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

196 lines
6.7 KiB
Plaintext
Raw Normal View History

# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+sse2 -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=NOVL --check-prefix=SSE2
# 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=NOVL --check-prefix=AVX1
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f,+avx512vl -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f,+avx512vl,+avx512bw -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX512BWVL
--- |
define <16 x i8> @test_add_v16i8(<16 x i8> %arg1, <16 x i8> %arg2) {
%ret = add <16 x i8> %arg1, %arg2
ret <16 x i8> %ret
}
define <8 x i16> @test_add_v8i16(<8 x i16> %arg1, <8 x i16> %arg2) {
%ret = add <8 x i16> %arg1, %arg2
ret <8 x i16> %ret
}
define <4 x i32> @test_add_v4i32(<4 x i32> %arg1, <4 x i32> %arg2) {
%ret = add <4 x i32> %arg1, %arg2
ret <4 x i32> %ret
}
define <2 x i64> @test_add_v2i64(<2 x i64> %arg1, <2 x i64> %arg2) {
%ret = add <2 x i64> %arg1, %arg2
ret <2 x i64> %ret
}
...
---
name: test_add_v16i8
# ALL-LABEL: name: test_add_v16i8
alignment: 4
legalized: true
regBankSelected: true
# NOVL: registers:
# NOVL-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# NOVL-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# NOVL-NEXT: - { id: 2, class: vr128, preferred-register: '' }
#
# AVX512VL: registers:
# AVX512VL-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# AVX512VL-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# AVX512VL-NEXT: - { id: 2, class: vr128, preferred-register: '' }
#
# AVX512BWVL: registers:
# AVX512BWVL-NEXT: - { id: 0, class: vr128x, preferred-register: '' }
# AVX512BWVL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512BWVL-NEXT: - { id: 2, class: vr128x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# SSE2: %2 = PADDBrr %0, %1
#
# AVX1: %2 = VPADDBrr %0, %1
#
# AVX512VL: %2 = VPADDBrr %0, %1
#
# AVX512BWVL: %2 = VPADDBZ128rr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %xmm0, %xmm1
%0(<16 x s8>) = COPY %xmm0
%1(<16 x s8>) = COPY %xmm1
%2(<16 x s8>) = G_ADD %0, %1
%xmm0 = COPY %2(<16 x s8>)
RET 0, implicit %xmm0
...
---
name: test_add_v8i16
# ALL-LABEL: name: test_add_v8i16
alignment: 4
legalized: true
regBankSelected: true
# NOVL: registers:
# NOVL-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# NOVL-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# NOVL-NEXT: - { id: 2, class: vr128, preferred-register: '' }
#
# AVX512VL: registers:
# AVX512VL-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# AVX512VL-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# AVX512VL-NEXT: - { id: 2, class: vr128, preferred-register: '' }
#
# AVX512BWVL: registers:
# AVX512BWVL-NEXT: - { id: 0, class: vr128x, preferred-register: '' }
# AVX512BWVL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512BWVL-NEXT: - { id: 2, class: vr128x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# SSE2: %2 = PADDWrr %0, %1
#
# AVX1: %2 = VPADDWrr %0, %1
#
# AVX512VL: %2 = VPADDWrr %0, %1
#
# AVX512BWVL: %2 = VPADDWZ128rr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %xmm0, %xmm1
%0(<8 x s16>) = COPY %xmm0
%1(<8 x s16>) = COPY %xmm1
%2(<8 x s16>) = G_ADD %0, %1
%xmm0 = COPY %2(<8 x s16>)
RET 0, implicit %xmm0
...
---
name: test_add_v4i32
# ALL-LABEL: name: test_add_v4i32
alignment: 4
legalized: true
regBankSelected: true
# NOVL: registers:
# NOVL-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# NOVL-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# NOVL-NEXT: - { id: 2, class: vr128, preferred-register: '' }
#
# AVX512VL: registers:
# AVX512VL-NEXT: - { id: 0, class: vr128x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 2, class: vr128x, preferred-register: '' }
#
# AVX512BWVL: registers:
# AVX512BWVL-NEXT: - { id: 0, class: vr128x, preferred-register: '' }
# AVX512BWVL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512BWVL-NEXT: - { id: 2, class: vr128x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# SSE2: %2 = PADDDrr %0, %1
#
# AVX1: %2 = VPADDDrr %0, %1
#
# AVX512VL: %2 = VPADDDZ128rr %0, %1
#
# AVX512BWVL: %2 = VPADDDZ128rr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %xmm0, %xmm1
%0(<4 x s32>) = COPY %xmm0
%1(<4 x s32>) = COPY %xmm1
%2(<4 x s32>) = G_ADD %0, %1
%xmm0 = COPY %2(<4 x s32>)
RET 0, implicit %xmm0
...
---
name: test_add_v2i64
# ALL-LABEL: name: test_add_v2i64
alignment: 4
legalized: true
regBankSelected: true
# NOVL: registers:
# NOVL-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# NOVL-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# NOVL-NEXT: - { id: 2, class: vr128, preferred-register: '' }
#
# AVX512VL: registers:
# AVX512VL-NEXT: - { id: 0, class: vr128x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 2, class: vr128x, preferred-register: '' }
#
# AVX512BWVL: registers:
# AVX512BWVL-NEXT: - { id: 0, class: vr128x, preferred-register: '' }
# AVX512BWVL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512BWVL-NEXT: - { id: 2, class: vr128x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# SSE2: %2 = PADDQrr %0, %1
#
# AVX1: %2 = VPADDQrr %0, %1
#
# AVX512VL: %2 = VPADDQZ128rr %0, %1
#
# AVX512BWVL: %2 = VPADDQZ128rr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %xmm0, %xmm1
%0(<2 x s64>) = COPY %xmm0
%1(<2 x s64>) = COPY %xmm1
%2(<2 x s64>) = G_ADD %0, %1
%xmm0 = COPY %2(<2 x s64>)
RET 0, implicit %xmm0
...