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-flush-denormals-to-zer...

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

28 lines
2.5 KiB
Plaintext
Raw Normal View History

Consolidate internal denormal flushing controls Currently there are 4 different mechanisms for controlling denormal flushing behavior, and about as many equivalent frontend controls. - AMDGPU uses the fp32-denormals and fp64-f16-denormals subtarget features - NVPTX uses the nvptx-f32ftz attribute - ARM directly uses the denormal-fp-math attribute - Other targets indirectly use denormal-fp-math in one DAGCombine - cl-denorms-are-zero has a corresponding denorms-are-zero attribute AMDGPU wants a distinct control for f32 flushing from f16/f64, and as far as I can tell the same is true for NVPTX (based on the attribute name). Work on consolidating these into the denormal-fp-math attribute, and a new type specific denormal-fp-math-f32 variant. Only ARM seems to support the two different flush modes, so this is overkill for the other use cases. Ideally we would error on the unsupported positive-zero mode on other targets from somewhere. Move the logic for selecting the flush mode into the compiler driver, instead of handling it in cc1. denormal-fp-math/denormal-fp-math-f32 are now both cc1 flags, but denormal-fp-math-f32 is not yet exposed as a user flag. -cl-denorms-are-zero, -fcuda-flush-denormals-to-zero and -fno-cuda-flush-denormals-to-zero will be mapped to -fp-denormal-math-f32=ieee or preserve-sign rather than the old attributes. Stop emitting the denorms-are-zero attribute for the OpenCL flag. It has no in-tree users. The meaning would also be target dependent, such as the AMDGPU choice to treat this as only meaning allow flushing of f32 and not f16 or f64. The naming is also potentially confusing, since DAZ in other contexts refers to instructions implicitly treating input denormals as zero, not necessarily flushing output denormals to zero. This also does not attempt to change the behavior for the current attribute. The LangRef now states that the default is ieee behavior, but this is inaccurate for the current implementation. The clang handling is slightly hacky to avoid touching the existing denormal-fp-math uses. Fixing this will be left for a future patch. AMDGPU is still using the subtarget feature to control the denormal mode, but the new attribute are now emitted. A future change will switch this and remove the subtarget features.
2019-11-02 08:57:29 +08:00
// Checks that cuda compilation does the right thing when passed
// -fcuda-flush-denormals-to-zero. This should be translated to
// -fdenormal-fp-math-f32=preserve-sign
CUDA: Fix broken test run lines There was a misisng space between the -march and --cuda-gpu-arch arguments, so --cuda-gpu-arch wasn't actually being parsed. I'm not sure what the intent of the sm_10 run lines were, but they error as an unsupported architecture. Switch these to something else.
2020-03-26 23:51:25 +08:00
// RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=sm_20 -fcuda-flush-denormals-to-zero -nocudainc -nocudalib %s 2>&1 | FileCheck -check-prefix=FTZ %s
// RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=sm_20 -fno-cuda-flush-denormals-to-zero -nocudainc -nocudalib %s 2>&1 | FileCheck -check-prefix=NOFTZ %s
// RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=sm_70 -fcuda-flush-denormals-to-zero -nocudainc -nocudalib %s 2>&1 | FileCheck -check-prefix=FTZ %s
// RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=sm_70 -fno-cuda-flush-denormals-to-zero -nocudainc -nocudalib %s 2>&1 | FileCheck -check-prefix=NOFTZ %s
Consolidate internal denormal flushing controls Currently there are 4 different mechanisms for controlling denormal flushing behavior, and about as many equivalent frontend controls. - AMDGPU uses the fp32-denormals and fp64-f16-denormals subtarget features - NVPTX uses the nvptx-f32ftz attribute - ARM directly uses the denormal-fp-math attribute - Other targets indirectly use denormal-fp-math in one DAGCombine - cl-denorms-are-zero has a corresponding denorms-are-zero attribute AMDGPU wants a distinct control for f32 flushing from f16/f64, and as far as I can tell the same is true for NVPTX (based on the attribute name). Work on consolidating these into the denormal-fp-math attribute, and a new type specific denormal-fp-math-f32 variant. Only ARM seems to support the two different flush modes, so this is overkill for the other use cases. Ideally we would error on the unsupported positive-zero mode on other targets from somewhere. Move the logic for selecting the flush mode into the compiler driver, instead of handling it in cc1. denormal-fp-math/denormal-fp-math-f32 are now both cc1 flags, but denormal-fp-math-f32 is not yet exposed as a user flag. -cl-denorms-are-zero, -fcuda-flush-denormals-to-zero and -fno-cuda-flush-denormals-to-zero will be mapped to -fp-denormal-math-f32=ieee or preserve-sign rather than the old attributes. Stop emitting the denorms-are-zero attribute for the OpenCL flag. It has no in-tree users. The meaning would also be target dependent, such as the AMDGPU choice to treat this as only meaning allow flushing of f32 and not f16 or f64. The naming is also potentially confusing, since DAZ in other contexts refers to instructions implicitly treating input denormals as zero, not necessarily flushing output denormals to zero. This also does not attempt to change the behavior for the current attribute. The LangRef now states that the default is ieee behavior, but this is inaccurate for the current implementation. The clang handling is slightly hacky to avoid touching the existing denormal-fp-math uses. Fixing this will be left for a future patch. AMDGPU is still using the subtarget feature to control the denormal mode, but the new attribute are now emitted. A future change will switch this and remove the subtarget features.
2019-11-02 08:57:29 +08:00
HIP: Ensure new denormal mode attributes are set Apparently HIPToolChain does not subclass from AMDGPUToolChain, so this was not applying the new denormal attributes. I'm not sure why this doesn't subclass. Just copy the implementation for now.
2020-03-26 23:17:53 +08:00
// Test explicit argument.
// RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=gfx803 -fcuda-flush-denormals-to-zero -nocudainc -nogpulib %s 2>&1 | FileCheck -check-prefix=FTZ %s
// RUN: %clang -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=gfx803 -fno-cuda-flush-denormals-to-zero -nocudainc -nogpulib %s 2>&1 | FileCheck -check-prefix=NOFTZ %s
// RUN: %clang -x hip -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=gfx900 -fcuda-flush-denormals-to-zero -nocudainc -nogpulib %s 2>&1 | FileCheck -check-prefix=FTZ %s
// RUN: %clang -x hip -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=gfx900 -fno-cuda-flush-denormals-to-zero -nocudainc -nogpulib %s 2>&1 | FileCheck -check-prefix=NOFTZ %s
// Test the default changing with no argument based on the subtarget.
// RUN: %clang -x hip -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=gfx803 -nocudainc -nogpulib %s 2>&1 | FileCheck -check-prefix=FTZ %s
// RUN: %clang -x hip -no-canonical-prefixes -### -target x86_64-linux-gnu -c -march=haswell --cuda-gpu-arch=gfx900 -nocudainc -nogpulib %s 2>&1 | FileCheck -check-prefix=NOFTZ %s
Consolidate internal denormal flushing controls Currently there are 4 different mechanisms for controlling denormal flushing behavior, and about as many equivalent frontend controls. - AMDGPU uses the fp32-denormals and fp64-f16-denormals subtarget features - NVPTX uses the nvptx-f32ftz attribute - ARM directly uses the denormal-fp-math attribute - Other targets indirectly use denormal-fp-math in one DAGCombine - cl-denorms-are-zero has a corresponding denorms-are-zero attribute AMDGPU wants a distinct control for f32 flushing from f16/f64, and as far as I can tell the same is true for NVPTX (based on the attribute name). Work on consolidating these into the denormal-fp-math attribute, and a new type specific denormal-fp-math-f32 variant. Only ARM seems to support the two different flush modes, so this is overkill for the other use cases. Ideally we would error on the unsupported positive-zero mode on other targets from somewhere. Move the logic for selecting the flush mode into the compiler driver, instead of handling it in cc1. denormal-fp-math/denormal-fp-math-f32 are now both cc1 flags, but denormal-fp-math-f32 is not yet exposed as a user flag. -cl-denorms-are-zero, -fcuda-flush-denormals-to-zero and -fno-cuda-flush-denormals-to-zero will be mapped to -fp-denormal-math-f32=ieee or preserve-sign rather than the old attributes. Stop emitting the denorms-are-zero attribute for the OpenCL flag. It has no in-tree users. The meaning would also be target dependent, such as the AMDGPU choice to treat this as only meaning allow flushing of f32 and not f16 or f64. The naming is also potentially confusing, since DAZ in other contexts refers to instructions implicitly treating input denormals as zero, not necessarily flushing output denormals to zero. This also does not attempt to change the behavior for the current attribute. The LangRef now states that the default is ieee behavior, but this is inaccurate for the current implementation. The clang handling is slightly hacky to avoid touching the existing denormal-fp-math uses. Fixing this will be left for a future patch. AMDGPU is still using the subtarget feature to control the denormal mode, but the new attribute are now emitted. A future change will switch this and remove the subtarget features.
2019-11-02 08:57:29 +08:00
// CPUFTZ-NOT: -fdenormal-fp-math
Reapply "clang: Treat ieee mode as the default for denormal-fp-math" This reverts commit 737394c490444e968a6f640b99a6614567ca7f28. The fp-model test was failing on platforms that enable denormal flushing based on -ffast-math. This needs to reset to IEEE, not the default in these cases. Change-Id: Ibbad32f66d0d0b89b9c1173a3a96fb1a570ddd89
2020-03-05 22:13:09 +08:00
// FTZ-NOT: -fdenormal-fp-math-f32=
Separately track input and output denormal mode AMDGPU and x86 at least both have separate controls for whether denormal results are flushed on output, and for whether denormals are implicitly treated as 0 as an input. The current DAGCombiner use only really cares about the input treatment of denormals.
2019-11-07 09:10:52 +08:00
// FTZ: "-fdenormal-fp-math-f32=preserve-sign,preserve-sign"
Reapply "clang: Treat ieee mode as the default for denormal-fp-math" This reverts commit 737394c490444e968a6f640b99a6614567ca7f28. The fp-model test was failing on platforms that enable denormal flushing based on -ffast-math. This needs to reset to IEEE, not the default in these cases. Change-Id: Ibbad32f66d0d0b89b9c1173a3a96fb1a570ddd89
2020-03-05 22:13:09 +08:00
// The default of ieee is omitted
// NOFTZ-NOT: "-fdenormal-fp-math"
// NOFTZ-NOT: "-fdenormal-fp-math-f32"