forked from OSchip/llvm-project
246 lines
11 KiB
YAML
246 lines
11 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx -global-isel -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX1
|
|
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f -global-isel -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX512F
|
|
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f,+avx512bw -global-isel -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX512BW
|
|
|
|
--- |
|
|
define void @test_add_v64i8() {
|
|
%ret = add <64 x i8> undef, undef
|
|
ret void
|
|
}
|
|
|
|
define void @test_add_v32i16() {
|
|
%ret = add <32 x i16> undef, undef
|
|
ret void
|
|
}
|
|
|
|
define void @test_add_v16i32() {
|
|
%ret = add <16 x i32> undef, undef
|
|
ret void
|
|
}
|
|
|
|
define void @test_add_v8i64() {
|
|
%ret = add <8 x i64> undef, undef
|
|
ret void
|
|
}
|
|
|
|
define <64 x i8> @test_add_v64i8_2(<64 x i8> %arg1, <64 x i8> %arg2) #0 {
|
|
%ret = add <64 x i8> %arg1, %arg2
|
|
ret <64 x i8> %ret
|
|
}
|
|
...
|
|
---
|
|
name: test_add_v64i8
|
|
alignment: 4
|
|
legalized: false
|
|
regBankSelected: false
|
|
registers:
|
|
- { id: 0, class: _ }
|
|
- { id: 1, class: _ }
|
|
- { id: 2, class: _ }
|
|
body: |
|
|
bb.1 (%ir-block.0):
|
|
liveins: $zmm0, $zmm1
|
|
|
|
; ALL-LABEL: name: test_add_v64i8
|
|
; ALL: [[DEF:%[0-9]+]]:_(<64 x s8>) = IMPLICIT_DEF
|
|
; ALL: [[DEF1:%[0-9]+]]:_(<64 x s8>) = IMPLICIT_DEF
|
|
; AVX1: [[UV:%[0-9]+]]:_(<16 x s8>), [[UV1:%[0-9]+]]:_(<16 x s8>), [[UV2:%[0-9]+]]:_(<16 x s8>), [[UV3:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF]](<64 x s8>)
|
|
; AVX1: [[UV4:%[0-9]+]]:_(<16 x s8>), [[UV5:%[0-9]+]]:_(<16 x s8>), [[UV6:%[0-9]+]]:_(<16 x s8>), [[UV7:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF1]](<64 x s8>)
|
|
; AVX1: [[ADD:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV]], [[UV4]]
|
|
; AVX1: [[ADD1:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV1]], [[UV5]]
|
|
; AVX1: [[ADD2:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV2]], [[UV6]]
|
|
; AVX1: [[ADD3:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV3]], [[UV7]]
|
|
; AVX1: [[MV:%[0-9]+]]:_(<64 x s8>) = G_MERGE_VALUES [[ADD]](<16 x s8>), [[ADD1]](<16 x s8>), [[ADD2]](<16 x s8>), [[ADD3]](<16 x s8>)
|
|
; AVX1: $zmm0 = COPY [[MV]](<64 x s8>)
|
|
; AVX512F: [[UV:%[0-9]+]]:_(<32 x s8>), [[UV1:%[0-9]+]]:_(<32 x s8>) = G_UNMERGE_VALUES [[DEF]](<64 x s8>)
|
|
; AVX512F: [[UV2:%[0-9]+]]:_(<32 x s8>), [[UV3:%[0-9]+]]:_(<32 x s8>) = G_UNMERGE_VALUES [[DEF1]](<64 x s8>)
|
|
; AVX512F: [[ADD:%[0-9]+]]:_(<32 x s8>) = G_ADD [[UV]], [[UV2]]
|
|
; AVX512F: [[ADD1:%[0-9]+]]:_(<32 x s8>) = G_ADD [[UV1]], [[UV3]]
|
|
; AVX512F: [[MV:%[0-9]+]]:_(<64 x s8>) = G_MERGE_VALUES [[ADD]](<32 x s8>), [[ADD1]](<32 x s8>)
|
|
; AVX512F: $zmm0 = COPY [[MV]](<64 x s8>)
|
|
; AVX512BW: [[ADD:%[0-9]+]]:_(<64 x s8>) = G_ADD [[DEF]], [[DEF1]]
|
|
; AVX512BW: $zmm0 = COPY [[ADD]](<64 x s8>)
|
|
; ALL: RET 0
|
|
%0(<64 x s8>) = IMPLICIT_DEF
|
|
%1(<64 x s8>) = IMPLICIT_DEF
|
|
%2(<64 x s8>) = G_ADD %0, %1
|
|
$zmm0 = COPY %2
|
|
RET 0
|
|
|
|
...
|
|
---
|
|
name: test_add_v32i16
|
|
alignment: 4
|
|
legalized: false
|
|
regBankSelected: false
|
|
registers:
|
|
- { id: 0, class: _ }
|
|
- { id: 1, class: _ }
|
|
- { id: 2, class: _ }
|
|
body: |
|
|
bb.1 (%ir-block.0):
|
|
liveins: $zmm0, $zmm1
|
|
|
|
; ALL-LABEL: name: test_add_v32i16
|
|
; ALL: [[DEF:%[0-9]+]]:_(<32 x s16>) = IMPLICIT_DEF
|
|
; ALL: [[DEF1:%[0-9]+]]:_(<32 x s16>) = IMPLICIT_DEF
|
|
; AVX1: [[UV:%[0-9]+]]:_(<8 x s16>), [[UV1:%[0-9]+]]:_(<8 x s16>), [[UV2:%[0-9]+]]:_(<8 x s16>), [[UV3:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF]](<32 x s16>)
|
|
; AVX1: [[UV4:%[0-9]+]]:_(<8 x s16>), [[UV5:%[0-9]+]]:_(<8 x s16>), [[UV6:%[0-9]+]]:_(<8 x s16>), [[UV7:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF1]](<32 x s16>)
|
|
; AVX1: [[ADD:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV]], [[UV4]]
|
|
; AVX1: [[ADD1:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV1]], [[UV5]]
|
|
; AVX1: [[ADD2:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV2]], [[UV6]]
|
|
; AVX1: [[ADD3:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV3]], [[UV7]]
|
|
; AVX1: [[MV:%[0-9]+]]:_(<32 x s16>) = G_MERGE_VALUES [[ADD]](<8 x s16>), [[ADD1]](<8 x s16>), [[ADD2]](<8 x s16>), [[ADD3]](<8 x s16>)
|
|
; AVX1: $zmm0 = COPY [[MV]](<32 x s16>)
|
|
; AVX512F: [[UV:%[0-9]+]]:_(<16 x s16>), [[UV1:%[0-9]+]]:_(<16 x s16>) = G_UNMERGE_VALUES [[DEF]](<32 x s16>)
|
|
; AVX512F: [[UV2:%[0-9]+]]:_(<16 x s16>), [[UV3:%[0-9]+]]:_(<16 x s16>) = G_UNMERGE_VALUES [[DEF1]](<32 x s16>)
|
|
; AVX512F: [[ADD:%[0-9]+]]:_(<16 x s16>) = G_ADD [[UV]], [[UV2]]
|
|
; AVX512F: [[ADD1:%[0-9]+]]:_(<16 x s16>) = G_ADD [[UV1]], [[UV3]]
|
|
; AVX512F: [[MV:%[0-9]+]]:_(<32 x s16>) = G_MERGE_VALUES [[ADD]](<16 x s16>), [[ADD1]](<16 x s16>)
|
|
; AVX512F: $zmm0 = COPY [[MV]](<32 x s16>)
|
|
; AVX512BW: [[ADD:%[0-9]+]]:_(<32 x s16>) = G_ADD [[DEF]], [[DEF1]]
|
|
; AVX512BW: $zmm0 = COPY [[ADD]](<32 x s16>)
|
|
; ALL: RET 0
|
|
%0(<32 x s16>) = IMPLICIT_DEF
|
|
%1(<32 x s16>) = IMPLICIT_DEF
|
|
%2(<32 x s16>) = G_ADD %0, %1
|
|
$zmm0 = COPY %2
|
|
RET 0
|
|
|
|
...
|
|
---
|
|
name: test_add_v16i32
|
|
alignment: 4
|
|
legalized: false
|
|
regBankSelected: false
|
|
registers:
|
|
- { id: 0, class: _ }
|
|
- { id: 1, class: _ }
|
|
- { id: 2, class: _ }
|
|
body: |
|
|
bb.1 (%ir-block.0):
|
|
liveins: $zmm0, $zmm1
|
|
|
|
; ALL-LABEL: name: test_add_v16i32
|
|
; ALL: [[DEF:%[0-9]+]]:_(<16 x s32>) = IMPLICIT_DEF
|
|
; ALL: [[DEF1:%[0-9]+]]:_(<16 x s32>) = IMPLICIT_DEF
|
|
; AVX1: [[UV:%[0-9]+]]:_(<4 x s32>), [[UV1:%[0-9]+]]:_(<4 x s32>), [[UV2:%[0-9]+]]:_(<4 x s32>), [[UV3:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF]](<16 x s32>)
|
|
; AVX1: [[UV4:%[0-9]+]]:_(<4 x s32>), [[UV5:%[0-9]+]]:_(<4 x s32>), [[UV6:%[0-9]+]]:_(<4 x s32>), [[UV7:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF1]](<16 x s32>)
|
|
; AVX1: [[ADD:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV]], [[UV4]]
|
|
; AVX1: [[ADD1:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV1]], [[UV5]]
|
|
; AVX1: [[ADD2:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV2]], [[UV6]]
|
|
; AVX1: [[ADD3:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV3]], [[UV7]]
|
|
; AVX1: [[MV:%[0-9]+]]:_(<16 x s32>) = G_MERGE_VALUES [[ADD]](<4 x s32>), [[ADD1]](<4 x s32>), [[ADD2]](<4 x s32>), [[ADD3]](<4 x s32>)
|
|
; AVX1: $zmm0 = COPY [[MV]](<16 x s32>)
|
|
; AVX512F: [[ADD:%[0-9]+]]:_(<16 x s32>) = G_ADD [[DEF]], [[DEF1]]
|
|
; AVX512F: $zmm0 = COPY [[ADD]](<16 x s32>)
|
|
; AVX512BW: [[ADD:%[0-9]+]]:_(<16 x s32>) = G_ADD [[DEF]], [[DEF1]]
|
|
; AVX512BW: $zmm0 = COPY [[ADD]](<16 x s32>)
|
|
; ALL: RET 0
|
|
%0(<16 x s32>) = IMPLICIT_DEF
|
|
%1(<16 x s32>) = IMPLICIT_DEF
|
|
%2(<16 x s32>) = G_ADD %0, %1
|
|
$zmm0 = COPY %2
|
|
RET 0
|
|
|
|
...
|
|
---
|
|
name: test_add_v8i64
|
|
alignment: 4
|
|
legalized: false
|
|
regBankSelected: false
|
|
registers:
|
|
- { id: 0, class: _ }
|
|
- { id: 1, class: _ }
|
|
- { id: 2, class: _ }
|
|
body: |
|
|
bb.1 (%ir-block.0):
|
|
liveins: $zmm0, $zmm1
|
|
|
|
; ALL-LABEL: name: test_add_v8i64
|
|
; ALL: [[DEF:%[0-9]+]]:_(<8 x s64>) = IMPLICIT_DEF
|
|
; ALL: [[DEF1:%[0-9]+]]:_(<8 x s64>) = IMPLICIT_DEF
|
|
; AVX1: [[UV:%[0-9]+]]:_(<2 x s64>), [[UV1:%[0-9]+]]:_(<2 x s64>), [[UV2:%[0-9]+]]:_(<2 x s64>), [[UV3:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF]](<8 x s64>)
|
|
; AVX1: [[UV4:%[0-9]+]]:_(<2 x s64>), [[UV5:%[0-9]+]]:_(<2 x s64>), [[UV6:%[0-9]+]]:_(<2 x s64>), [[UV7:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF1]](<8 x s64>)
|
|
; AVX1: [[ADD:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV]], [[UV4]]
|
|
; AVX1: [[ADD1:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV1]], [[UV5]]
|
|
; AVX1: [[ADD2:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV2]], [[UV6]]
|
|
; AVX1: [[ADD3:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV3]], [[UV7]]
|
|
; AVX1: [[MV:%[0-9]+]]:_(<8 x s64>) = G_MERGE_VALUES [[ADD]](<2 x s64>), [[ADD1]](<2 x s64>), [[ADD2]](<2 x s64>), [[ADD3]](<2 x s64>)
|
|
; AVX1: $zmm0 = COPY [[MV]](<8 x s64>)
|
|
; AVX512F: [[ADD:%[0-9]+]]:_(<8 x s64>) = G_ADD [[DEF]], [[DEF1]]
|
|
; AVX512F: $zmm0 = COPY [[ADD]](<8 x s64>)
|
|
; AVX512BW: [[ADD:%[0-9]+]]:_(<8 x s64>) = G_ADD [[DEF]], [[DEF1]]
|
|
; AVX512BW: $zmm0 = COPY [[ADD]](<8 x s64>)
|
|
; ALL: RET 0
|
|
%0(<8 x s64>) = IMPLICIT_DEF
|
|
%1(<8 x s64>) = IMPLICIT_DEF
|
|
%2(<8 x s64>) = G_ADD %0, %1
|
|
$zmm0 = COPY %2
|
|
RET 0
|
|
|
|
...
|
|
---
|
|
name: test_add_v64i8_2
|
|
alignment: 4
|
|
legalized: false
|
|
regBankSelected: false
|
|
registers:
|
|
- { id: 0, class: _ }
|
|
- { id: 1, class: _ }
|
|
- { id: 2, class: _ }
|
|
- { id: 3, class: _ }
|
|
- { id: 4, class: _ }
|
|
- { id: 5, class: _ }
|
|
- { id: 6, class: _ }
|
|
- { id: 7, class: _ }
|
|
- { id: 8, class: _ }
|
|
#
|
|
#
|
|
body: |
|
|
bb.1 (%ir-block.0):
|
|
liveins: $ymm0, $ymm1, $ymm2, $ymm3
|
|
|
|
; ALL-LABEL: name: test_add_v64i8_2
|
|
; ALL: [[COPY:%[0-9]+]]:_(<32 x s8>) = COPY $ymm0
|
|
; ALL: [[COPY1:%[0-9]+]]:_(<32 x s8>) = COPY $ymm1
|
|
; ALL: [[COPY2:%[0-9]+]]:_(<32 x s8>) = COPY $ymm2
|
|
; ALL: [[COPY3:%[0-9]+]]:_(<32 x s8>) = COPY $ymm3
|
|
; AVX1: [[UV:%[0-9]+]]:_(<16 x s8>), [[UV1:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[COPY]](<32 x s8>)
|
|
; AVX1: [[UV2:%[0-9]+]]:_(<16 x s8>), [[UV3:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[COPY1]](<32 x s8>)
|
|
; AVX1: [[UV4:%[0-9]+]]:_(<16 x s8>), [[UV5:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[COPY2]](<32 x s8>)
|
|
; AVX1: [[UV6:%[0-9]+]]:_(<16 x s8>), [[UV7:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[COPY3]](<32 x s8>)
|
|
; AVX1: [[ADD:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV]], [[UV4]]
|
|
; AVX1: [[ADD1:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV1]], [[UV5]]
|
|
; AVX1: [[ADD2:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV2]], [[UV6]]
|
|
; AVX1: [[ADD3:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV3]], [[UV7]]
|
|
; AVX1: [[MV:%[0-9]+]]:_(<32 x s8>) = G_MERGE_VALUES [[ADD]](<16 x s8>), [[ADD1]](<16 x s8>)
|
|
; AVX1: [[MV1:%[0-9]+]]:_(<32 x s8>) = G_MERGE_VALUES [[ADD2]](<16 x s8>), [[ADD3]](<16 x s8>)
|
|
; AVX1: $ymm0 = COPY [[MV]](<32 x s8>)
|
|
; AVX1: $ymm1 = COPY [[MV1]](<32 x s8>)
|
|
; AVX512F: [[ADD:%[0-9]+]]:_(<32 x s8>) = G_ADD [[COPY]], [[COPY2]]
|
|
; AVX512F: [[ADD1:%[0-9]+]]:_(<32 x s8>) = G_ADD [[COPY1]], [[COPY3]]
|
|
; AVX512F: $ymm0 = COPY [[ADD]](<32 x s8>)
|
|
; AVX512F: $ymm1 = COPY [[ADD1]](<32 x s8>)
|
|
; AVX512BW: [[MV:%[0-9]+]]:_(<64 x s8>) = G_MERGE_VALUES [[COPY]](<32 x s8>), [[COPY1]](<32 x s8>)
|
|
; AVX512BW: [[MV1:%[0-9]+]]:_(<64 x s8>) = G_MERGE_VALUES [[COPY2]](<32 x s8>), [[COPY3]](<32 x s8>)
|
|
; AVX512BW: [[ADD:%[0-9]+]]:_(<64 x s8>) = G_ADD [[MV]], [[MV1]]
|
|
; AVX512BW: [[UV:%[0-9]+]]:_(<32 x s8>), [[UV1:%[0-9]+]]:_(<32 x s8>) = G_UNMERGE_VALUES [[ADD]](<64 x s8>)
|
|
; AVX512BW: $ymm0 = COPY [[UV]](<32 x s8>)
|
|
; AVX512BW: $ymm1 = COPY [[UV1]](<32 x s8>)
|
|
; ALL: RET 0, implicit $ymm0, implicit $ymm1
|
|
%2(<32 x s8>) = COPY $ymm0
|
|
%3(<32 x s8>) = COPY $ymm1
|
|
%4(<32 x s8>) = COPY $ymm2
|
|
%5(<32 x s8>) = COPY $ymm3
|
|
%0(<64 x s8>) = G_MERGE_VALUES %2(<32 x s8>), %3(<32 x s8>)
|
|
%1(<64 x s8>) = G_MERGE_VALUES %4(<32 x s8>), %5(<32 x s8>)
|
|
%6(<64 x s8>) = G_ADD %0, %1
|
|
%7(<32 x s8>), %8(<32 x s8>) = G_UNMERGE_VALUES %6(<64 x s8>)
|
|
$ymm0 = COPY %7(<32 x s8>)
|
|
$ymm1 = COPY %8(<32 x s8>)
|
|
RET 0, implicit $ymm0, implicit $ymm1
|
|
|
|
...
|