forked from OSchip/llvm-project
155 lines
6.3 KiB
YAML
155 lines
6.3 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -run-pass=legalizer %s -o - | FileCheck -check-prefix=GCN %s
|
|
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -run-pass=legalizer %s -o - | FileCheck -check-prefix=GCN %s
|
|
|
|
---
|
|
name: s_buffer_load_s32
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; GCN-LABEL: name: s_buffer_load_s32
|
|
; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(s32) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 4)
|
|
; GCN: S_ENDPGM 0, implicit [[AMDGPU_S_BUFFER_LOAD]](s32)
|
|
%0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%1:_(s32) = G_CONSTANT i32 0
|
|
%2:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|
|
|
|
---
|
|
name: s_buffer_load_v3s32
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; GCN-LABEL: name: s_buffer_load_v3s32
|
|
; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
|
|
; GCN: [[EXTRACT:%[0-9]+]]:_(<3 x s32>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<4 x s32>), 0
|
|
; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<3 x s32>)
|
|
%0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%1:_(s32) = G_CONSTANT i32 0
|
|
%2:_(<3 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|
|
|
|
---
|
|
name: s_buffer_load_v3p3
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; GCN-LABEL: name: s_buffer_load_v3p3
|
|
; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<4 x p3>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
|
|
; GCN: [[EXTRACT:%[0-9]+]]:_(<3 x p3>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<4 x p3>), 0
|
|
; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<3 x p3>)
|
|
%0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%1:_(s32) = G_CONSTANT i32 0
|
|
%2:_(<3 x p3>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|
|
|
|
---
|
|
name: s_buffer_load_v6s16
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; GCN-LABEL: name: s_buffer_load_v6s16
|
|
; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<8 x s16>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
|
|
; GCN: [[EXTRACT:%[0-9]+]]:_(<6 x s16>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<8 x s16>), 0
|
|
; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<6 x s16>)
|
|
%0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%1:_(s32) = G_CONSTANT i32 0
|
|
%2:_(<6 x s16>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|
|
|
|
---
|
|
name: s_buffer_load_v6s32
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; GCN-LABEL: name: s_buffer_load_v6s32
|
|
; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<8 x s32>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 24, align 4)
|
|
; GCN: [[EXTRACT:%[0-9]+]]:_(<6 x s32>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<8 x s32>), 0
|
|
; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<6 x s32>)
|
|
%0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%1:_(s32) = G_CONSTANT i32 0
|
|
%2:_(<6 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|
|
|
|
---
|
|
name: s_buffer_load_v3s64
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; GCN-LABEL: name: s_buffer_load_v3s64
|
|
; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<4 x s64>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 24, align 4)
|
|
; GCN: [[EXTRACT:%[0-9]+]]:_(<3 x s64>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<4 x s64>), 0
|
|
; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<3 x s64>)
|
|
%0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%1:_(s32) = G_CONSTANT i32 0
|
|
%2:_(<3 x s64>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|
|
|
|
---
|
|
name: s_buffer_load_v12s8
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; GCN-LABEL: name: s_buffer_load_v12s8
|
|
; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<16 x s8>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
|
|
; GCN: [[EXTRACT:%[0-9]+]]:_(<12 x s8>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<16 x s8>), 0
|
|
; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<12 x s8>)
|
|
%0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%1:_(s32) = G_CONSTANT i32 0
|
|
%2:_(<12 x s8>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|
|
|
|
---
|
|
name: s_buffer_load_s96
|
|
body: |
|
|
bb.0:
|
|
liveins: $sgpr0_sgpr1_sgpr2_sgpr3
|
|
|
|
; GCN-LABEL: name: s_buffer_load_s96
|
|
; GCN: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
; GCN: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
|
; GCN: [[AMDGPU_S_BUFFER_LOAD:%[0-9]+]]:_(<4 x s32>) = G_AMDGPU_S_BUFFER_LOAD [[COPY]](<4 x s32>), [[C]](s32), 0 :: (dereferenceable invariant load 12, align 4)
|
|
; GCN: [[EXTRACT:%[0-9]+]]:_(<3 x s32>) = G_EXTRACT [[AMDGPU_S_BUFFER_LOAD]](<4 x s32>), 0
|
|
; GCN: S_ENDPGM 0, implicit [[EXTRACT]](<3 x s32>)
|
|
%0:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3
|
|
%1:_(s32) = G_CONSTANT i32 0
|
|
%2:_(<3 x s32>) = G_INTRINSIC intrinsic(@llvm.amdgcn.s.buffer.load), %0, %1, 0
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|