llvm-project/llvm/test/CodeGen/AMDGPU/merge-load-store.mir

166 lines
7.1 KiB
YAML

# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-load-store-opt -o - %s | FileCheck %s
# Check that SILoadStoreOptimizer honors memory dependencies between moved
# instructions.
#
# The following IR snippet would usually be optimized by the peephole optimizer.
# However, an equivalent situation can occur with buffer instructions as well.
# CHECK-LABEL: name: mem_dependency
# CHECK: DS_READ2_B32 %0, 0, 1,
# CHECK: DS_WRITE_B32 %0, killed %1, 64,
# CHECK: DS_READ2_B32 %0, 16, 17,
# CHECK: DS_WRITE_B32 killed %0, %5, 0
--- |
define amdgpu_kernel void @mem_dependency(i32 addrspace(3)* %ptr.0) nounwind {
%ptr.4 = getelementptr i32, i32 addrspace(3)* %ptr.0, i32 1
%ptr.64 = getelementptr i32, i32 addrspace(3)* %ptr.0, i32 16
%1 = load i32, i32 addrspace(3)* %ptr.0
store i32 %1, i32 addrspace(3)* %ptr.64
%2 = load i32, i32 addrspace(3)* %ptr.64
%3 = load i32, i32 addrspace(3)* %ptr.4
%4 = add i32 %2, %3
store i32 %4, i32 addrspace(3)* %ptr.0
ret void
}
@lds0 = external dso_local unnamed_addr addrspace(3) global [256 x i32], align 4
@lds1 = external dso_local unnamed_addr addrspace(3) global [256 x i32], align 4
@lds2 = external dso_local unnamed_addr addrspace(3) global [256 x i32], align 4
@lds3 = external dso_local unnamed_addr addrspace(3) global [256 x i32], align 4
define void @asm_defines_address() #0 {
bb:
%tmp1 = load i32, i32 addrspace(3)* getelementptr inbounds ([256 x i32], [256 x i32] addrspace(3)* @lds0, i32 0, i32 0), align 4
%0 = and i32 %tmp1, 255
%tmp3 = load i32, i32 addrspace(3)* getelementptr ([256 x i32], [256 x i32] addrspace(3)* @lds1, i32 0, i32 undef), align 4
%tmp6 = load i32, i32 addrspace(3)* getelementptr ([256 x i32], [256 x i32] addrspace(3)* @lds3, i32 0, i32 undef), align 4
%tmp7 = tail call i32 asm "v_or_b32 $0, 0, $1", "=v,v"(i32 %tmp6) #1
%tmp10 = lshr i32 %tmp7, 16
%tmp11 = and i32 %tmp10, 255
%tmp12 = getelementptr inbounds [256 x i32], [256 x i32] addrspace(3)* @lds1, i32 0, i32 %tmp11
%tmp13 = load i32, i32 addrspace(3)* %tmp12, align 4
%tmp14 = xor i32 %tmp3, %tmp13
%tmp15 = lshr i32 %tmp14, 8
%tmp16 = and i32 %tmp15, 16711680
%tmp19 = lshr i32 %tmp16, 16
%tmp20 = and i32 %tmp19, 255
%tmp21 = getelementptr inbounds [256 x i32], [256 x i32] addrspace(3)* @lds1, i32 0, i32 %tmp20
%tmp22 = load i32, i32 addrspace(3)* %tmp21, align 4
%tmp24 = load i32, i32 addrspace(3)* getelementptr ([256 x i32], [256 x i32] addrspace(3)* @lds2, i32 0, i32 undef), align 4
%tmp25 = xor i32 %tmp22, %tmp24
%tmp26 = and i32 %tmp25, -16777216
%tmp28 = or i32 %0, %tmp26
store volatile i32 %tmp28, i32 addrspace(1)* undef
ret void
}
attributes #0 = { convergent nounwind }
attributes #1 = { convergent nounwind readnone }
define amdgpu_kernel void @move_waw_hazards() #0 {
ret void
}
attributes #0 = { convergent nounwind }
...
---
name: mem_dependency
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '$vgpr0', virtual-reg: '%1' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0:
liveins: $vgpr0
%1:vgpr_32 = COPY $vgpr0
$m0 = S_MOV_B32 -1
%2:vgpr_32 = DS_READ_B32 %1, 0, 0, implicit $m0, implicit $exec :: (load 4 from %ir.ptr.0)
DS_WRITE_B32 %1, killed %2, 64, 0, implicit $m0, implicit $exec :: (store 4 into %ir.ptr.64)
; Make this load unmergeable, to tempt SILoadStoreOptimizer into merging the
; other two loads.
%6:vreg_64 = DS_READ2_B32 %1, 16, 17, 0, implicit $m0, implicit $exec :: (load 8 from %ir.ptr.64, align 4)
%3:vgpr_32 = COPY %6.sub0
%4:vgpr_32 = DS_READ_B32 %1, 4, 0, implicit $m0, implicit $exec :: (load 4 from %ir.ptr.4)
%5:vgpr_32 = V_ADD_I32_e32 killed %3, killed %4, implicit-def $vcc, implicit $exec
DS_WRITE_B32 killed %1, %5, 0, 0, implicit killed $m0, implicit $exec :: (store 4 into %ir.ptr.0)
S_ENDPGM 0
...
---
# Make sure the asm def isn't moved after the point where it's used for
# the address.
# CHECK-LABEL: name: asm_defines_address
# CHECK: DS_READ2ST64_B32
# CHECK: DS_READ2ST64_B32
# CHECK: INLINEASM
# CHECK: DS_READ_B32
# CHECK: DS_READ_B32
name: asm_defines_address
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
body: |
bb.0:
%1:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
%2:vgpr_32 = DS_READ_B32 %1, 3072, 0, implicit $m0, implicit $exec :: (dereferenceable load 4 from `i32 addrspace(3)* getelementptr inbounds ([256 x i32], [256 x i32] addrspace(3)* @lds0, i32 0, i32 0)`, addrspace 3)
%3:vgpr_32 = DS_READ_B32 %1, 2048, 0, implicit $m0, implicit $exec :: (load 4 from `i32 addrspace(3)* getelementptr ([256 x i32], [256 x i32] addrspace(3)* @lds1, i32 0, i32 undef)`, addrspace 3)
%4:vgpr_32 = DS_READ_B32 %1, 1024, 0, implicit $m0, implicit $exec :: (load 4 from `i32 addrspace(3)* getelementptr ([256 x i32], [256 x i32] addrspace(3)* @lds3, i32 0, i32 undef)`, addrspace 3)
INLINEASM &"v_or_b32 $0, 0, $1", 32, 327690, def %0, 327689, %4
%5:vgpr_32 = DS_READ_B32 %0, 2048, 0, implicit $m0, implicit $exec :: (load 4 from %ir.tmp12, addrspace 3)
%6:vgpr_32 = DS_READ_B32 %5, 2048, 0, implicit $m0, implicit $exec :: (load 4 from %ir.tmp21, addrspace 3)
%7:vgpr_32 = DS_READ_B32 %1, 0, 0, implicit $m0, implicit $exec :: (load 4 from `i32 addrspace(3)* getelementptr ([256 x i32], [256 x i32] addrspace(3)* @lds2, i32 0, i32 undef)`, addrspace 3)
S_SETPC_B64_return undef $sgpr30_sgpr31, implicit %6, implicit %7
...
---
# Make sure Write-after-Write hazards are correctly detected and the
# instructions moved accordingly.
# operations.
# CHECK-LABEL: name: move_waw_hazards
# CHECK: S_AND_B64
# CHECK: S_CMP_EQ_U32
name: move_waw_hazards
tracksRegLiveness: true
body: |
bb.0:
liveins: $sgpr0_sgpr1
%3:sgpr_64 = COPY $sgpr0_sgpr1
%6:sreg_32_xm0_xexec = S_MOV_B32 0
%7:sreg_32_xm0 = S_MOV_B32 0
%8:sreg_64_xexec = REG_SEQUENCE killed %6, %subreg.sub0, %7, %subreg.sub1
%9:sreg_128 = S_LOAD_DWORDX4_IMM killed %8, 0, 0, 0 :: (invariant load 16, addrspace 6)
%31:sreg_64_xexec = S_BUFFER_LOAD_DWORDX2_IMM %9, 0, 0, 0 :: (dereferenceable invariant load 4)
%10:sreg_32_xm0_xexec = COPY %31.sub0
%11:sreg_32_xm0_xexec = COPY killed %31.sub1
%12:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %9, 2, 0, 0 :: (dereferenceable invariant load 4)
%13:sreg_64 = V_CMP_NE_U32_e64 killed %11, 0, implicit $exec
%15:sreg_64 = V_CMP_NE_U32_e64 killed %12, 0, implicit $exec
%17:sreg_64_xexec = S_AND_B64 killed %13, killed %15, implicit-def dead $scc
S_CMP_EQ_U32 killed %10, 0, implicit-def $scc
%18:sreg_32_xm0_xexec = S_BUFFER_LOAD_DWORD_IMM %9, 3, 0, 0 :: (dereferenceable invariant load 4)
S_ENDPGM 0
...