8b2ca766f0
We need to guarantee cheap copies between AGPRs, and unfortunately gfx908 cannot directly do this. Theoretically we could set the scavenger up with an emergency spill slot, but it also feels unreasonable to pay that cost for what was assumed to be a simple and cheap copy. Pick a register that doesn't conflict with any ABI registers. This does not address the same issue when copying from SGPR to AGPR for gfx90a (this coincidentally fixes it for gfx908), but that's less interesting since the register allocator shouldn't be proactively introducing such copies. One edge case I'm worried about is respecting the VGPR budget implied by amdgpu-waves-per-eu. If the theoretical upper bound of a function is 32 VGPRs, this will force the actual count to be 33. This is also broken if inline assembly uses/defs something in v32. The coalescer will eliminate the intermediate vreg between the def and use, and the introduced copy will clobber the user value. (cherry picked from commit 3335784ac2d587ff4eac04586e189532ae8b2607)
237 lines
7.9 KiB
YAML
237 lines
7.9 KiB
YAML
# RUN: llc -march=amdgcn -mcpu=gfx908 -start-before=greedy,0 -stop-after=virtregrewriter,1 -verify-machineinstrs -o - %s | FileCheck --check-prefixes=GCN,GFX908 %s
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_vgpr_64
|
|
# GFX908: $vgpr3_vgpr4 = GLOBAL_LOAD
|
|
name: alloc_vgpr_64
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$vgpr2' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%1:vgpr_32 = COPY $vgpr2
|
|
%2:vreg_64 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX2 %0, %2, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_vgpr_96
|
|
# GFX908: $vgpr3_vgpr4_vgpr5 = GLOBAL_LOAD
|
|
name: alloc_vgpr_96
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$vgpr2' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%1:vgpr_32 = COPY $vgpr2
|
|
%2:vreg_96 = GLOBAL_LOAD_DWORDX3 %0, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX3 %0, %2, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_vgpr_128
|
|
# GFX908: $vgpr3_vgpr4_vgpr5_vgpr6 = GLOBAL_LOAD
|
|
name: alloc_vgpr_128
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$vgpr2' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%1:vgpr_32 = COPY $vgpr2
|
|
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_vgpr_160
|
|
# GFX908: $vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = IMAGE_LOAD
|
|
name: alloc_vgpr_160
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$vgpr2' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%1:vgpr_32 = COPY $vgpr2
|
|
%2:vreg_160 = IMAGE_LOAD_V5_V1 %1, undef %3:sgpr_256, 0, 0, 0, 0, 0, 1, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub0_sub1_sub2_sub3, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_vgpr_256
|
|
# GFX908: $vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10 = COPY
|
|
name: alloc_vgpr_256
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$vgpr2' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%1:vgpr_32 = COPY $vgpr2
|
|
%3:sgpr_256 = IMPLICIT_DEF
|
|
%2:vreg_256 = COPY %3:sgpr_256
|
|
%4:vreg_128 = IMAGE_SAMPLE_C_CL_O_V4_V8 %2, %3:sgpr_256, undef %5:sgpr_128, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub0_sub1_sub2_sub3, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_vgpr_512
|
|
# GFX908: $vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18 = IMPLICIT_DEF
|
|
name: alloc_vgpr_512
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$vgpr2' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%1:vgpr_32 = COPY $vgpr2
|
|
%2:vreg_512 = IMPLICIT_DEF
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub0_sub1_sub2_sub3, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub4_sub5_sub6_sub7, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub8_sub9_sub10_sub11, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub12_sub13_sub14_sub15, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_vgpr_1024
|
|
# GFX908: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 = IMPLICIT_DEF
|
|
name: alloc_vgpr_1024
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$vgpr2' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%1:vgpr_32 = COPY $vgpr2
|
|
%2:vreg_1024 = IMPLICIT_DEF
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub0_sub1_sub2_sub3, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub4_sub5_sub6_sub7, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub8_sub9_sub10_sub11, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub12_sub13_sub14_sub15, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub16_sub17_sub18_sub19, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub20_sub21_sub22_sub23, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub24_sub25_sub26_sub27, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub28_sub29_sub30_sub31, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_agpr_64
|
|
# GFX908: $agpr1_agpr2 = IMPLICIT_DEF
|
|
name: alloc_agpr_64
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$agpr0' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $agpr0
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%3:areg_64 = IMPLICIT_DEF
|
|
%2:vreg_64 = COPY %3:areg_64
|
|
GLOBAL_STORE_DWORDX2 %0, %2, 0, 0, implicit $exec
|
|
%1:vgpr_32 = COPY $agpr0
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_agpr_128
|
|
# GFX908: $agpr1_agpr2_agpr3_agpr4 = IMPLICIT_DEF
|
|
name: alloc_agpr_128
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$agpr0' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $agpr0
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%3:areg_128 = IMPLICIT_DEF
|
|
%2:vreg_128 = COPY %3:areg_128
|
|
GLOBAL_STORE_DWORDX4 %0, %2, 0, 0, implicit $exec
|
|
%1:vgpr_32 = COPY $agpr0
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_agpr_512
|
|
# GFX908: $agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16 = IMPLICIT_DEF
|
|
name: alloc_agpr_512
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$agpr0' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $agpr0
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%3:areg_512 = IMPLICIT_DEF
|
|
%2:vreg_512 = COPY %3:areg_512
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub0_sub1_sub2_sub3, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub4_sub5_sub6_sub7, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub8_sub9_sub10_sub11, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub12_sub13_sub14_sub15, 0, 0, implicit $exec
|
|
%1:vgpr_32 = COPY $agpr0
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: alloc_agpr_1024
|
|
# GFX908: $agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31_agpr32 = IMPLICIT_DEF
|
|
name: alloc_agpr_1024
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0_vgpr1' }
|
|
- { reg: '$agpr0' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $agpr0
|
|
|
|
%0:vreg_64 = COPY $vgpr0_vgpr1
|
|
%3:areg_1024 = IMPLICIT_DEF
|
|
%2:vreg_1024 = COPY %3:areg_1024
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub0_sub1_sub2_sub3, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub4_sub5_sub6_sub7, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub8_sub9_sub10_sub11, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub12_sub13_sub14_sub15, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub16_sub17_sub18_sub19, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub20_sub21_sub22_sub23, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub24_sub25_sub26_sub27, 0, 0, implicit $exec
|
|
GLOBAL_STORE_DWORDX4 %0, %2.sub28_sub29_sub30_sub31, 0, 0, implicit $exec
|
|
%1:vgpr_32 = COPY $agpr0
|
|
GLOBAL_STORE_DWORD %0, %1, 0, 0, implicit $exec
|
|
...
|