maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

MSG 

llvm-svn: 329114
This commit is contained in:
Farhana Aleen 2018-04-03 21:20:39 +00:00
parent ce8766b2fd
commit 3ab409dc86
3 changed files with 25 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
View File

@ -6446,7 +6446,7 @@ SDValue SITargetLowering::performMinMaxCombine(SDNode *N,
if (Opc != AMDGPUISD::FMIN_LEGACY && Opc != AMDGPUISD::FMAX_LEGACY && if (Opc != AMDGPUISD::FMIN_LEGACY && Opc != AMDGPUISD::FMAX_LEGACY &&
VT != MVT::f64 && !VT.isVector() && VT != MVT::f64 &&
((VT != MVT::f16 && VT != MVT::i16) || Subtarget->hasMin3Max3_16())) { ((VT != MVT::f16 && VT != MVT::i16) || Subtarget->hasMin3Max3_16())) {
// max(max(a, b), c) -> max3(a, b, c) // max(max(a, b), c) -> max3(a, b, c)
// min(min(a, b), c) -> min3(a, b, c) // min(min(a, b), c) -> min3(a, b, c)

12
llvm/test/CodeGen/AMDGPU/fmax3.ll
View File

@ -84,9 +84,21 @@ define amdgpu_kernel void @test_fmax3_olt_1_f16(half addrspace(1)* %out, half ad
ret void ret void
} }
; Checks whether the test passes; performMinMaxCombine() should not optimize vector patterns of max3
; since there are no pack instructions for fmax3.
; GCN-LABEL: {{^}}no_fmax3_v2f16:
define <2 x half> @no_fmax3_v2f16(<2 x half> %a, <2 x half> %b, <2 x half> %c, <2 x half> %d) {
entry:
%max = tail call fast <2 x half> @llvm.maxnum.v2f16(<2 x half> %a, <2 x half> %b)
%max1 = tail call fast <2 x half> @llvm.maxnum.v2f16(<2 x half> %c, <2 x half> %max)
%res = tail call fast <2 x half> @llvm.maxnum.v2f16(<2 x half> %max1, <2 x half> %d)
ret <2 x half> %res
}
declare i32 @llvm.amdgcn.workitem.id.x() #1 declare i32 @llvm.amdgcn.workitem.id.x() #1
declare float @llvm.maxnum.f32(float, float) #1 declare float @llvm.maxnum.f32(float, float) #1
declare half @llvm.maxnum.f16(half, half) #1 declare half @llvm.maxnum.f16(half, half) #1
declare <2 x half> @llvm.maxnum.v2f16(<2 x half>, <2 x half>)
attributes #0 = { nounwind } attributes #0 = { nounwind }
attributes #1 = { nounwind readnone speculatable } attributes #1 = { nounwind readnone speculatable }

12
llvm/test/CodeGen/AMDGPU/fmin3.ll
View File

@ -82,9 +82,21 @@ define amdgpu_kernel void @test_fmin3_olt_1_f16(half addrspace(1)* %out, half ad
ret void ret void
} }
; Checks whether the test passes; performMinMaxCombine() should not optimize vector patterns of min3
; since there are no pack instructions for fmin3.
; GCN-LABEL: {{^}}no_fmin3_v2f16:
define <2 x half> @no_fmin3_v2f16(<2 x half> %a, <2 x half> %b, <2 x half> %c, <2 x half> %d) {
entry:
%min = tail call fast <2 x half> @llvm.minnum.v2f16(<2 x half> %a, <2 x half> %b)
%min1 = tail call fast <2 x half> @llvm.minnum.v2f16(<2 x half> %c, <2 x half> %min)
%res = tail call fast <2 x half> @llvm.minnum.v2f16(<2 x half> %min1, <2 x half> %d)
ret <2 x half> %res
}
declare i32 @llvm.amdgcn.workitem.id.x() #1 declare i32 @llvm.amdgcn.workitem.id.x() #1
declare float @llvm.minnum.f32(float, float) #1 declare float @llvm.minnum.f32(float, float) #1
declare half @llvm.minnum.f16(half, half) #1 declare half @llvm.minnum.f16(half, half) #1
declare <2 x half> @llvm.minnum.v2f16(<2 x half>, <2 x half>)
attributes #0 = { nounwind } attributes #0 = { nounwind }
attributes #1 = { nounwind readnone speculatable } attributes #1 = { nounwind readnone speculatable }