maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/hsa-fp-mode.ll

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

102 lines
3.7 KiB
LLVM
Raw Normal View History

AMDGPU: Update AMDHSA code object version handling Differential Revision: https://reviews.llvm.org/D89076
2020-10-15 01:03:37 +08:00
; RUN: llc -mtriple=amdgcn--amdhsa --amdhsa-code-object-version=2 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
AMDGPU: Set DX10Clamp bit llvm-svn: 259088
2016-01-29 04:53:35 +08:00
AMDGPU: Simplify tests with per function subtargets llvm-svn: 274971
2016-07-09 15:55:03 +08:00
; GCN-LABEL: {{^}}test_default_ci:
AMDGPU: Assume f32 denormals are enabled by default This will likely introduce catastrophic performance regressions on older subtargets, but should be correct. A follow up change will remove the old fp32-denormals subtarget features, and switch to using the new denormal-fp-math/denormal-fp-math-f32 attributes. Frontends should be making sure to add the denormal-fp-math-f32 attribute when appropriate to avoid performance regressions.
2019-11-01 14:32:31 +08:00
; GCN: float_mode = 240
[AMDGPU] Assembler: rename amd_kernel_code_t asm names according to spec Summary: Also removed duplicate code from AMDGPUTargetAsmStreamer. This change only change how amd_kernel_code_t is parsed and printed. No variable names are changed. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, wdng, nhaehnle Differential Revision: https://reviews.llvm.org/D24296 llvm-svn: 281028
2016-09-09 18:08:02 +08:00
; GCN: enable_dx10_clamp = 1
AMDGPU : Add a function to enable and disable IEEEBit for SC and shader respectively. Differential Revision: http://reviews.llvm.org/D25789 llvm-svn: 284655
2016-10-20 06:34:49 +08:00
; GCN: enable_ieee_mode = 1
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_default_ci(float addrspace(1)* %out0, double addrspace(1)* %out1) #0 {
AMDGPU: Set DX10Clamp bit llvm-svn: 259088
2016-01-29 04:53:35 +08:00
store float 0.0, float addrspace(1)* %out0
store double 0.0, double addrspace(1)* %out1
ret void
}
AMDGPU: Simplify tests with per function subtargets llvm-svn: 274971
2016-07-09 15:55:03 +08:00
; GCN-LABEL: {{^}}test_default_vi:
AMDGPU: Assume f32 denormals are enabled by default This will likely introduce catastrophic performance regressions on older subtargets, but should be correct. A follow up change will remove the old fp32-denormals subtarget features, and switch to using the new denormal-fp-math/denormal-fp-math-f32 attributes. Frontends should be making sure to add the denormal-fp-math-f32 attribute when appropriate to avoid performance regressions.
2019-11-01 14:32:31 +08:00
; GCN: float_mode = 240
[AMDGPU] Assembler: rename amd_kernel_code_t asm names according to spec Summary: Also removed duplicate code from AMDGPUTargetAsmStreamer. This change only change how amd_kernel_code_t is parsed and printed. No variable names are changed. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, wdng, nhaehnle Differential Revision: https://reviews.llvm.org/D24296 llvm-svn: 281028
2016-09-09 18:08:02 +08:00
; GCN: enable_dx10_clamp = 1
AMDGPU : Add a function to enable and disable IEEEBit for SC and shader respectively. Differential Revision: http://reviews.llvm.org/D25789 llvm-svn: 284655
2016-10-20 06:34:49 +08:00
; GCN: enable_ieee_mode = 1
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_default_vi(float addrspace(1)* %out0, double addrspace(1)* %out1) #1 {
AMDGPU: Simplify tests with per function subtargets llvm-svn: 274971
2016-07-09 15:55:03 +08:00
store float 0.0, float addrspace(1)* %out0
store double 0.0, double addrspace(1)* %out1
ret void
}
; GCN-LABEL: {{^}}test_f64_denormals:
[AMDGPU] Assembler: rename amd_kernel_code_t asm names according to spec Summary: Also removed duplicate code from AMDGPUTargetAsmStreamer. This change only change how amd_kernel_code_t is parsed and printed. No variable names are changed. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, wdng, nhaehnle Differential Revision: https://reviews.llvm.org/D24296 llvm-svn: 281028
2016-09-09 18:08:02 +08:00
; GCN: float_mode = 192
; GCN: enable_dx10_clamp = 1
AMDGPU : Add a function to enable and disable IEEEBit for SC and shader respectively. Differential Revision: http://reviews.llvm.org/D25789 llvm-svn: 284655
2016-10-20 06:34:49 +08:00
; GCN: enable_ieee_mode = 1
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_f64_denormals(float addrspace(1)* %out0, double addrspace(1)* %out1) #2 {
AMDGPU: Simplify tests with per function subtargets llvm-svn: 274971
2016-07-09 15:55:03 +08:00
store float 0.0, float addrspace(1)* %out0
store double 0.0, double addrspace(1)* %out1
ret void
}
; GCN-LABEL: {{^}}test_f32_denormals:
[AMDGPU] Assembler: rename amd_kernel_code_t asm names according to spec Summary: Also removed duplicate code from AMDGPUTargetAsmStreamer. This change only change how amd_kernel_code_t is parsed and printed. No variable names are changed. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, wdng, nhaehnle Differential Revision: https://reviews.llvm.org/D24296 llvm-svn: 281028
2016-09-09 18:08:02 +08:00
; GCN: float_mode = 48
; GCN: enable_dx10_clamp = 1
AMDGPU : Add a function to enable and disable IEEEBit for SC and shader respectively. Differential Revision: http://reviews.llvm.org/D25789 llvm-svn: 284655
2016-10-20 06:34:49 +08:00
; GCN: enable_ieee_mode = 1
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_f32_denormals(float addrspace(1)* %out0, double addrspace(1)* %out1) #3 {
AMDGPU: Simplify tests with per function subtargets llvm-svn: 274971
2016-07-09 15:55:03 +08:00
store float 0.0, float addrspace(1)* %out0
store double 0.0, double addrspace(1)* %out1
ret void
}
; GCN-LABEL: {{^}}test_f32_f64_denormals:
[AMDGPU] Assembler: rename amd_kernel_code_t asm names according to spec Summary: Also removed duplicate code from AMDGPUTargetAsmStreamer. This change only change how amd_kernel_code_t is parsed and printed. No variable names are changed. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, wdng, nhaehnle Differential Revision: https://reviews.llvm.org/D24296 llvm-svn: 281028
2016-09-09 18:08:02 +08:00
; GCN: float_mode = 240
; GCN: enable_dx10_clamp = 1
AMDGPU : Add a function to enable and disable IEEEBit for SC and shader respectively. Differential Revision: http://reviews.llvm.org/D25789 llvm-svn: 284655
2016-10-20 06:34:49 +08:00
; GCN: enable_ieee_mode = 1
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_f32_f64_denormals(float addrspace(1)* %out0, double addrspace(1)* %out1) #4 {
AMDGPU: Simplify tests with per function subtargets llvm-svn: 274971
2016-07-09 15:55:03 +08:00
store float 0.0, float addrspace(1)* %out0
store double 0.0, double addrspace(1)* %out1
ret void
}
; GCN-LABEL: {{^}}test_no_denormals:
[AMDGPU] Assembler: rename amd_kernel_code_t asm names according to spec Summary: Also removed duplicate code from AMDGPUTargetAsmStreamer. This change only change how amd_kernel_code_t is parsed and printed. No variable names are changed. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, wdng, nhaehnle Differential Revision: https://reviews.llvm.org/D24296 llvm-svn: 281028
2016-09-09 18:08:02 +08:00
; GCN: float_mode = 0
; GCN: enable_dx10_clamp = 1
AMDGPU : Add a function to enable and disable IEEEBit for SC and shader respectively. Differential Revision: http://reviews.llvm.org/D25789 llvm-svn: 284655
2016-10-20 06:34:49 +08:00
; GCN: enable_ieee_mode = 1
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_no_denormals(float addrspace(1)* %out0, double addrspace(1)* %out1) #5 {
AMDGPU: Simplify tests with per function subtargets llvm-svn: 274971
2016-07-09 15:55:03 +08:00
store float 0.0, float addrspace(1)* %out0
store double 0.0, double addrspace(1)* %out1
ret void
}
AMDGPU: Redefine clamp node as clamp 0.0-1.0 Change implementation to use max instead of add. min/max/med3 do not flush denormals regardless of the mode, so it is OK to use it whether or not they are enabled. Also allow using clamp with f16, and use knowledge of dx10_clamp. llvm-svn: 295788
2017-02-22 07:35:48 +08:00
; GCN-LABEL: {{^}}test_no_dx10_clamp_vi:
AMDGPU: Assume f32 denormals are enabled by default This will likely introduce catastrophic performance regressions on older subtargets, but should be correct. A follow up change will remove the old fp32-denormals subtarget features, and switch to using the new denormal-fp-math/denormal-fp-math-f32 attributes. Frontends should be making sure to add the denormal-fp-math-f32 attribute when appropriate to avoid performance regressions.
2019-11-01 14:32:31 +08:00
; GCN: float_mode = 240
AMDGPU: Redefine clamp node as clamp 0.0-1.0 Change implementation to use max instead of add. min/max/med3 do not flush denormals regardless of the mode, so it is OK to use it whether or not they are enabled. Also allow using clamp with f16, and use knowledge of dx10_clamp. llvm-svn: 295788
2017-02-22 07:35:48 +08:00
; GCN: enable_dx10_clamp = 0
; GCN: enable_ieee_mode = 1
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_no_dx10_clamp_vi(float addrspace(1)* %out0, double addrspace(1)* %out1) #6 {
AMDGPU: Redefine clamp node as clamp 0.0-1.0 Change implementation to use max instead of add. min/max/med3 do not flush denormals regardless of the mode, so it is OK to use it whether or not they are enabled. Also allow using clamp with f16, and use knowledge of dx10_clamp. llvm-svn: 295788
2017-02-22 07:35:48 +08:00
store float 0.0, float addrspace(1)* %out0
store double 0.0, double addrspace(1)* %out1
ret void
}
AMDGPU: Remove dx10-clamp from subtarget features Since this can be set with s_setreg*, it should not be a subtarget property. Set a default based on the calling convention, and Introduce a new amdgpu-dx10-clamp attribute to override this if desired. Also introduce a new amdgpu-ieee attribute to match. The values need to match to allow inlining. I think it is OK for the caller's dx10-clamp attribute to override the callee, but there doesn't appear to be the infrastructure to do this currently without definining the attribute in the generic Attributes.td. Eventually the calling convention lowering will need to insert a mode switch somewhere for these. llvm-svn: 357302
2019-03-30 03:14:54 +08:00
; GCN-LABEL: {{^}}test_no_ieee_mode_vi:
AMDGPU: Assume f32 denormals are enabled by default This will likely introduce catastrophic performance regressions on older subtargets, but should be correct. A follow up change will remove the old fp32-denormals subtarget features, and switch to using the new denormal-fp-math/denormal-fp-math-f32 attributes. Frontends should be making sure to add the denormal-fp-math-f32 attribute when appropriate to avoid performance regressions.
2019-11-01 14:32:31 +08:00
; GCN: float_mode = 240
AMDGPU: Remove dx10-clamp from subtarget features Since this can be set with s_setreg*, it should not be a subtarget property. Set a default based on the calling convention, and Introduce a new amdgpu-dx10-clamp attribute to override this if desired. Also introduce a new amdgpu-ieee attribute to match. The values need to match to allow inlining. I think it is OK for the caller's dx10-clamp attribute to override the callee, but there doesn't appear to be the infrastructure to do this currently without definining the attribute in the generic Attributes.td. Eventually the calling convention lowering will need to insert a mode switch somewhere for these. llvm-svn: 357302
2019-03-30 03:14:54 +08:00
; GCN: enable_dx10_clamp = 1
; GCN: enable_ieee_mode = 0
define amdgpu_kernel void @test_no_ieee_mode_vi(float addrspace(1)* %out0, double addrspace(1)* %out1) #7 {
store float 0.0, float addrspace(1)* %out0
store double 0.0, double addrspace(1)* %out1
ret void
}
; GCN-LABEL: {{^}}test_no_ieee_mode_no_dx10_clamp_vi:
AMDGPU: Assume f32 denormals are enabled by default This will likely introduce catastrophic performance regressions on older subtargets, but should be correct. A follow up change will remove the old fp32-denormals subtarget features, and switch to using the new denormal-fp-math/denormal-fp-math-f32 attributes. Frontends should be making sure to add the denormal-fp-math-f32 attribute when appropriate to avoid performance regressions.
2019-11-01 14:32:31 +08:00
; GCN: float_mode = 240
AMDGPU: Remove dx10-clamp from subtarget features Since this can be set with s_setreg*, it should not be a subtarget property. Set a default based on the calling convention, and Introduce a new amdgpu-dx10-clamp attribute to override this if desired. Also introduce a new amdgpu-ieee attribute to match. The values need to match to allow inlining. I think it is OK for the caller's dx10-clamp attribute to override the callee, but there doesn't appear to be the infrastructure to do this currently without definining the attribute in the generic Attributes.td. Eventually the calling convention lowering will need to insert a mode switch somewhere for these. llvm-svn: 357302
2019-03-30 03:14:54 +08:00
; GCN: enable_dx10_clamp = 0
; GCN: enable_ieee_mode = 0
define amdgpu_kernel void @test_no_ieee_mode_no_dx10_clamp_vi(float addrspace(1)* %out0, double addrspace(1)* %out1) #8 {
store float 0.0, float addrspace(1)* %out0
store double 0.0, double addrspace(1)* %out1
ret void
}
AMDGPU: Update AMDHSA code object version handling Differential Revision: https://reviews.llvm.org/D89076
2020-10-15 01:03:37 +08:00
attributes #0 = { nounwind "target-cpu"="kaveri" }
attributes #1 = { nounwind "target-cpu"="fiji" }
attributes #2 = { nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" }
attributes #3 = { nounwind "denormal-fp-math-f32"="ieee,ieee" "denormal-fp-math"="preserve-sign,preserve-sign" }
attributes #4 = { nounwind "denormal-fp-math"="ieee,ieee" }
attributes #5 = { nounwind "denormal-fp-math"="preserve-sign,preserve-sign" }
attributes #6 = { nounwind "amdgpu-dx10-clamp"="false" "target-cpu"="fiji" }
attributes #7 = { nounwind "amdgpu-ieee"="false" "target-cpu"="fiji" }
attributes #8 = { nounwind "amdgpu-dx10-clamp"="false" "amdgpu-ieee"="false" "target-cpu"="fiji" }