llvm-project/llvm/test/CodeGen/X86/GlobalISel/select-memop-v128.mir

134 lines
4.9 KiB
YAML

# RUN: llc -mtriple=x86_64-linux-gnu -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=NO_AVX512VL --check-prefix=NO_AVX512F --check-prefix=SSE
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=NO_AVX512VL --check-prefix=NO_AVX512F --check-prefix=AVX
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=NO_AVX512VL --check-prefix=AVX512ALL --check-prefix=AVX512F
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f -mattr=+avx512vl -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX512ALL --check-prefix=AVX512VL
--- |
define <4 x i32> @test_load_v4i32_noalign(<4 x i32>* %p1) {
%r = load <4 x i32>, <4 x i32>* %p1, align 1
ret <4 x i32> %r
}
define <4 x i32> @test_load_v4i32_align(<4 x i32>* %p1) {
%r = load <4 x i32>, <4 x i32>* %p1, align 16
ret <4 x i32> %r
}
define <4 x i32>* @test_store_v4i32_align(<4 x i32> %val, <4 x i32>* %p1) {
store <4 x i32> %val, <4 x i32>* %p1, align 16
ret <4 x i32>* %p1
}
define <4 x i32>* @test_store_v4i32_noalign(<4 x i32> %val, <4 x i32>* %p1) {
store <4 x i32> %val, <4 x i32>* %p1, align 1
ret <4 x i32>* %p1
}
...
---
# ALL-LABEL: name: test_load_v4i32_noalign
name: test_load_v4i32_noalign
alignment: 4
legalized: true
regBankSelected: true
registers:
- { id: 0, class: gpr }
- { id: 1, class: vecr }
# ALL: %0:gr64 = COPY %rdi
# SSE: %1:vr128 = MOVUPSrm %0, 1, _, 0, _ :: (load 16 from %ir.p1, align 1)
# AVX: %1:vr128 = VMOVUPSrm %0, 1, _, 0, _ :: (load 16 from %ir.p1, align 1)
# AVX512F: %1:vr128x = VMOVUPSZ128rm_NOVLX %0, 1, _, 0, _ :: (load 16 from %ir.p1, align 1)
# AVX512VL: %1:vr128x = VMOVUPSZ128rm %0, 1, _, 0, _ :: (load 16 from %ir.p1, align 1)
# ALL: %xmm0 = COPY %1
body: |
bb.1 (%ir-block.0):
liveins: %rdi
%0(p0) = COPY %rdi
%1(<4 x s32>) = G_LOAD %0(p0) :: (load 16 from %ir.p1, align 1)
%xmm0 = COPY %1(<4 x s32>)
RET 0, implicit %xmm0
...
---
# ALL-LABEL: name: test_load_v4i32_align
name: test_load_v4i32_align
alignment: 4
legalized: true
regBankSelected: true
registers:
- { id: 0, class: gpr }
- { id: 1, class: vecr }
# ALL: %0:gr64 = COPY %rdi
# SSE: %1:vr128 = MOVAPSrm %0, 1, _, 0, _ :: (load 16 from %ir.p1)
# AVX: %1:vr128 = VMOVAPSrm %0, 1, _, 0, _ :: (load 16 from %ir.p1)
# AVX512F: %1:vr128x = VMOVAPSZ128rm_NOVLX %0, 1, _, 0, _ :: (load 16 from %ir.p1)
# AVX512VL: %1:vr128x = VMOVAPSZ128rm %0, 1, _, 0, _ :: (load 16 from %ir.p1)
# ALL: %xmm0 = COPY %1
body: |
bb.1 (%ir-block.0):
liveins: %rdi
%0(p0) = COPY %rdi
%1(<4 x s32>) = G_LOAD %0(p0) :: (load 16 from %ir.p1)
%xmm0 = COPY %1(<4 x s32>)
RET 0, implicit %xmm0
...
---
# ALL-LABEL: name: test_store_v4i32_align
name: test_store_v4i32_align
alignment: 4
legalized: true
regBankSelected: true
registers:
- { id: 0, class: vecr }
- { id: 1, class: gpr }
# NO_AVX512F: %0:vr128 = COPY %xmm0
# AVX512ALL: %0:vr128x = COPY %xmm0
# ALL: %1:gr64 = COPY %rdi
# SSE: MOVAPSmr %1, 1, _, 0, _, %0 :: (store 16 into %ir.p1)
# AVX: VMOVAPSmr %1, 1, _, 0, _, %0 :: (store 16 into %ir.p1)
# AVX512F: VMOVAPSZ128mr_NOVLX %1, 1, _, 0, _, %0 :: (store 16 into %ir.p1)
# AVX512VL: VMOVAPSZ128mr %1, 1, _, 0, _, %0 :: (store 16 into %ir.p1)
# ALL: %rax = COPY %1
body: |
bb.1 (%ir-block.0):
liveins: %rdi, %xmm0
%0(<4 x s32>) = COPY %xmm0
%1(p0) = COPY %rdi
G_STORE %0(<4 x s32>), %1(p0) :: (store 16 into %ir.p1, align 16)
%rax = COPY %1(p0)
RET 0, implicit %rax
...
---
# ALL-LABEL: name: test_store_v4i32_noalign
name: test_store_v4i32_noalign
alignment: 4
legalized: true
regBankSelected: true
registers:
- { id: 0, class: vecr }
- { id: 1, class: gpr }
# NO_AVX512F: %0:vr128 = COPY %xmm0
# AVX512ALL: %0:vr128x = COPY %xmm0
# ALL: %1:gr64 = COPY %rdi
# SSE: MOVUPSmr %1, 1, _, 0, _, %0 :: (store 16 into %ir.p1, align 1)
# AVX: VMOVUPSmr %1, 1, _, 0, _, %0 :: (store 16 into %ir.p1, align 1)
# AVX512F: VMOVUPSZ128mr_NOVLX %1, 1, _, 0, _, %0 :: (store 16 into %ir.p1, align 1)
# AVX512VL: VMOVUPSZ128mr %1, 1, _, 0, _, %0 :: (store 16 into %ir.p1, align 1)
# ALL: %rax = COPY %1
body: |
bb.1 (%ir-block.0):
liveins: %rdi, %xmm0
%0(<4 x s32>) = COPY %xmm0
%1(p0) = COPY %rdi
G_STORE %0(<4 x s32>), %1(p0) :: (store 16 into %ir.p1, align 1)
%rax = COPY %1(p0)
RET 0, implicit %rax
...