maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/lib/Basic/Cuda.cpp

372 lines
10 KiB
C++
Raw Normal View History

[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
#include "clang/Basic/Cuda.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/StringSwitch.h"
[CUDA] Fix "control reaches end of non-void function" warnings in Cuda.cpp. Some compilers are too dumb to realize that the switch statement covers all cases. (Don't use a "default" label, because we explicitly want to get a warning if our switch doesn't cover all the cases.) llvm-svn: 274713
2016-07-07 09:06:59 +08:00
#include "llvm/Support/ErrorHandling.h"
[CUDA] Propagate detected version of CUDA to cc1 ..and use it to control that parts of CUDA compilation that depend on the specific version of CUDA SDK. This patch has a placeholder for a 'new launch API' support which is in a separate patch. The list will be further extended in the upcoming patch to support CUDA-10.1. Differential Revision: https://reviews.llvm.org/D57487 llvm-svn: 352798
2019-02-01 05:32:24 +08:00
#include "llvm/Support/VersionTuple.h"
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
namespace clang {
const char *CudaVersionToString(CudaVersion V) {
switch (V) {
case CudaVersion::UNKNOWN:
return "unknown";
case CudaVersion::CUDA_70:
return "7.0";
case CudaVersion::CUDA_75:
return "7.5";
case CudaVersion::CUDA_80:
return "8.0";
[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
case CudaVersion::CUDA_90:
return "9.0";
[CUDA] Added partial support for CUDA-9.1 Clang can use CUDA-9.1 now, though new APIs (are not implemented yet. The major change is that headers in CUDA-9.1 went through substantial changes that started in CUDA-9.0 which required substantial changes in the cuda compatibility headers provided by clang. There are two major issues: * CUDA SDK no longer provides declarations for libdevice functions. * A lot of device-side functions have become nvcc's builtins and CUDA headers no longer contain their implementations. This patch changes the way CUDA headers are handled if we compile with CUDA 9.x. Both 9.0 and 9.1 are affected. * Clang provides its own declarations of libdevice functions. * For CUDA-9.x clang now provides implementation of device-side 'standard library' functions using libdevice. This patch should not affect compilation with CUDA-8. There may be some observable differences for CUDA-9.0, though they are not expected to affect functionality. Tested: CUDA test-suite tests for all supported combinations of: CUDA: 7.0,7.5,8.0,9.0,9.1 GPU: sm_20, sm_35, sm_60, sm_70 Differential Revision: https://reviews.llvm.org/D42513 llvm-svn: 323713
2018-01-30 08:00:12 +08:00
case CudaVersion::CUDA_91:
return "9.1";
[CUDA] Enable CUDA compilation with CUDA-9.2 Differential Revision: https://reviews.llvm.org/D45827 llvm-svn: 330753
2018-04-25 02:23:19 +08:00
case CudaVersion::CUDA_92:
return "9.2";
[CUDA] Added basic support for compiling with CUDA-10.0 llvm-svn: 342924
2018-09-25 07:10:44 +08:00
case CudaVersion::CUDA_100:
return "10.0";
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
[CUDA] Fix "control reaches end of non-void function" warnings in Cuda.cpp. Some compilers are too dumb to realize that the switch statement covers all cases. (Don't use a "default" label, because we explicitly want to get a warning if our switch doesn't cover all the cases.) llvm-svn: 274713
2016-07-07 09:06:59 +08:00
llvm_unreachable("invalid enum");
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
[CUDA] Propagate detected version of CUDA to cc1 ..and use it to control that parts of CUDA compilation that depend on the specific version of CUDA SDK. This patch has a placeholder for a 'new launch API' support which is in a separate patch. The list will be further extended in the upcoming patch to support CUDA-10.1. Differential Revision: https://reviews.llvm.org/D57487 llvm-svn: 352798
2019-02-01 05:32:24 +08:00
CudaVersion CudaStringToVersion(llvm::StringRef S) {
return llvm::StringSwitch<CudaVersion>(S)
.Case("7.0", CudaVersion::CUDA_70)
.Case("7.5", CudaVersion::CUDA_75)
.Case("8.0", CudaVersion::CUDA_80)
.Case("9.0", CudaVersion::CUDA_90)
.Case("9.1", CudaVersion::CUDA_91)
.Case("9.2", CudaVersion::CUDA_92)
.Case("10.0", CudaVersion::CUDA_100);
}
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
const char *CudaArchToString(CudaArch A) {
switch (A) {
Add NVPTX Support to ValidCPUList (enabling march notes) A followup to: https://reviews.llvm.org/D42978 This patch adds NVPTX support for enabling the march notes. Differential Revision: https://reviews.llvm.org/D43045 llvm-svn: 324675
2018-02-09 07:16:00 +08:00
case CudaArch::LAST:
break;
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
case CudaArch::UNKNOWN:
return "unknown";
case CudaArch::SM_20:
return "sm_20";
case CudaArch::SM_21:
return "sm_21";
case CudaArch::SM_30:
return "sm_30";
case CudaArch::SM_32:
return "sm_32";
case CudaArch::SM_35:
return "sm_35";
case CudaArch::SM_37:
return "sm_37";
case CudaArch::SM_50:
return "sm_50";
case CudaArch::SM_52:
return "sm_52";
case CudaArch::SM_53:
return "sm_53";
case CudaArch::SM_60:
return "sm_60";
case CudaArch::SM_61:
return "sm_61";
case CudaArch::SM_62:
return "sm_62";
[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
case CudaArch::SM_70:
return "sm_70";
[CUDA] Added partial support for CUDA-9.1 Clang can use CUDA-9.1 now, though new APIs (are not implemented yet. The major change is that headers in CUDA-9.1 went through substantial changes that started in CUDA-9.0 which required substantial changes in the cuda compatibility headers provided by clang. There are two major issues: * CUDA SDK no longer provides declarations for libdevice functions. * A lot of device-side functions have become nvcc's builtins and CUDA headers no longer contain their implementations. This patch changes the way CUDA headers are handled if we compile with CUDA 9.x. Both 9.0 and 9.1 are affected. * Clang provides its own declarations of libdevice functions. * For CUDA-9.x clang now provides implementation of device-side 'standard library' functions using libdevice. This patch should not affect compilation with CUDA-8. There may be some observable differences for CUDA-9.0, though they are not expected to affect functionality. Tested: CUDA test-suite tests for all supported combinations of: CUDA: 7.0,7.5,8.0,9.0,9.1 GPU: sm_20, sm_35, sm_60, sm_70 Differential Revision: https://reviews.llvm.org/D42513 llvm-svn: 323713
2018-01-30 08:00:12 +08:00
case CudaArch::SM_72:
return "sm_72";
[CUDA] Added basic support for compiling with CUDA-10.0 llvm-svn: 342924
2018-09-25 07:10:44 +08:00
case CudaArch::SM_75:
return "sm_75";
[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
case CudaArch::GFX600: // tahiti
return "gfx600";
case CudaArch::GFX601: // pitcairn, verde, oland,hainan
return "gfx601";
case CudaArch::GFX700: // kaveri
return "gfx700";
case CudaArch::GFX701: // hawaii
return "gfx701";
case CudaArch::GFX702: // 290,290x,R390,R390x
return "gfx702";
case CudaArch::GFX703: // kabini mullins
return "gfx703";
case CudaArch::GFX704: // bonaire
return "gfx704";
case CudaArch::GFX801: // carrizo
return "gfx801";
case CudaArch::GFX802: // tonga,iceland
return "gfx802";
case CudaArch::GFX803: // fiji,polaris10
return "gfx803";
case CudaArch::GFX810: // stoney
return "gfx810";
case CudaArch::GFX900: // vega, instinct
return "gfx900";
case CudaArch::GFX902: // TBA
return "gfx902";
Add gfx904 and gfx906 to GPU Arch Differential Revision: https://reviews.llvm.org/D53472 llvm-svn: 344996
2018-10-23 10:05:31 +08:00
case CudaArch::GFX904: // TBA
return "gfx904";
case CudaArch::GFX906: // TBA
return "gfx906";
Add gfx909 to GPU Arch Subscribers: jholewinski, cfe-commits Differential Revision: https://reviews.llvm.org/D53558 llvm-svn: 345198
2018-10-25 05:19:02 +08:00
case CudaArch::GFX909: // TBA
return "gfx909";
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
[CUDA] Fix "control reaches end of non-void function" warnings in Cuda.cpp. Some compilers are too dumb to realize that the switch statement covers all cases. (Don't use a "default" label, because we explicitly want to get a warning if our switch doesn't cover all the cases.) llvm-svn: 274713
2016-07-07 09:06:59 +08:00
llvm_unreachable("invalid enum");
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
CudaArch StringToCudaArch(llvm::StringRef S) {
return llvm::StringSwitch<CudaArch>(S)
.Case("sm_20", CudaArch::SM_20)
.Case("sm_21", CudaArch::SM_21)
.Case("sm_30", CudaArch::SM_30)
.Case("sm_32", CudaArch::SM_32)
.Case("sm_35", CudaArch::SM_35)
.Case("sm_37", CudaArch::SM_37)
.Case("sm_50", CudaArch::SM_50)
.Case("sm_52", CudaArch::SM_52)
.Case("sm_53", CudaArch::SM_53)
.Case("sm_60", CudaArch::SM_60)
.Case("sm_61", CudaArch::SM_61)
.Case("sm_62", CudaArch::SM_62)
[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
.Case("sm_70", CudaArch::SM_70)
[CUDA] Added partial support for CUDA-9.1 Clang can use CUDA-9.1 now, though new APIs (are not implemented yet. The major change is that headers in CUDA-9.1 went through substantial changes that started in CUDA-9.0 which required substantial changes in the cuda compatibility headers provided by clang. There are two major issues: * CUDA SDK no longer provides declarations for libdevice functions. * A lot of device-side functions have become nvcc's builtins and CUDA headers no longer contain their implementations. This patch changes the way CUDA headers are handled if we compile with CUDA 9.x. Both 9.0 and 9.1 are affected. * Clang provides its own declarations of libdevice functions. * For CUDA-9.x clang now provides implementation of device-side 'standard library' functions using libdevice. This patch should not affect compilation with CUDA-8. There may be some observable differences for CUDA-9.0, though they are not expected to affect functionality. Tested: CUDA test-suite tests for all supported combinations of: CUDA: 7.0,7.5,8.0,9.0,9.1 GPU: sm_20, sm_35, sm_60, sm_70 Differential Revision: https://reviews.llvm.org/D42513 llvm-svn: 323713
2018-01-30 08:00:12 +08:00
.Case("sm_72", CudaArch::SM_72)
[CUDA] Added basic support for compiling with CUDA-10.0 llvm-svn: 342924
2018-09-25 07:10:44 +08:00
.Case("sm_75", CudaArch::SM_75)
[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
.Case("gfx600", CudaArch::GFX600)
.Case("gfx601", CudaArch::GFX601)
.Case("gfx700", CudaArch::GFX700)
.Case("gfx701", CudaArch::GFX701)
.Case("gfx702", CudaArch::GFX702)
.Case("gfx703", CudaArch::GFX703)
.Case("gfx704", CudaArch::GFX704)
.Case("gfx801", CudaArch::GFX801)
.Case("gfx802", CudaArch::GFX802)
.Case("gfx803", CudaArch::GFX803)
.Case("gfx810", CudaArch::GFX810)
.Case("gfx900", CudaArch::GFX900)
.Case("gfx902", CudaArch::GFX902)
Add gfx904 and gfx906 to GPU Arch Differential Revision: https://reviews.llvm.org/D53472 llvm-svn: 344996
2018-10-23 10:05:31 +08:00
.Case("gfx904", CudaArch::GFX904)
.Case("gfx906", CudaArch::GFX906)
Add gfx909 to GPU Arch Subscribers: jholewinski, cfe-commits Differential Revision: https://reviews.llvm.org/D53558 llvm-svn: 345198
2018-10-25 05:19:02 +08:00
.Case("gfx909", CudaArch::GFX909)
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
.Default(CudaArch::UNKNOWN);
}
const char *CudaVirtualArchToString(CudaVirtualArch A) {
switch (A) {
case CudaVirtualArch::UNKNOWN:
return "unknown";
case CudaVirtualArch::COMPUTE_20:
return "compute_20";
case CudaVirtualArch::COMPUTE_30:
return "compute_30";
case CudaVirtualArch::COMPUTE_32:
return "compute_32";
case CudaVirtualArch::COMPUTE_35:
return "compute_35";
case CudaVirtualArch::COMPUTE_37:
return "compute_37";
case CudaVirtualArch::COMPUTE_50:
return "compute_50";
case CudaVirtualArch::COMPUTE_52:
return "compute_52";
case CudaVirtualArch::COMPUTE_53:
return "compute_53";
case CudaVirtualArch::COMPUTE_60:
return "compute_60";
case CudaVirtualArch::COMPUTE_61:
return "compute_61";
case CudaVirtualArch::COMPUTE_62:
return "compute_62";
[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
case CudaVirtualArch::COMPUTE_70:
return "compute_70";
[CUDA] Added partial support for CUDA-9.1 Clang can use CUDA-9.1 now, though new APIs (are not implemented yet. The major change is that headers in CUDA-9.1 went through substantial changes that started in CUDA-9.0 which required substantial changes in the cuda compatibility headers provided by clang. There are two major issues: * CUDA SDK no longer provides declarations for libdevice functions. * A lot of device-side functions have become nvcc's builtins and CUDA headers no longer contain their implementations. This patch changes the way CUDA headers are handled if we compile with CUDA 9.x. Both 9.0 and 9.1 are affected. * Clang provides its own declarations of libdevice functions. * For CUDA-9.x clang now provides implementation of device-side 'standard library' functions using libdevice. This patch should not affect compilation with CUDA-8. There may be some observable differences for CUDA-9.0, though they are not expected to affect functionality. Tested: CUDA test-suite tests for all supported combinations of: CUDA: 7.0,7.5,8.0,9.0,9.1 GPU: sm_20, sm_35, sm_60, sm_70 Differential Revision: https://reviews.llvm.org/D42513 llvm-svn: 323713
2018-01-30 08:00:12 +08:00
case CudaVirtualArch::COMPUTE_72:
return "compute_72";
[CUDA] Added basic support for compiling with CUDA-10.0 llvm-svn: 342924
2018-09-25 07:10:44 +08:00
case CudaVirtualArch::COMPUTE_75:
return "compute_75";
[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
case CudaVirtualArch::COMPUTE_AMDGCN:
return "compute_amdgcn";
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
[CUDA] Fix "control reaches end of non-void function" warnings in Cuda.cpp. Some compilers are too dumb to realize that the switch statement covers all cases. (Don't use a "default" label, because we explicitly want to get a warning if our switch doesn't cover all the cases.) llvm-svn: 274713
2016-07-07 09:06:59 +08:00
llvm_unreachable("invalid enum");
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
CudaVirtualArch StringToCudaVirtualArch(llvm::StringRef S) {
return llvm::StringSwitch<CudaVirtualArch>(S)
.Case("compute_20", CudaVirtualArch::COMPUTE_20)
.Case("compute_30", CudaVirtualArch::COMPUTE_30)
.Case("compute_32", CudaVirtualArch::COMPUTE_32)
.Case("compute_35", CudaVirtualArch::COMPUTE_35)
.Case("compute_37", CudaVirtualArch::COMPUTE_37)
.Case("compute_50", CudaVirtualArch::COMPUTE_50)
.Case("compute_52", CudaVirtualArch::COMPUTE_52)
.Case("compute_53", CudaVirtualArch::COMPUTE_53)
.Case("compute_60", CudaVirtualArch::COMPUTE_60)
.Case("compute_61", CudaVirtualArch::COMPUTE_61)
.Case("compute_62", CudaVirtualArch::COMPUTE_62)
[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
.Case("compute_70", CudaVirtualArch::COMPUTE_70)
[CUDA] Added partial support for CUDA-9.1 Clang can use CUDA-9.1 now, though new APIs (are not implemented yet. The major change is that headers in CUDA-9.1 went through substantial changes that started in CUDA-9.0 which required substantial changes in the cuda compatibility headers provided by clang. There are two major issues: * CUDA SDK no longer provides declarations for libdevice functions. * A lot of device-side functions have become nvcc's builtins and CUDA headers no longer contain their implementations. This patch changes the way CUDA headers are handled if we compile with CUDA 9.x. Both 9.0 and 9.1 are affected. * Clang provides its own declarations of libdevice functions. * For CUDA-9.x clang now provides implementation of device-side 'standard library' functions using libdevice. This patch should not affect compilation with CUDA-8. There may be some observable differences for CUDA-9.0, though they are not expected to affect functionality. Tested: CUDA test-suite tests for all supported combinations of: CUDA: 7.0,7.5,8.0,9.0,9.1 GPU: sm_20, sm_35, sm_60, sm_70 Differential Revision: https://reviews.llvm.org/D42513 llvm-svn: 323713
2018-01-30 08:00:12 +08:00
.Case("compute_72", CudaVirtualArch::COMPUTE_72)
[CUDA] Added basic support for compiling with CUDA-10.0 llvm-svn: 342924
2018-09-25 07:10:44 +08:00
.Case("compute_75", CudaVirtualArch::COMPUTE_75)
[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
.Case("compute_amdgcn", CudaVirtualArch::COMPUTE_AMDGCN)
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
.Default(CudaVirtualArch::UNKNOWN);
}
CudaVirtualArch VirtualArchForCudaArch(CudaArch A) {
switch (A) {
Add NVPTX Support to ValidCPUList (enabling march notes) A followup to: https://reviews.llvm.org/D42978 This patch adds NVPTX support for enabling the march notes. Differential Revision: https://reviews.llvm.org/D43045 llvm-svn: 324675
2018-02-09 07:16:00 +08:00
case CudaArch::LAST:
break;
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
case CudaArch::UNKNOWN:
return CudaVirtualArch::UNKNOWN;
case CudaArch::SM_20:
case CudaArch::SM_21:
return CudaVirtualArch::COMPUTE_20;
case CudaArch::SM_30:
return CudaVirtualArch::COMPUTE_30;
case CudaArch::SM_32:
return CudaVirtualArch::COMPUTE_32;
case CudaArch::SM_35:
return CudaVirtualArch::COMPUTE_35;
case CudaArch::SM_37:
return CudaVirtualArch::COMPUTE_37;
case CudaArch::SM_50:
return CudaVirtualArch::COMPUTE_50;
case CudaArch::SM_52:
return CudaVirtualArch::COMPUTE_52;
case CudaArch::SM_53:
return CudaVirtualArch::COMPUTE_53;
case CudaArch::SM_60:
return CudaVirtualArch::COMPUTE_60;
case CudaArch::SM_61:
return CudaVirtualArch::COMPUTE_61;
case CudaArch::SM_62:
return CudaVirtualArch::COMPUTE_62;
[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
case CudaArch::SM_70:
return CudaVirtualArch::COMPUTE_70;
[CUDA] Added partial support for CUDA-9.1 Clang can use CUDA-9.1 now, though new APIs (are not implemented yet. The major change is that headers in CUDA-9.1 went through substantial changes that started in CUDA-9.0 which required substantial changes in the cuda compatibility headers provided by clang. There are two major issues: * CUDA SDK no longer provides declarations for libdevice functions. * A lot of device-side functions have become nvcc's builtins and CUDA headers no longer contain their implementations. This patch changes the way CUDA headers are handled if we compile with CUDA 9.x. Both 9.0 and 9.1 are affected. * Clang provides its own declarations of libdevice functions. * For CUDA-9.x clang now provides implementation of device-side 'standard library' functions using libdevice. This patch should not affect compilation with CUDA-8. There may be some observable differences for CUDA-9.0, though they are not expected to affect functionality. Tested: CUDA test-suite tests for all supported combinations of: CUDA: 7.0,7.5,8.0,9.0,9.1 GPU: sm_20, sm_35, sm_60, sm_70 Differential Revision: https://reviews.llvm.org/D42513 llvm-svn: 323713
2018-01-30 08:00:12 +08:00
case CudaArch::SM_72:
return CudaVirtualArch::COMPUTE_72;
[CUDA] Added basic support for compiling with CUDA-10.0 llvm-svn: 342924
2018-09-25 07:10:44 +08:00
case CudaArch::SM_75:
return CudaVirtualArch::COMPUTE_75;
[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
case CudaArch::GFX600:
case CudaArch::GFX601:
case CudaArch::GFX700:
case CudaArch::GFX701:
case CudaArch::GFX702:
case CudaArch::GFX703:
case CudaArch::GFX704:
case CudaArch::GFX801:
case CudaArch::GFX802:
case CudaArch::GFX803:
case CudaArch::GFX810:
case CudaArch::GFX900:
case CudaArch::GFX902:
Add gfx904 and gfx906 to GPU Arch Differential Revision: https://reviews.llvm.org/D53472 llvm-svn: 344996
2018-10-23 10:05:31 +08:00
case CudaArch::GFX904:
case CudaArch::GFX906:
Add gfx909 to GPU Arch Subscribers: jholewinski, cfe-commits Differential Revision: https://reviews.llvm.org/D53558 llvm-svn: 345198
2018-10-25 05:19:02 +08:00
case CudaArch::GFX909:
[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
return CudaVirtualArch::COMPUTE_AMDGCN;
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
[CUDA] Fix "control reaches end of non-void function" warnings in Cuda.cpp. Some compilers are too dumb to realize that the switch statement covers all cases. (Don't use a "default" label, because we explicitly want to get a warning if our switch doesn't cover all the cases.) llvm-svn: 274713
2016-07-07 09:06:59 +08:00
llvm_unreachable("invalid enum");
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
CudaVersion MinVersionForCudaArch(CudaArch A) {
switch (A) {
Add NVPTX Support to ValidCPUList (enabling march notes) A followup to: https://reviews.llvm.org/D42978 This patch adds NVPTX support for enabling the march notes. Differential Revision: https://reviews.llvm.org/D43045 llvm-svn: 324675
2018-02-09 07:16:00 +08:00
case CudaArch::LAST:
break;
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
case CudaArch::UNKNOWN:
return CudaVersion::UNKNOWN;
case CudaArch::SM_20:
case CudaArch::SM_21:
case CudaArch::SM_30:
case CudaArch::SM_32:
case CudaArch::SM_35:
case CudaArch::SM_37:
case CudaArch::SM_50:
case CudaArch::SM_52:
case CudaArch::SM_53:
return CudaVersion::CUDA_70;
case CudaArch::SM_60:
case CudaArch::SM_61:
case CudaArch::SM_62:
return CudaVersion::CUDA_80;
[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
case CudaArch::SM_70:
return CudaVersion::CUDA_90;
[CUDA] Added partial support for CUDA-9.1 Clang can use CUDA-9.1 now, though new APIs (are not implemented yet. The major change is that headers in CUDA-9.1 went through substantial changes that started in CUDA-9.0 which required substantial changes in the cuda compatibility headers provided by clang. There are two major issues: * CUDA SDK no longer provides declarations for libdevice functions. * A lot of device-side functions have become nvcc's builtins and CUDA headers no longer contain their implementations. This patch changes the way CUDA headers are handled if we compile with CUDA 9.x. Both 9.0 and 9.1 are affected. * Clang provides its own declarations of libdevice functions. * For CUDA-9.x clang now provides implementation of device-side 'standard library' functions using libdevice. This patch should not affect compilation with CUDA-8. There may be some observable differences for CUDA-9.0, though they are not expected to affect functionality. Tested: CUDA test-suite tests for all supported combinations of: CUDA: 7.0,7.5,8.0,9.0,9.1 GPU: sm_20, sm_35, sm_60, sm_70 Differential Revision: https://reviews.llvm.org/D42513 llvm-svn: 323713
2018-01-30 08:00:12 +08:00
case CudaArch::SM_72:
return CudaVersion::CUDA_91;
[CUDA] Added basic support for compiling with CUDA-10.0 llvm-svn: 342924
2018-09-25 07:10:44 +08:00
case CudaArch::SM_75:
return CudaVersion::CUDA_100;
[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
case CudaArch::GFX600:
case CudaArch::GFX601:
case CudaArch::GFX700:
case CudaArch::GFX701:
case CudaArch::GFX702:
case CudaArch::GFX703:
case CudaArch::GFX704:
case CudaArch::GFX801:
case CudaArch::GFX802:
case CudaArch::GFX803:
case CudaArch::GFX810:
case CudaArch::GFX900:
case CudaArch::GFX902:
Add gfx904 and gfx906 to GPU Arch Differential Revision: https://reviews.llvm.org/D53472 llvm-svn: 344996
2018-10-23 10:05:31 +08:00
case CudaArch::GFX904:
case CudaArch::GFX906:
Add gfx909 to GPU Arch Subscribers: jholewinski, cfe-commits Differential Revision: https://reviews.llvm.org/D53558 llvm-svn: 345198
2018-10-25 05:19:02 +08:00
case CudaArch::GFX909:
[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
return CudaVersion::CUDA_70;
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
[CUDA] Fix "control reaches end of non-void function" warnings in Cuda.cpp. Some compilers are too dumb to realize that the switch statement covers all cases. (Don't use a "default" label, because we explicitly want to get a warning if our switch doesn't cover all the cases.) llvm-svn: 274713
2016-07-07 09:06:59 +08:00
llvm_unreachable("invalid enum");
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
}
[CUDA] Print an error if you try to compile with < sm_30 on CUDA 9. Summary: CUDA 9's minimum sm is sm_30. Ideally we should also make sm_30 the default when compiling with CUDA 9, but that seems harder than it should be. Subscribers: sanjoy Differential Revision: https://reviews.llvm.org/D39109 llvm-svn: 316611
2017-10-26 05:32:06 +08:00
CudaVersion MaxVersionForCudaArch(CudaArch A) {
switch (A) {
case CudaArch::UNKNOWN:
return CudaVersion::UNKNOWN;
case CudaArch::SM_20:
case CudaArch::SM_21:
[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
case CudaArch::GFX600:
case CudaArch::GFX601:
case CudaArch::GFX700:
case CudaArch::GFX701:
case CudaArch::GFX702:
case CudaArch::GFX703:
case CudaArch::GFX704:
case CudaArch::GFX801:
case CudaArch::GFX802:
case CudaArch::GFX803:
case CudaArch::GFX810:
case CudaArch::GFX900:
case CudaArch::GFX902:
[CUDA] Print an error if you try to compile with < sm_30 on CUDA 9. Summary: CUDA 9's minimum sm is sm_30. Ideally we should also make sm_30 the default when compiling with CUDA 9, but that seems harder than it should be. Subscribers: sanjoy Differential Revision: https://reviews.llvm.org/D39109 llvm-svn: 316611
2017-10-26 05:32:06 +08:00
return CudaVersion::CUDA_80;
default:
return CudaVersion::LATEST;
}
}
[CUDA] Propagate detected version of CUDA to cc1 ..and use it to control that parts of CUDA compilation that depend on the specific version of CUDA SDK. This patch has a placeholder for a 'new launch API' support which is in a separate patch. The list will be further extended in the upcoming patch to support CUDA-10.1. Differential Revision: https://reviews.llvm.org/D57487 llvm-svn: 352798
2019-02-01 05:32:24 +08:00
static CudaVersion ToCudaVersion(llvm::VersionTuple Version) {
int IVer =
Version.getMajor() * 10 + Version.getMinor().getValueOr(0);
switch(IVer) {
case 70:
return CudaVersion::CUDA_70;
case 75:
return CudaVersion::CUDA_75;
case 80:
return CudaVersion::CUDA_80;
case 90:
return CudaVersion::CUDA_90;
case 91:
return CudaVersion::CUDA_91;
case 92:
return CudaVersion::CUDA_92;
case 100:
return CudaVersion::CUDA_100;
default:
return CudaVersion::UNKNOWN;
}
}
bool CudaFeatureEnabled(llvm::VersionTuple Version, CudaFeature Feature) {
return CudaFeatureEnabled(ToCudaVersion(Version), Feature);
}
bool CudaFeatureEnabled(CudaVersion Version, CudaFeature Feature) {
switch (Feature) {
case CudaFeature::CUDA_USES_NEW_LAUNCH:
return Version >= CudaVersion::CUDA_92;
}
llvm_unreachable("Unknown CUDA feature.");
}
[CUDA] Add utility functions for dealing with CUDA versions / architectures. Summary: Currently our handling of CUDA architectures is scattered all around clang. This patch centralizes it. A key advantage of this centralization is that you can now write a C++ switch on e.g. CudaArch and get a compile error if you don't handle one of the enum values. Reviewers: tra Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D21867 llvm-svn: 274681
2016-07-07 05:21:39 +08:00
} // namespace clang