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/GlobalISel/inst-select-load-local.mir

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

825 lines
33 KiB
Plaintext
Raw Normal View History

AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=tahiti -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX6 %s
# RUN: llc -march=amdgcn -mcpu=hawaii -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX7 %s
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX7 %s
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX9 %s
# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX9 %s
---
name: load_local_s32_from_4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_s32_from_4
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_B32_]]
; GFX7-LABEL: name: load_local_s32_from_4
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_s32_from_4
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX7-DS128: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_s32_from_4
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_B32_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_B32_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 4, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_B32_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = G_LOAD %0 :: (load 4, align 4, addrspace 3)
$vgpr0 = COPY %1
...
---
name: load_local_s32_from_2
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_s32_from_2
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_READ_U16_:%[0-9]+]]:vgpr_32 = DS_READ_U16 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 2, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_U16_]]
; GFX7-LABEL: name: load_local_s32_from_2
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_READ_U16_:%[0-9]+]]:vgpr_32 = DS_READ_U16 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 2, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_U16_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_s32_from_2
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_U16_:%[0-9]+]]:vgpr_32 = DS_READ_U16 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 2, addrspace 3)
; GFX7-DS128: $vgpr0 = COPY [[DS_READ_U16_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_s32_from_2
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_U16_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U16_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 2, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_U16_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = G_LOAD %0 :: (load 2, align 2, addrspace 3)
$vgpr0 = COPY %1
...
---
name: load_local_s32_from_1
legalized: true
regBankSelected: true
tracksRegLiveness: true
machineFunctionInfo:
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
scratchWaveOffsetReg: $sgpr4
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_s32_from_1
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_U8_]]
; GFX7-LABEL: name: load_local_s32_from_1
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_U8_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_s32_from_1
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX7-DS128: $vgpr0 = COPY [[DS_READ_U8_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_s32_from_1
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_U8_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U8_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 1, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_U8_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = G_LOAD %0 :: (load 1, align 1, addrspace 3)
$vgpr0 = COPY %1
...
---
name: load_local_v2s32
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_v2s32
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
; GFX7-LABEL: name: load_local_v2s32
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_v2s32
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX7-DS128: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_v2s32
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_B64_gfx9_:%[0-9]+]]:vreg_64 = DS_READ_B64_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 8, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[DS_READ_B64_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(<2 x s32>) = G_LOAD %0 :: (load 8, align 8, addrspace 3)
$vgpr0_vgpr1 = COPY %1
...
---
name: load_local_v2s32_align4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_v2s32_align4
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[LOAD:%[0-9]+]]:vreg_64(<2 x s32>) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[LOAD]](<2 x s32>)
; GFX7-LABEL: name: load_local_v2s32_align4
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[LOAD:%[0-9]+]]:vreg_64(<2 x s32>) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[LOAD]](<2 x s32>)
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_v2s32_align4
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[LOAD:%[0-9]+]]:vreg_64(<2 x s32>) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX7-DS128: $vgpr0_vgpr1 = COPY [[LOAD]](<2 x s32>)
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_v2s32_align4
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX9: [[LOAD:%[0-9]+]]:vreg_64(<2 x s32>) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[LOAD]](<2 x s32>)
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(<2 x s32>) = G_LOAD %0 :: (load 8, align 4, addrspace 3)
$vgpr0_vgpr1 = COPY %1
...
---
name: load_local_s64
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_s64
; GFX6: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX6: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7-LABEL: name: load_local_s64
; GFX7: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_s64
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX7-DS128: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_s64
; GFX9: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_B64_gfx9_:%[0-9]+]]:vreg_64 = DS_READ_B64_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 8, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[DS_READ_B64_gfx9_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s64) = G_LOAD %0 :: (load 8, align 8, addrspace 3)
$vgpr0_vgpr1 = COPY %1
...
---
name: load_local_s64_align4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_s64_align4
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[LOAD:%[0-9]+]]:vreg_64(s64) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[LOAD]](s64)
; GFX7-LABEL: name: load_local_s64_align4
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[LOAD:%[0-9]+]]:vreg_64(s64) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[LOAD]](s64)
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_s64_align4
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[LOAD:%[0-9]+]]:vreg_64(s64) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX7-DS128: $vgpr0_vgpr1 = COPY [[LOAD]](s64)
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_s64_align4
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX9: [[LOAD:%[0-9]+]]:vreg_64(s64) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[LOAD]](s64)
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s64) = G_LOAD %0 :: (load 8, align 4, addrspace 3)
$vgpr0_vgpr1 = COPY %1
...
---
name: load_local_p3_from_4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_p3_from_4
; GFX6: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX6: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7-LABEL: name: load_local_p3_from_4
; GFX7: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_p3_from_4
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX7-DS128: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_p3_from_4
; GFX9: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_B32_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_B32_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 4, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_B32_gfx9_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(p3) = G_LOAD %0 :: (load 4, align 4, addrspace 3)
$vgpr0 = COPY %1
...
---
name: load_local_p5_from_4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_p5_from_4
; GFX6: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX6: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7-LABEL: name: load_local_p5_from_4
; GFX7: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_p5_from_4
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX7-DS128: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_p5_from_4
; GFX9: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_B32_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_B32_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 4, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_B32_gfx9_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(p3) = G_LOAD %0 :: (load 4, align 4, addrspace 3)
$vgpr0 = COPY %1
...
---
name: load_local_p1_align8
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_p1_align8
; GFX6: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX6: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7-LABEL: name: load_local_p1_align8
; GFX7: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_p1_align8
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX7-DS128: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_p1_align8
; GFX9: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_B64_gfx9_:%[0-9]+]]:vreg_64 = DS_READ_B64_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 8, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[DS_READ_B64_gfx9_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(p1) = G_LOAD %0 :: (load 8, align 8, addrspace 3)
$vgpr0_vgpr1 = COPY %1
...
---
name: load_local_p1_align4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_p1_align4
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[LOAD:%[0-9]+]]:vreg_64(p1) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[LOAD]](p1)
; GFX7-LABEL: name: load_local_p1_align4
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[LOAD:%[0-9]+]]:vreg_64(p1) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[LOAD]](p1)
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_p1_align4
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[LOAD:%[0-9]+]]:vreg_64(p1) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX7-DS128: $vgpr0_vgpr1 = COPY [[LOAD]](p1)
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_p1_align4
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX9: [[LOAD:%[0-9]+]]:vreg_64(p1) = G_LOAD [[COPY]](p3) :: (load 8, align 4, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[LOAD]](p1)
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(p1) = G_LOAD %0 :: (load 8, align 4, addrspace 3)
$vgpr0_vgpr1 = COPY %1
...
---
name: load_local_p999_from_8
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_p999_from_8
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[LOAD:%[0-9]+]]:vreg_64(p999) = G_LOAD [[COPY]](p3) :: (load 8, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[LOAD]](p999)
; GFX7-LABEL: name: load_local_p999_from_8
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[LOAD:%[0-9]+]]:vreg_64(p999) = G_LOAD [[COPY]](p3) :: (load 8, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[LOAD]](p999)
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_p999_from_8
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[LOAD:%[0-9]+]]:vreg_64(p999) = G_LOAD [[COPY]](p3) :: (load 8, addrspace 3)
; GFX7-DS128: $vgpr0_vgpr1 = COPY [[LOAD]](p999)
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_p999_from_8
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX9: [[LOAD:%[0-9]+]]:vreg_64(p999) = G_LOAD [[COPY]](p3) :: (load 8, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[LOAD]](p999)
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(p999) = G_LOAD %0 :: (load 8, align 8, addrspace 3)
$vgpr0_vgpr1 = COPY %1
...
---
name: load_local_v2p3
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_v2p3
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[LOAD:%[0-9]+]]:vreg_64(<2 x p3>) = G_LOAD [[COPY]](p3) :: (load 8, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[LOAD]](<2 x p3>)
; GFX7-LABEL: name: load_local_v2p3
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[LOAD:%[0-9]+]]:vreg_64(<2 x p3>) = G_LOAD [[COPY]](p3) :: (load 8, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[LOAD]](<2 x p3>)
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_v2p3
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[LOAD:%[0-9]+]]:vreg_64(<2 x p3>) = G_LOAD [[COPY]](p3) :: (load 8, addrspace 3)
; GFX7-DS128: $vgpr0_vgpr1 = COPY [[LOAD]](<2 x p3>)
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_v2p3
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX9: [[LOAD:%[0-9]+]]:vreg_64(<2 x p3>) = G_LOAD [[COPY]](p3) :: (load 8, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[LOAD]](<2 x p3>)
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(<2 x p3>) = G_LOAD %0 :: (load 8, align 8, addrspace 3)
$vgpr0_vgpr1 = COPY %1
...
---
name: load_local_v2s16
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_v2s16
; GFX6: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX6: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7-LABEL: name: load_local_v2s16
; GFX7: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_v2s16
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 4, addrspace 3)
; GFX7-DS128: $vgpr0 = COPY [[DS_READ_B32_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_v2s16
; GFX9: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_B32_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_B32_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 4, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_B32_gfx9_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(<2 x s16>) = G_LOAD %0 :: (load 4, align 4, addrspace 3)
$vgpr0 = COPY %1
...
---
name: load_local_v4s16
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_v4s16
; GFX6: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX6: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX6: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7-LABEL: name: load_local_v4s16
; GFX7: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX7: $m0 = S_MOV_B32 -1
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX7: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_v4s16
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_B64_:%[0-9]+]]:vreg_64 = DS_READ_B64 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load 8, addrspace 3)
; GFX7-DS128: $vgpr0_vgpr1 = COPY [[DS_READ_B64_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_v4s16
; GFX9: liveins: $vgpr0
AMDGPU/GlobalISel: Fix load/store of types in other address spaces There should probably be a size only matcher. llvm-svn: 371155
2019-09-06 08:36:06 +08:00
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_B64_gfx9_:%[0-9]+]]:vreg_64 = DS_READ_B64_gfx9 [[COPY]], 0, 0, implicit $exec :: (load 8, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[DS_READ_B64_gfx9_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(<4 x s16>) = G_LOAD %0 :: (load 8, align 8, addrspace 3)
$vgpr0_vgpr1 = COPY %1
...
# ---
# name: load_local_v6s16
# legalized: true
# regBankSelected: true
# tracksRegLiveness: true
# machineFunctionInfo:
# scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
# scratchWaveOffsetReg: $sgpr4
# stackPtrOffsetReg: $sgpr32
# body: |
# bb.0:
# liveins: $vgpr0
# %0:vgpr(p3) = COPY $vgpr0
# %1:vgpr(<6 x s16>) = G_LOAD %0 :: (load 12, align 4, addrspace 3)
# $vgpr0_vgpr1_vgpr2 = COPY %1
# ...
################################################################################
### Stress addressing modes
################################################################################
---
name: load_local_s32_from_1_gep_65535
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_s32_from_1_gep_65535
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 65535, implicit $exec
; GFX6: %2:vgpr_32, dead %4:sreg_64_xexec = V_ADD_I32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 %2, 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_U8_]]
; GFX7-LABEL: name: load_local_s32_from_1_gep_65535
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[COPY]], 65535, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_U8_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_s32_from_1_gep_65535
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[COPY]], 65535, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX7-DS128: $vgpr0 = COPY [[DS_READ_U8_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_s32_from_1_gep_65535
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[DS_READ_U8_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U8_gfx9 [[COPY]], 65535, 0, implicit $exec :: (load 1, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_U8_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = G_CONSTANT i32 65535
%2:vgpr(p3) = G_GEP %0, %1
%3:vgpr(s32) = G_LOAD %2 :: (load 1, align 1, addrspace 3)
$vgpr0 = COPY %3
...
---
AMDGPU/GlobalISel: Use known bits for selection llvm-svn: 371409
2019-09-09 23:39:32 +08:00
name: load_local_s32_from_1_gep_65535_known_bits_base_address
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_s32_from_1_gep_65535_known_bits_base_address
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2147483647, implicit $exec
; GFX6: [[V_AND_B32_e64_:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY]], [[V_MOV_B32_e32_]], implicit $exec
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[V_AND_B32_e64_]], 65535, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_U8_]]
; GFX7-LABEL: name: load_local_s32_from_1_gep_65535_known_bits_base_address
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2147483647, implicit $exec
; GFX7: [[V_AND_B32_e64_:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY]], [[V_MOV_B32_e32_]], implicit $exec
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 [[V_AND_B32_e64_]], 65535, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_U8_]]
; GFX9-LABEL: name: load_local_s32_from_1_gep_65535_known_bits_base_address
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2147483647, implicit $exec
; GFX9: [[V_AND_B32_e64_:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY]], [[V_MOV_B32_e32_]], implicit $exec
; GFX9: [[DS_READ_U8_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U8_gfx9 [[V_AND_B32_e64_]], 65535, 0, implicit $exec :: (load 1, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_U8_gfx9_]]
%0:vgpr(s32) = COPY $vgpr0
%1:vgpr(s32) = G_CONSTANT i32 2147483647
%2:vgpr(s32) = G_AND %0, %1
%3:vgpr(p3) = G_INTTOPTR %2
%4:vgpr(s32) = G_CONSTANT i32 65535
%5:vgpr(p3) = G_GEP %3, %4
%6:vgpr(s32) = G_LOAD %5 :: (load 1, align 1, addrspace 3)
$vgpr0 = COPY %6
...
---
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
name: load_local_s32_from_1_gep_65536
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_s32_from_1_gep_65536
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 65536, implicit $exec
; GFX6: %2:vgpr_32, dead %4:sreg_64_xexec = V_ADD_I32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 %2, 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_U8_]]
; GFX7-LABEL: name: load_local_s32_from_1_gep_65536
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 65536, implicit $exec
; GFX7: %2:vgpr_32, dead %4:sreg_64_xexec = V_ADD_I32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 %2, 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_U8_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_s32_from_1_gep_65536
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 65536, implicit $exec
; GFX7-DS128: %2:vgpr_32, dead %4:sreg_64_xexec = V_ADD_I32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 %2, 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX7-DS128: $vgpr0 = COPY [[DS_READ_U8_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_s32_from_1_gep_65536
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 65536, implicit $exec
; GFX9: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX9: [[DS_READ_U8_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U8_gfx9 [[V_ADD_U32_e64_]], 0, 0, implicit $exec :: (load 1, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_U8_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = G_CONSTANT i32 65536
%2:vgpr(p3) = G_GEP %0, %1
%3:vgpr(s32) = G_LOAD %2 :: (load 1, align 1, addrspace 3)
$vgpr0 = COPY %3
...
---
name: load_local_s32_from_1_gep_m1
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GFX6-LABEL: name: load_local_s32_from_1_gep_m1
; GFX6: liveins: $vgpr0
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4294967295, implicit $exec
; GFX6: %2:vgpr_32, dead %4:sreg_64_xexec = V_ADD_I32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 %2, 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_READ_U8_]]
; GFX7-LABEL: name: load_local_s32_from_1_gep_m1
; GFX7: liveins: $vgpr0
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4294967295, implicit $exec
; GFX7: %2:vgpr_32, dead %4:sreg_64_xexec = V_ADD_I32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 %2, 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_READ_U8_]]
AMDGPU/GlobalISel: First pass at attempting to legalize load/stores There's still a lot more to do, but this handles decomposing due to alignment. I've gotten it to the point where nothing crashes or infinite loops the legalizer. llvm-svn: 371533
2019-09-11 00:20:14 +08:00
; GFX7-DS128-LABEL: name: load_local_s32_from_1_gep_m1
; GFX7-DS128: liveins: $vgpr0
; GFX7-DS128: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7-DS128: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4294967295, implicit $exec
; GFX7-DS128: %2:vgpr_32, dead %4:sreg_64_xexec = V_ADD_I32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX7-DS128: $m0 = S_MOV_B32 -1
; GFX7-DS128: [[DS_READ_U8_:%[0-9]+]]:vgpr_32 = DS_READ_U8 %2, 0, 0, implicit $m0, implicit $exec :: (load 1, addrspace 3)
; GFX7-DS128: $vgpr0 = COPY [[DS_READ_U8_]]
AMDGPU/GlobalISel: Select local loads llvm-svn: 367498
2019-08-01 08:53:38 +08:00
; GFX9-LABEL: name: load_local_s32_from_1_gep_m1
; GFX9: liveins: $vgpr0
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4294967295, implicit $exec
; GFX9: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX9: [[DS_READ_U8_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U8_gfx9 [[V_ADD_U32_e64_]], 0, 0, implicit $exec :: (load 1, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_READ_U8_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = G_CONSTANT i32 -1
%2:vgpr(p3) = G_GEP %0, %1
%3:vgpr(s32) = G_LOAD %2 :: (load 1, align 1, addrspace 3)
$vgpr0 = COPY %3
...