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/fptrunc.ll

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

68 lines
2.5 KiB
LLVM
Raw Normal View History

Enable FeatureFlatForGlobal on Volcanic Islands This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
2017-01-25 06:02:15 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -enable-unsafe-fp-math -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN-UNSAFE %s
R600/SI: Implement fp32<->fp64 conversions llvm-svn: 187988
2013-08-09 00:06:15 +08:00
AMDGPU: Fix some incorrect FUNC-LABEL checks
2020-02-26 17:41:41 +08:00
; GCN-LABEL: {{^}}fptrunc_f64_to_f32:
AMDGPU: Implement expansion of f16 = FP_TO_FP16 f64 I wanted to implement this as a target independent expansion, however when targets say they want to expand FP_TO_FP16 what they actually want is the unsafe math expansion when possible and expansion to a libcall in all other cases. The only way to make this work as a target independent would be to add logic to target's TargetLowering construction to mark theses nodes as Expand when LegalizeDAG can use the unsafe expansion and mark them as LibCall when it cannot. I think this would be possible, but I think it would be too fragile and complex as it would require targets to keep their expansion logic up to date with the code in LegalizeDAG. Reviewers: bogner, ab, t.p.northover, arsenm Subscribers: wdng, llvm-commits, nhaehnle Differential Revision: https://reviews.llvm.org/D25999 llvm-svn: 285704
2016-11-02 00:31:48 +08:00
; GCN: v_cvt_f32_f64_e32 {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}
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 @fptrunc_f64_to_f32(float addrspace(1)* %out, double %in) {
R600/SI: Implement fp32<->fp64 conversions llvm-svn: 187988
2013-08-09 00:06:15 +08:00
%result = fptrunc double %in to float
store float %result, float addrspace(1)* %out
ret void
}
R600/SI: Improve fpext / fptrunc test coverage llvm-svn: 226197
2015-01-16 03:39:42 +08:00
AMDGPU: Fix some incorrect FUNC-LABEL checks
2020-02-26 17:41:41 +08:00
; GCN-LABEL: {{^}}fptrunc_f64_to_f16:
AMDGPU: Implement expansion of f16 = FP_TO_FP16 f64 I wanted to implement this as a target independent expansion, however when targets say they want to expand FP_TO_FP16 what they actually want is the unsafe math expansion when possible and expansion to a libcall in all other cases. The only way to make this work as a target independent would be to add logic to target's TargetLowering construction to mark theses nodes as Expand when LegalizeDAG can use the unsafe expansion and mark them as LibCall when it cannot. I think this would be possible, but I think it would be too fragile and complex as it would require targets to keep their expansion logic up to date with the code in LegalizeDAG. Reviewers: bogner, ab, t.p.northover, arsenm Subscribers: wdng, llvm-commits, nhaehnle Differential Revision: https://reviews.llvm.org/D25999 llvm-svn: 285704
2016-11-02 00:31:48 +08:00
; GCN-NOT: v_cvt
[AMDGPU] Add missing test for rL287203 llvm-svn: 287204
2016-11-17 12:33:20 +08:00
; GCN-UNSAFE: v_cvt_f32_f64_e32 [[F32:v[0-9]+]]
; GCN-UNSAFE: v_cvt_f16_f32_e32 v{{[0-9]+}}, [[F32]]
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 @fptrunc_f64_to_f16(i16 addrspace(1)* %out, double %in) {
AMDGPU: Implement expansion of f16 = FP_TO_FP16 f64 I wanted to implement this as a target independent expansion, however when targets say they want to expand FP_TO_FP16 what they actually want is the unsafe math expansion when possible and expansion to a libcall in all other cases. The only way to make this work as a target independent would be to add logic to target's TargetLowering construction to mark theses nodes as Expand when LegalizeDAG can use the unsafe expansion and mark them as LibCall when it cannot. I think this would be possible, but I think it would be too fragile and complex as it would require targets to keep their expansion logic up to date with the code in LegalizeDAG. Reviewers: bogner, ab, t.p.northover, arsenm Subscribers: wdng, llvm-commits, nhaehnle Differential Revision: https://reviews.llvm.org/D25999 llvm-svn: 285704
2016-11-02 00:31:48 +08:00
%result = fptrunc double %in to half
%result_i16 = bitcast half %result to i16
store i16 %result_i16, i16 addrspace(1)* %out
ret void
}
AMDGPU: Fix some incorrect FUNC-LABEL checks
2020-02-26 17:41:41 +08:00
; GCN-LABEL: {{^}}fptrunc_v2f64_to_v2f32:
AMDGPU: Implement expansion of f16 = FP_TO_FP16 f64 I wanted to implement this as a target independent expansion, however when targets say they want to expand FP_TO_FP16 what they actually want is the unsafe math expansion when possible and expansion to a libcall in all other cases. The only way to make this work as a target independent would be to add logic to target's TargetLowering construction to mark theses nodes as Expand when LegalizeDAG can use the unsafe expansion and mark them as LibCall when it cannot. I think this would be possible, but I think it would be too fragile and complex as it would require targets to keep their expansion logic up to date with the code in LegalizeDAG. Reviewers: bogner, ab, t.p.northover, arsenm Subscribers: wdng, llvm-commits, nhaehnle Differential Revision: https://reviews.llvm.org/D25999 llvm-svn: 285704
2016-11-02 00:31:48 +08:00
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
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 @fptrunc_v2f64_to_v2f32(<2 x float> addrspace(1)* %out, <2 x double> %in) {
R600/SI: Improve fpext / fptrunc test coverage llvm-svn: 226197
2015-01-16 03:39:42 +08:00
%result = fptrunc <2 x double> %in to <2 x float>
store <2 x float> %result, <2 x float> addrspace(1)* %out
ret void
}
AMDGPU: Fix some incorrect FUNC-LABEL checks
2020-02-26 17:41:41 +08:00
; GCN-LABEL: {{^}}fptrunc_v3f64_to_v3f32:
[SelectionDAG] Add support for FP_ROUND in WidenVectorOperand. Summary: This is used on AMDGPU for rounding from v3f64 (which is illegal) to v3f32 (which is legal). Subscribers: jvesely, nhaehnle, tpr, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D69339
2019-10-23 21:22:16 +08:00
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
define amdgpu_kernel void @fptrunc_v3f64_to_v3f32(<3 x float> addrspace(1)* %out, <3 x double> %in) {
%result = fptrunc <3 x double> %in to <3 x float>
store <3 x float> %result, <3 x float> addrspace(1)* %out
ret void
}
AMDGPU: Fix some incorrect FUNC-LABEL checks
2020-02-26 17:41:41 +08:00
; GCN-LABEL: {{^}}fptrunc_v4f64_to_v4f32:
AMDGPU: Implement expansion of f16 = FP_TO_FP16 f64 I wanted to implement this as a target independent expansion, however when targets say they want to expand FP_TO_FP16 what they actually want is the unsafe math expansion when possible and expansion to a libcall in all other cases. The only way to make this work as a target independent would be to add logic to target's TargetLowering construction to mark theses nodes as Expand when LegalizeDAG can use the unsafe expansion and mark them as LibCall when it cannot. I think this would be possible, but I think it would be too fragile and complex as it would require targets to keep their expansion logic up to date with the code in LegalizeDAG. Reviewers: bogner, ab, t.p.northover, arsenm Subscribers: wdng, llvm-commits, nhaehnle Differential Revision: https://reviews.llvm.org/D25999 llvm-svn: 285704
2016-11-02 00:31:48 +08:00
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
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 @fptrunc_v4f64_to_v4f32(<4 x float> addrspace(1)* %out, <4 x double> %in) {
R600/SI: Improve fpext / fptrunc test coverage llvm-svn: 226197
2015-01-16 03:39:42 +08:00
%result = fptrunc <4 x double> %in to <4 x float>
store <4 x float> %result, <4 x float> addrspace(1)* %out
ret void
}
AMDGPU: Fix some incorrect FUNC-LABEL checks
2020-02-26 17:41:41 +08:00
; GCN-LABEL: {{^}}fptrunc_v8f64_to_v8f32:
AMDGPU: Implement expansion of f16 = FP_TO_FP16 f64 I wanted to implement this as a target independent expansion, however when targets say they want to expand FP_TO_FP16 what they actually want is the unsafe math expansion when possible and expansion to a libcall in all other cases. The only way to make this work as a target independent would be to add logic to target's TargetLowering construction to mark theses nodes as Expand when LegalizeDAG can use the unsafe expansion and mark them as LibCall when it cannot. I think this would be possible, but I think it would be too fragile and complex as it would require targets to keep their expansion logic up to date with the code in LegalizeDAG. Reviewers: bogner, ab, t.p.northover, arsenm Subscribers: wdng, llvm-commits, nhaehnle Differential Revision: https://reviews.llvm.org/D25999 llvm-svn: 285704
2016-11-02 00:31:48 +08:00
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
; GCN: v_cvt_f32_f64_e32
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 @fptrunc_v8f64_to_v8f32(<8 x float> addrspace(1)* %out, <8 x double> %in) {
R600/SI: Improve fpext / fptrunc test coverage llvm-svn: 226197
2015-01-16 03:39:42 +08:00
%result = fptrunc <8 x double> %in to <8 x float>
store <8 x float> %result, <8 x float> addrspace(1)* %out
ret void
}