llvm-project/llvm/test/CodeGen/X86/GlobalISel/legalize-add-v256.mir

208 lines
8.9 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+sse2 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=NOT_AVX2 --check-prefix=SSE2
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=NOT_AVX2 --check-prefix=AVX1
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx2 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX2
--- |
define void @test_add_v32i8() {
%ret = add <32 x i8> undef, undef
ret void
}
define void @test_add_v16i16() {
%ret = add <16 x i16> undef, undef
ret void
}
define void @test_add_v8i32() {
%ret = add <8 x i32> undef, undef
ret void
}
define void @test_add_v4i64() {
%ret = add <4 x i64> undef, undef
ret void
}
...
---
name: test_add_v32i8
alignment: 4
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $ymm0, $ymm1
; SSE2-LABEL: name: test_add_v32i8
; SSE2: [[DEF:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; SSE2: [[DEF1:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; SSE2: [[UV:%[0-9]+]]:_(<16 x s8>), [[UV1:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF]](<32 x s8>)
; SSE2: [[UV2:%[0-9]+]]:_(<16 x s8>), [[UV3:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF1]](<32 x s8>)
; SSE2: [[ADD:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV]], [[UV2]]
; SSE2: [[ADD1:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV1]], [[UV3]]
; SSE2: [[CONCAT_VECTORS:%[0-9]+]]:_(<32 x s8>) = G_CONCAT_VECTORS [[ADD]](<16 x s8>), [[ADD1]](<16 x s8>)
; SSE2: $ymm0 = COPY [[CONCAT_VECTORS]](<32 x s8>)
; SSE2: RET 0
; AVX1-LABEL: name: test_add_v32i8
; AVX1: [[DEF:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<16 x s8>), [[UV1:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF]](<32 x s8>)
; AVX1: [[UV2:%[0-9]+]]:_(<16 x s8>), [[UV3:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF1]](<32 x s8>)
; AVX1: [[ADD:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV]], [[UV2]]
; AVX1: [[ADD1:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV1]], [[UV3]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<32 x s8>) = G_CONCAT_VECTORS [[ADD]](<16 x s8>), [[ADD1]](<16 x s8>)
; AVX1: $ymm0 = COPY [[CONCAT_VECTORS]](<32 x s8>)
; AVX1: RET 0
; AVX2-LABEL: name: test_add_v32i8
; AVX2: [[DEF:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; AVX2: [[DEF1:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; AVX2: [[ADD:%[0-9]+]]:_(<32 x s8>) = G_ADD [[DEF]], [[DEF1]]
; AVX2: $ymm0 = COPY [[ADD]](<32 x s8>)
; AVX2: RET 0
%0(<32 x s8>) = IMPLICIT_DEF
%1(<32 x s8>) = IMPLICIT_DEF
%2(<32 x s8>) = G_ADD %0, %1
$ymm0 = COPY %2
RET 0
...
---
name: test_add_v16i16
alignment: 4
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $ymm0, $ymm1
; SSE2-LABEL: name: test_add_v16i16
; SSE2: [[DEF:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; SSE2: [[DEF1:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; SSE2: [[UV:%[0-9]+]]:_(<8 x s16>), [[UV1:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF]](<16 x s16>)
; SSE2: [[UV2:%[0-9]+]]:_(<8 x s16>), [[UV3:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF1]](<16 x s16>)
; SSE2: [[ADD:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV]], [[UV2]]
; SSE2: [[ADD1:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV1]], [[UV3]]
; SSE2: [[CONCAT_VECTORS:%[0-9]+]]:_(<16 x s16>) = G_CONCAT_VECTORS [[ADD]](<8 x s16>), [[ADD1]](<8 x s16>)
; SSE2: $ymm0 = COPY [[CONCAT_VECTORS]](<16 x s16>)
; SSE2: RET 0
; AVX1-LABEL: name: test_add_v16i16
; AVX1: [[DEF:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<8 x s16>), [[UV1:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF]](<16 x s16>)
; AVX1: [[UV2:%[0-9]+]]:_(<8 x s16>), [[UV3:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF1]](<16 x s16>)
; AVX1: [[ADD:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV]], [[UV2]]
; AVX1: [[ADD1:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV1]], [[UV3]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<16 x s16>) = G_CONCAT_VECTORS [[ADD]](<8 x s16>), [[ADD1]](<8 x s16>)
; AVX1: $ymm0 = COPY [[CONCAT_VECTORS]](<16 x s16>)
; AVX1: RET 0
; AVX2-LABEL: name: test_add_v16i16
; AVX2: [[DEF:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; AVX2: [[DEF1:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; AVX2: [[ADD:%[0-9]+]]:_(<16 x s16>) = G_ADD [[DEF]], [[DEF1]]
; AVX2: $ymm0 = COPY [[ADD]](<16 x s16>)
; AVX2: RET 0
%0(<16 x s16>) = IMPLICIT_DEF
%1(<16 x s16>) = IMPLICIT_DEF
%2(<16 x s16>) = G_ADD %0, %1
$ymm0 = COPY %2
RET 0
...
---
name: test_add_v8i32
alignment: 4
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $ymm0, $ymm1
; SSE2-LABEL: name: test_add_v8i32
; SSE2: [[DEF:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; SSE2: [[DEF1:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; SSE2: [[UV:%[0-9]+]]:_(<4 x s32>), [[UV1:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF]](<8 x s32>)
; SSE2: [[UV2:%[0-9]+]]:_(<4 x s32>), [[UV3:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF1]](<8 x s32>)
; SSE2: [[ADD:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV]], [[UV2]]
; SSE2: [[ADD1:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV1]], [[UV3]]
; SSE2: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s32>) = G_CONCAT_VECTORS [[ADD]](<4 x s32>), [[ADD1]](<4 x s32>)
; SSE2: $ymm0 = COPY [[CONCAT_VECTORS]](<8 x s32>)
; SSE2: RET 0
; AVX1-LABEL: name: test_add_v8i32
; AVX1: [[DEF:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<4 x s32>), [[UV1:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF]](<8 x s32>)
; AVX1: [[UV2:%[0-9]+]]:_(<4 x s32>), [[UV3:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF1]](<8 x s32>)
; AVX1: [[ADD:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV]], [[UV2]]
; AVX1: [[ADD1:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV1]], [[UV3]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s32>) = G_CONCAT_VECTORS [[ADD]](<4 x s32>), [[ADD1]](<4 x s32>)
; AVX1: $ymm0 = COPY [[CONCAT_VECTORS]](<8 x s32>)
; AVX1: RET 0
; AVX2-LABEL: name: test_add_v8i32
; AVX2: [[DEF:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; AVX2: [[DEF1:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; AVX2: [[ADD:%[0-9]+]]:_(<8 x s32>) = G_ADD [[DEF]], [[DEF1]]
; AVX2: $ymm0 = COPY [[ADD]](<8 x s32>)
; AVX2: RET 0
%0(<8 x s32>) = IMPLICIT_DEF
%1(<8 x s32>) = IMPLICIT_DEF
%2(<8 x s32>) = G_ADD %0, %1
$ymm0 = COPY %2
RET 0
...
---
name: test_add_v4i64
alignment: 4
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $ymm0, $ymm1
; SSE2-LABEL: name: test_add_v4i64
; SSE2: [[DEF:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; SSE2: [[DEF1:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; SSE2: [[UV:%[0-9]+]]:_(<2 x s64>), [[UV1:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF]](<4 x s64>)
; SSE2: [[UV2:%[0-9]+]]:_(<2 x s64>), [[UV3:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF1]](<4 x s64>)
; SSE2: [[ADD:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV]], [[UV2]]
; SSE2: [[ADD1:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV1]], [[UV3]]
; SSE2: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s64>) = G_CONCAT_VECTORS [[ADD]](<2 x s64>), [[ADD1]](<2 x s64>)
; SSE2: $ymm0 = COPY [[CONCAT_VECTORS]](<4 x s64>)
; SSE2: RET 0
; AVX1-LABEL: name: test_add_v4i64
; AVX1: [[DEF:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<2 x s64>), [[UV1:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF]](<4 x s64>)
; AVX1: [[UV2:%[0-9]+]]:_(<2 x s64>), [[UV3:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF1]](<4 x s64>)
; AVX1: [[ADD:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV]], [[UV2]]
; AVX1: [[ADD1:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV1]], [[UV3]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s64>) = G_CONCAT_VECTORS [[ADD]](<2 x s64>), [[ADD1]](<2 x s64>)
; AVX1: $ymm0 = COPY [[CONCAT_VECTORS]](<4 x s64>)
; AVX1: RET 0
; AVX2-LABEL: name: test_add_v4i64
; AVX2: [[DEF:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; AVX2: [[DEF1:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; AVX2: [[ADD:%[0-9]+]]:_(<4 x s64>) = G_ADD [[DEF]], [[DEF1]]
; AVX2: $ymm0 = COPY [[ADD]](<4 x s64>)
; AVX2: RET 0
%0(<4 x s64>) = IMPLICIT_DEF
%1(<4 x s64>) = IMPLICIT_DEF
%2(<4 x s64>) = G_ADD %0, %1
$ymm0 = COPY %2
RET 0
...