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/llvm.amdgcn.fmul.legacy.ll

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

55 lines
2.2 KiB
LLVM
Raw Normal View History

AMDGPU: Add fp legacy instruction intrinsics This could use some additional optimization work to use mad/mac legacy. llvm-svn: 276764
2016-07-27 00:45:45 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}test_mul_legacy_f32:
; GCN: v_mul_legacy_f32_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[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 @test_mul_legacy_f32(float addrspace(1)* %out, float %a, float %b) #0 {
AMDGPU: Add fp legacy instruction intrinsics This could use some additional optimization work to use mad/mac legacy. llvm-svn: 276764
2016-07-27 00:45:45 +08:00
%result = call float @llvm.amdgcn.fmul.legacy(float %a, float %b)
store float %result, float addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}test_mul_legacy_undef0_f32:
; GCN: v_mul_legacy_f32_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 @test_mul_legacy_undef0_f32(float addrspace(1)* %out, float %a) #0 {
AMDGPU: Add fp legacy instruction intrinsics This could use some additional optimization work to use mad/mac legacy. llvm-svn: 276764
2016-07-27 00:45:45 +08:00
%result = call float @llvm.amdgcn.fmul.legacy(float undef, float %a)
store float %result, float addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}test_mul_legacy_undef1_f32:
; GCN: v_mul_legacy_f32_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 @test_mul_legacy_undef1_f32(float addrspace(1)* %out, float %a) #0 {
AMDGPU: Add fp legacy instruction intrinsics This could use some additional optimization work to use mad/mac legacy. llvm-svn: 276764
2016-07-27 00:45:45 +08:00
%result = call float @llvm.amdgcn.fmul.legacy(float %a, float undef)
store float %result, float addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}test_mul_legacy_fabs_f32:
[AMDGPU] Allow SDWA in instructions with immediates and SGPRs An encoding does not allow to use SDWA in an instruction with scalar operands, either literals or SGPRs. That is however possible to copy these operands into a VGPR first. Several copies of the value are produced if multiple SDWA conversions were done. To cleanup MachineLICM (to hoist copies out of loops), MachineCSE (to remove duplicate copies) and SIFoldOperands (to replace SGPR to VGPR copy with immediate copy right to the VGPR) runs are added after the SDWA pass. Differential Revision: https://reviews.llvm.org/D33583 llvm-svn: 304219
2017-05-31 00:49:24 +08:00
; GCN: v_mul_legacy_f32_e64 v{{[0-9]+}}, |s{{[0-9]+}}|, |v{{[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 @test_mul_legacy_fabs_f32(float addrspace(1)* %out, float %a, float %b) #0 {
AMDGPU: Add fp legacy instruction intrinsics This could use some additional optimization work to use mad/mac legacy. llvm-svn: 276764
2016-07-27 00:45:45 +08:00
%a.fabs = call float @llvm.fabs.f32(float %a)
%b.fabs = call float @llvm.fabs.f32(float %b)
%result = call float @llvm.amdgcn.fmul.legacy(float %a.fabs, float %b.fabs)
store float %result, float addrspace(1)* %out, align 4
ret void
}
; TODO: Should match mac_legacy/mad_legacy
; GCN-LABEL: {{^}}test_mad_legacy_f32:
; GCN: v_mul_legacy_f32_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}
; GCN: v_add_f32_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 @test_mad_legacy_f32(float addrspace(1)* %out, float %a, float %b, float %c) #0 {
AMDGPU: Add fp legacy instruction intrinsics This could use some additional optimization work to use mad/mac legacy. llvm-svn: 276764
2016-07-27 00:45:45 +08:00
%mul = call float @llvm.amdgcn.fmul.legacy(float %a, float %b)
%add = fadd float %mul, %c
store float %add, float addrspace(1)* %out, align 4
ret void
}
declare float @llvm.fabs.f32(float) #1
declare float @llvm.amdgcn.fmul.legacy(float, float) #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }