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

AMDGPU/GlobalISel: Better code for one case of G_SHUFFLE_VECTOR on v2i16 

Reviewers: arsenm

Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, rovka, dstuttard, tpr, t-tye, hiraditya, kerbowa, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D74987
This commit is contained in:
Jay Foad 2020-02-21 20:59:44 +00:00
parent e9c79a7aef
commit b72f1448ce
2 changed files with 19 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
View File

@ -2191,7 +2191,17 @@ bool AMDGPUInstructionSelector::selectG_SHUFFLE_VECTOR(
.addReg(SrcVec)
.addImm(16);
}
} else if (isZeroOrUndef(Mask[0]) && Mask[1] == 0) {
} else if (Mask[0] == -1 && Mask[1] == 0) {
if (IsVALU) {
BuildMI(*MBB, MI, DL, TII.get(AMDGPU::V_LSHLREV_B32_e64), DstReg)
.addImm(16)
.addReg(SrcVec);
} else {
BuildMI(*MBB, MI, DL, TII.get(AMDGPU::S_LSHL_B32), DstReg)
.addReg(SrcVec)
.addImm(16);
}
} else if (Mask[0] == 0 && Mask[1] == 0) {
if (IsVALU) {
// Write low half of the register into the high half.
MachineInstr *MovSDWA =

16
llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-shuffle-vector.v2s16.mir
View File

@ -56,8 +56,8 @@ body: |
; GFX9-LABEL: name: v_shufflevector_v2s16_v2s16_u_0
; GFX9: liveins: $vgpr0, $vgpr1
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[V_MOV_B32_sdwa:%[0-9]+]]:vgpr_32 = V_MOV_B32_sdwa 0, [[COPY]], 0, 5, 2, 4, implicit $exec, implicit [[COPY]](tied-def 0)
; GFX9: $vgpr0 = COPY [[V_MOV_B32_sdwa]]
; GFX9: [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 16, [[COPY]], implicit $exec
; GFX9: $vgpr0 = COPY [[V_LSHLREV_B32_e64_]]
%0:vgpr(<2 x s16>) = COPY $vgpr0
%1:vgpr(<2 x s16>) = COPY $vgpr1
%2:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(undef, 0)
@ -143,8 +143,8 @@ body: |
; GFX9-LABEL: name: v_shufflevector_v2s16_v2s16_u_2
; GFX9: liveins: $vgpr0, $vgpr1
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX9: [[V_MOV_B32_sdwa:%[0-9]+]]:vgpr_32 = V_MOV_B32_sdwa 0, [[COPY]], 0, 5, 2, 4, implicit $exec, implicit [[COPY]](tied-def 0)
; GFX9: $vgpr0 = COPY [[V_MOV_B32_sdwa]]
; GFX9: [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 16, [[COPY]], implicit $exec
; GFX9: $vgpr0 = COPY [[V_LSHLREV_B32_e64_]]
%0:vgpr(<2 x s16>) = COPY $vgpr0
%1:vgpr(<2 x s16>) = COPY $vgpr1
%2:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(undef, 2)
@ -424,8 +424,8 @@ body: |
; GFX9-LABEL: name: s_shufflevector_v2s16_v2s16_u_0
; GFX9: liveins: $sgpr0, $sgpr1
; GFX9: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GFX9: [[S_PACK_LL_B32_B16_:%[0-9]+]]:sreg_32 = S_PACK_LL_B32_B16 [[COPY]], [[COPY]]
; GFX9: $sgpr0 = COPY [[S_PACK_LL_B32_B16_]]
; GFX9: [[S_LSHL_B32_:%[0-9]+]]:sreg_32 = S_LSHL_B32 [[COPY]], 16, implicit-def $scc
; GFX9: $sgpr0 = COPY [[S_LSHL_B32_]]
%0:sgpr(<2 x s16>) = COPY $sgpr0
%1:sgpr(<2 x s16>) = COPY $sgpr1
%2:sgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(undef, 0)
@ -511,8 +511,8 @@ body: |
; GFX9-LABEL: name: s_shufflevector_v2s16_v2s16_u_2
; GFX9: liveins: $sgpr0, $sgpr1
; GFX9: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GFX9: [[S_PACK_LL_B32_B16_:%[0-9]+]]:sreg_32 = S_PACK_LL_B32_B16 [[COPY]], [[COPY]]
; GFX9: $sgpr0 = COPY [[S_PACK_LL_B32_B16_]]
; GFX9: [[S_LSHL_B32_:%[0-9]+]]:sreg_32 = S_LSHL_B32 [[COPY]], 16, implicit-def $scc
; GFX9: $sgpr0 = COPY [[S_LSHL_B32_]]
%0:sgpr(<2 x s16>) = COPY $sgpr0
%1:sgpr(<2 x s16>) = COPY $sgpr1
%2:sgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(undef, 2)