forked from OSchip/llvm-project
121 lines
3.7 KiB
YAML
121 lines
3.7 KiB
YAML
# RUN: llc -march=amdgcn -mcpu=gfx803 -run-pass si-insert-waitcnts %s -o - | FileCheck -check-prefix=GFX89 %s
|
|
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass si-insert-waitcnts %s -o - | FileCheck -check-prefix=GFX89 %s
|
|
|
|
--- |
|
|
define amdgpu_kernel void @flat_zero_waitcnt(i32 addrspace(1)* %global4,
|
|
<4 x i32> addrspace(1)* %global16,
|
|
i32* %flat4,
|
|
<4 x i32>* %flat16) {
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @single_fallthrough_successor_no_end_block_wait() {
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @single_branch_successor_not_next_block() {
|
|
ret void
|
|
}
|
|
|
|
...
|
|
---
|
|
|
|
# CHECK-LABEL: name: flat_zero_waitcnt
|
|
|
|
# CHECK-LABEL: bb.0:
|
|
# CHECK: FLAT_LOAD_DWORD
|
|
# CHECK: FLAT_LOAD_DWORDX4
|
|
# Global loads will return in order so we should:
|
|
# s_waitcnt vmcnt(1) lgkmcnt(1)
|
|
# CHECK-NEXT: S_WAITCNT 369
|
|
|
|
# CHECK-LABEL: bb.1:
|
|
# CHECK: FLAT_LOAD_DWORD
|
|
# GFX89: S_WAITCNT 112
|
|
# CHECK: FLAT_LOAD_DWORDX4
|
|
|
|
# CHECK-LABEL: bb.2:
|
|
# CHECK: FLAT_LOAD_DWORD
|
|
# GFX89: S_WAITCNT 112
|
|
# CHECK: FLAT_LOAD_DWORDX4
|
|
|
|
name: flat_zero_waitcnt
|
|
|
|
body: |
|
|
bb.0:
|
|
successors: %bb.1
|
|
$vgpr0 = FLAT_LOAD_DWORD $vgpr1_vgpr2, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %ir.global4)
|
|
$vgpr3_vgpr4_vgpr5_vgpr6 = FLAT_LOAD_DWORDX4 $vgpr7_vgpr8, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16 from %ir.global16)
|
|
$vgpr0 = V_MOV_B32_e32 $vgpr1, implicit $exec
|
|
S_BRANCH %bb.1
|
|
|
|
bb.1:
|
|
successors: %bb.2
|
|
$vgpr0 = FLAT_LOAD_DWORD $vgpr1_vgpr2, 0, 0, 0, 0, implicit $exec, implicit $flat_scr
|
|
$vgpr3_vgpr4_vgpr5_vgpr6 = FLAT_LOAD_DWORDX4 $vgpr7_vgpr8, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16 from %ir.global16)
|
|
$vgpr0 = V_MOV_B32_e32 $vgpr1, implicit $exec
|
|
S_BRANCH %bb.2
|
|
|
|
bb.2:
|
|
$vgpr0 = FLAT_LOAD_DWORD $vgpr1_vgpr2, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %ir.flat4)
|
|
$vgpr3_vgpr4_vgpr5_vgpr6 = FLAT_LOAD_DWORDX4 $vgpr7_vgpr8, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16 from %ir.flat16)
|
|
$vgpr0 = V_MOV_B32_e32 $vgpr1, implicit $exec
|
|
S_ENDPGM 0
|
|
...
|
|
---
|
|
# There is only a single fallthrough successor block, so there's no
|
|
# need to wait immediately.
|
|
|
|
# CHECK-LABEL: name: single_fallthrough_successor_no_end_block_wait
|
|
# CHECK: $vgpr0 = FLAT_LOAD_DWORD $vgpr1_vgpr2
|
|
# CHECK-NOT: S_WAITCNT
|
|
|
|
# CHECK: bb.1:
|
|
# CHECK-NEXT: V_LSHLREV_B64
|
|
# CHECK-NEXT: S_WAITCNT 112
|
|
# CHECK-NEXT: FLAT_STORE_DWORD
|
|
name: single_fallthrough_successor_no_end_block_wait
|
|
|
|
body: |
|
|
bb.0:
|
|
successors: %bb.1
|
|
$vgpr0 = FLAT_LOAD_DWORD $vgpr1_vgpr2, 0, 0, 0, 0, implicit $exec, implicit $flat_scr
|
|
|
|
bb.1:
|
|
$vgpr3_vgpr4 = V_LSHLREV_B64 4, $vgpr7_vgpr8, implicit $exec
|
|
FLAT_STORE_DWORD $vgpr3_vgpr4, $vgpr0, 0, 0, 0, 0, implicit $exec, implicit $flat_scr
|
|
S_ENDPGM 0
|
|
...
|
|
---
|
|
# The block has a single predecessor with a single successor, but it
|
|
# is not the next block so it's non-obvious that the wait is not needed.
|
|
|
|
|
|
# CHECK-LABEL: name: single_branch_successor_not_next_block
|
|
|
|
# CHECK: bb.1
|
|
# CHECK-NEXT: FLAT_STORE_DWORD
|
|
# CHECK-NEXT: S_ENDPGM 0
|
|
|
|
# CHECK: bb.2:
|
|
# CHECK-NEXT: V_LSHLREV_B64
|
|
# CHECK-NEXT: S_WAITCNT 112
|
|
# CHECK-NEXT: FLAT_STORE_DWORD
|
|
name: single_branch_successor_not_next_block
|
|
|
|
body: |
|
|
bb.0:
|
|
successors: %bb.2
|
|
$vgpr0 = FLAT_LOAD_DWORD $vgpr1_vgpr2, 0, 0, 0, 0, implicit $exec, implicit $flat_scr
|
|
S_BRANCH %bb.2
|
|
|
|
bb.1:
|
|
FLAT_STORE_DWORD $vgpr8_vgpr9, $vgpr10, 0, 0, 0, 0, implicit $exec, implicit $flat_scr
|
|
S_ENDPGM 0
|
|
|
|
bb.2:
|
|
$vgpr3_vgpr4 = V_LSHLREV_B64 4, $vgpr7_vgpr8, implicit $exec
|
|
FLAT_STORE_DWORD $vgpr3_vgpr4, $vgpr0, 0, 0, 0, 0, implicit $exec, implicit $flat_scr
|
|
S_ENDPGM 0
|
|
...
|