu -c --cuda-gpu-arch=gfx902 %s 2>&1 \
// RUN: | FileCheck -check-prefixes=COMMON,GFX902 %s
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// COMMON: ptxas
// COMMON-SAME: -m64
// COMMON: fatbinary
[CUDA] Invoke ptxas and fatbinary during compilation. Summary: Previously we compiled CUDA device code to PTX assembly and embedded that asm as text in our host binary. Now we compile to PTX assembly and then invoke ptxas to assemble the PTX into a cubin file. We gather the ptx and cubin files for each of our --cuda-gpu-archs and combine them using fatbinary, and then embed that into the host binary. Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary, which pass args down to the external tools. Reviewers: tra, echristo Subscribers: cfe-commits, jhen Differential Revision: http://reviews.llvm.org/D16082 llvm-svn: 257809
2016-01-15 05:41:27 +08:00
// SM20:--image=profile=sm_20{{.*}}--image=profile=compute_20
// SM21:--image=profile=sm_21{{.*}}--image=profile=compute_20
// SM30:--image=profile=sm_30{{.*}}--image=profile=compute_30
// SM32:--image=profile=sm_32{{.*}}--image=profile=compute_32
// SM35:--image=profile=sm_35{{.*}}--image=profile=compute_35
// SM37:--image=profile=sm_37{{.*}}--image=profile=compute_37
// SM50:--image=profile=sm_50{{.*}}--image=profile=compute_50
// SM52:--image=profile=sm_52{{.*}}--image=profile=compute_52
// SM53:--image=profile=sm_53{{.*}}--image=profile=compute_53
[CUDA] Added rudimentary support for CUDA-9 and sm_70. For now CUDA-9 is not included in the list of CUDA versions clang searches for, so the path to CUDA-9 must be explicitly passed via --cuda-path=. On LLVM side NVPTX added sm_70 GPU type which bumps required PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment. Differential Revision: https://reviews.llvm.org/D37576 llvm-svn: 312734
2017-09-08 02:14:32 +08:00
// SM60:--image=profile=sm_60{{.*}}--image=profile=compute_60
// SM61:--image=profile=sm_61{{.*}}--image=profile=compute_61
// SM62:--image=profile=sm_62{{.*}}--image=profile=compute_62
// SM70:--image=profile=sm_70{{.*}}--image=profile=compute_70
[CUDA] Add amdgpu sub archs Patch by Greg Rodgers. Revised and lit tests added by Yaxun Liu. Differential Revision: https://reviews.llvm.org/D45277 llvm-svn: 329232
2018-04-05 05:19:27 +08:00
// GFX600:--image=profile=gfx600{{.*}}--image=profile=compute_amdgcn
// GFX601:--image=profile=gfx601{{.*}}--image=profile=compute_amdgcn
[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
2020-10-07 01:23:59 +08:00
// GFX602:--image=profile=gfx602{{.*}}--image=profile=compute_amdgcn
[CUDA] Add amdgpu sub archs Patch by Greg Rodgers. Revised and lit tests added by Yaxun Liu. Differential Revision: https://reviews.llvm.org/D45277 llvm-svn: 329232
2018-04-05 05:19:27 +08:00
// GFX700:--image=profile=gfx700{{.*}}--image=profile=compute_amdgcn
// GFX701:--image=profile=gfx701{{.*}}--image=profile=compute_amdgcn
// GFX702:--image=profile=gfx702{{.*}}--image=profile=compute_amdgcn
// GFX703:--image=profile=gfx703{{.*}}--image=profile=compute_amdgcn
// GFX704:--image=profile=gfx704{{.*}}--image=profile=compute_amdgcn
[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
2020-10-07 01:23:59 +08:00
// GFX705:--image=profile=gfx705{{.*}}--image=profile=compute_amdgcn
[CUDA] Add amdgpu sub archs Patch by Greg Rodgers. Revised and lit tests added by Yaxun Liu. Differential Revision: https://reviews.llvm.org/D45277 llvm-svn: 329232
2018-04-05 05:19:27 +08:00
// GFX801:--image=profile=gfx801{{.*}}--image=profile=compute_amdgcn
// GFX802:--image=profile=gfx802{{.*}}--image=profile=compute_amdgcn
// GFX803:--image=profile=gfx803{{.*}}--image=profile=compute_amdgcn
[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
2020-10-07 01:23:59 +08:00
// GFX805:--image=profile=gfx805{{.*}}--image=profile=compute_amdgcn
[CUDA] Add amdgpu sub archs Patch by Greg Rodgers. Revised and lit tests added by Yaxun Liu. Differential Revision: https://reviews.llvm.org/D45277 llvm-svn: 329232
2018-04-05 05:19:27 +08:00
// GFX810:--image=profile=gfx810{{.*}}--image=profile=compute_amdgcn
// GFX900:--image=profile=gfx900{{.*}}--image=profile=compute_amdgcn
// GFX902:--image=profile=gfx902{{.*}}--image=profile=compute_amdgcn