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

AMDGPU/GlobalISel: Use SReg_32 for readfirstlane constraining 

This matches the DAG behavior where we don't use SReg_32_XM0
everywhere anymore, and fixes not coalescing the copies into m0.
This commit is contained in:
Matt Arsenault 2019-12-27 17:41:16 -05:00 committed by Matt Arsenault
parent e9775bb5d8
commit 5ce2ca524e
9 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -1022,7 +1022,7 @@ void AMDGPURegisterBankInfo::constrainOpWithReadfirstlane(
return;
MachineIRBuilder B(MI);
Register SGPR = MRI.createVirtualRegister(&AMDGPU::SReg_32_XM0RegClass);
Register SGPR = MRI.createVirtualRegister(&AMDGPU::SReg_32RegClass);
B.buildInstr(AMDGPU::V_READFIRSTLANE_B32)
.addDef(SGPR)
.addReg(Reg);

4
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.ds.gws.init.mir
View File

@ -34,7 +34,7 @@ body: |
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.gws.init), [[COPY2]](s32), [[V_READFIRSTLANE_B32_]]
%0:_(s32) = COPY $sgpr0
%1:_(s32) = COPY $vgpr0
@ -71,7 +71,7 @@ body: |
; CHECK: liveins: $vgpr0, $vgpr1
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr1
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.gws.init), [[COPY]](s32), [[V_READFIRSTLANE_B32_]]
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1

2
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.ds.gws.sema.v.mir
View File

@ -29,7 +29,7 @@ body: |
; CHECK-LABEL: name: ds_gws_init_v
; CHECK: liveins: $vgpr0
; CHECK: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.gws.sema.v), [[V_READFIRSTLANE_B32_]]
%0:_(s32) = COPY $vgpr0
G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.gws.sema.v), %0

4
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.ds.ordered.add.mir
View File

@ -30,7 +30,7 @@ body: |
; CHECK: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[INT:%[0-9]+]]:vgpr(s32) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.ordered.add), [[V_READFIRSTLANE_B32_]], [[COPY2]](s32), 0, 0, 0, 0, 0, 0
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $sgpr0
@ -47,7 +47,7 @@ body: |
; CHECK-LABEL: name: ds_ordered_add_vv
; CHECK: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[INT:%[0-9]+]]:vgpr(s32) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.ordered.add), [[V_READFIRSTLANE_B32_]], [[COPY1]](s32), 0, 0, 0, 0, 0, 0
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1

4
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.ds.ordered.swap.mir
View File

@ -30,7 +30,7 @@ body: |
; CHECK: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[COPY1]](s32)
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[INT:%[0-9]+]]:vgpr(s32) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.ordered.swap), [[V_READFIRSTLANE_B32_]], [[COPY2]](s32), 0, 0, 0, 0, 0, 0
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $sgpr0
@ -47,7 +47,7 @@ body: |
; CHECK-LABEL: name: ds_ordered_swap_vv
; CHECK: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[INT:%[0-9]+]]:vgpr(s32) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.ds.ordered.swap), [[V_READFIRSTLANE_B32_]], [[COPY1]](s32), 0, 0, 0, 0, 0, 0
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1

4
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.readlane.mir
View File

@ -45,7 +45,7 @@ body: |
; CHECK-LABEL: name: readlane_vv
; CHECK: [[COPY:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr1
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[INT:%[0-9]+]]:sgpr(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readlane), [[COPY]](s32), [[V_READFIRSTLANE_B32_]]
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
@ -63,7 +63,7 @@ body: |
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY [[COPY]](s32)
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[INT:%[0-9]+]]:sgpr(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readlane), [[COPY2]](s32), [[V_READFIRSTLANE_B32_]]
%0:_(s32) = COPY $sgpr0
%1:_(s32) = COPY $vgpr0

2
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.s.sendmsg.mir
View File

@ -25,7 +25,7 @@ body: |
liveins: $vgpr0
; CHECK-LABEL: name: sendmsg_v
; CHECK: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.s.sendmsg), 0, [[V_READFIRSTLANE_B32_]]
%0:_(s32) = COPY $vgpr0
G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.s.sendmsg), 0, %0

2
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.s.sendmsghalt.mir
View File

@ -25,7 +25,7 @@ body: |
liveins: $vgpr0
; CHECK-LABEL: name: sendmsghalt_v
; CHECK: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.s.sendmsghalt), 0, [[V_READFIRSTLANE_B32_]]
%0:_(s32) = COPY $vgpr0
G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.s.sendmsghalt), 0, %0

8
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.writelane.mir
View File

@ -50,7 +50,7 @@ body: |
; CHECK: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[INT:%[0-9]+]]:vgpr(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.writelane), [[V_READFIRSTLANE_B32_]], [[COPY1]](s32), [[COPY2]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $sgpr0
@ -69,8 +69,8 @@ body: |
; CHECK: [[COPY:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[INT:%[0-9]+]]:vgpr(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.writelane), [[V_READFIRSTLANE_B32_]], [[V_READFIRSTLANE_B32_1]], [[COPY2]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
@ -89,7 +89,7 @@ body: |
; CHECK: [[COPY:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr_32(s32) = COPY $vgpr0
; CHECK: [[COPY2:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32 = V_READFIRSTLANE_B32 [[COPY1]](s32), implicit $exec
; CHECK: [[INT:%[0-9]+]]:vgpr(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.writelane), [[COPY]](s32), [[V_READFIRSTLANE_B32_]], [[COPY2]](s32)
%0:_(s32) = COPY $sgpr0
%1:_(s32) = COPY $vgpr0