llvm-project/llvm/test/CodeGen/X86/GlobalISel/select-mul-vec.mir

481 lines
14 KiB
Plaintext
Raw Normal View History

# RUN: llc -mtriple=x86_64-linux-gnu -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s
--- |
define <8 x i16> @test_mul_v8i16(<8 x i16> %arg1, <8 x i16> %arg2) #0 {
%ret = mul <8 x i16> %arg1, %arg2
ret <8 x i16> %ret
}
define <8 x i16> @test_mul_v8i16_avx(<8 x i16> %arg1, <8 x i16> %arg2) #1 {
%ret = mul <8 x i16> %arg1, %arg2
ret <8 x i16> %ret
}
define <8 x i16> @test_mul_v8i16_avx512bwvl(<8 x i16> %arg1, <8 x i16> %arg2) #2 {
%ret = mul <8 x i16> %arg1, %arg2
ret <8 x i16> %ret
}
define <4 x i32> @test_mul_v4i32(<4 x i32> %arg1, <4 x i32> %arg2) #3 {
%ret = mul <4 x i32> %arg1, %arg2
ret <4 x i32> %ret
}
define <4 x i32> @test_mul_v4i32_avx(<4 x i32> %arg1, <4 x i32> %arg2) #1 {
%ret = mul <4 x i32> %arg1, %arg2
ret <4 x i32> %ret
}
define <4 x i32> @test_mul_v4i32_avx512vl(<4 x i32> %arg1, <4 x i32> %arg2) #4 {
%ret = mul <4 x i32> %arg1, %arg2
ret <4 x i32> %ret
}
define <2 x i64> @test_mul_v2i64(<2 x i64> %arg1, <2 x i64> %arg2) #5 {
%ret = mul <2 x i64> %arg1, %arg2
ret <2 x i64> %ret
}
define <16 x i16> @test_mul_v16i16(<16 x i16> %arg1, <16 x i16> %arg2) #6 {
%ret = mul <16 x i16> %arg1, %arg2
ret <16 x i16> %ret
}
define <16 x i16> @test_mul_v16i16_avx512bwvl(<16 x i16> %arg1, <16 x i16> %arg2) #2 {
%ret = mul <16 x i16> %arg1, %arg2
ret <16 x i16> %ret
}
define <8 x i32> @test_mul_v8i32(<8 x i32> %arg1, <8 x i32> %arg2) #6 {
%ret = mul <8 x i32> %arg1, %arg2
ret <8 x i32> %ret
}
define <8 x i32> @test_mul_v8i32_avx512vl(<8 x i32> %arg1, <8 x i32> %arg2) #4 {
%ret = mul <8 x i32> %arg1, %arg2
ret <8 x i32> %ret
}
define <4 x i64> @test_mul_v4i64(<4 x i64> %arg1, <4 x i64> %arg2) #5 {
%ret = mul <4 x i64> %arg1, %arg2
ret <4 x i64> %ret
}
define <32 x i16> @test_mul_v32i16(<32 x i16> %arg1, <32 x i16> %arg2) #7 {
%ret = mul <32 x i16> %arg1, %arg2
ret <32 x i16> %ret
}
define <16 x i32> @test_mul_v16i32(<16 x i32> %arg1, <16 x i32> %arg2) #8 {
%ret = mul <16 x i32> %arg1, %arg2
ret <16 x i32> %ret
}
define <8 x i64> @test_mul_v8i64(<8 x i64> %arg1, <8 x i64> %arg2) #9 {
%ret = mul <8 x i64> %arg1, %arg2
ret <8 x i64> %ret
}
attributes #0 = { "target-features"="+sse2" }
attributes #1 = { "target-features"="+avx" }
attributes #2 = { "target-features"="+avx512vl,+avx512f,+avx512bw" }
attributes #3 = { "target-features"="+sse4.1" }
attributes #4 = { "target-features"="+avx512vl,+avx512f" }
attributes #5 = { "target-features"="+avx2,+avx512vl,+avx512f,+avx512dq" }
attributes #6 = { "target-features"="+avx2" }
attributes #7 = { "target-features"="+avx512f,+avx512bw" }
attributes #8 = { "target-features"="+avx512f" }
attributes #9 = { "target-features"="+avx512f,+avx512dq" }
...
---
name: test_mul_v8i16
# CHECK-LABEL: name: test_mul_v8i16
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr128, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = PMULLWrr %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_MUL %0, %1
%xmm0 = COPY %2(<8 x s16>)
RET 0, implicit %xmm0
...
---
name: test_mul_v8i16_avx
# CHECK-LABEL: name: test_mul_v8i16_avx
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr128, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLWrr %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_MUL %0, %1
%xmm0 = COPY %2(<8 x s16>)
RET 0, implicit %xmm0
...
---
name: test_mul_v8i16_avx512bwvl
# CHECK-LABEL: name: test_mul_v8i16_avx512bwvl
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr128x, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr128x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLWZ128rr %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_MUL %0, %1
%xmm0 = COPY %2(<8 x s16>)
RET 0, implicit %xmm0
...
---
name: test_mul_v4i32
# CHECK-LABEL: name: test_mul_v4i32
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr128, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = PMULLDrr %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_MUL %0, %1
%xmm0 = COPY %2(<4 x s32>)
RET 0, implicit %xmm0
...
---
name: test_mul_v4i32_avx
# CHECK-LABEL: name: test_mul_v4i32_avx
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr128, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr128, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLDrr %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_MUL %0, %1
%xmm0 = COPY %2(<4 x s32>)
RET 0, implicit %xmm0
...
---
name: test_mul_v4i32_avx512vl
# CHECK-LABEL: name: test_mul_v4i32_avx512vl
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr128x, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr128x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLDZ128rr %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_MUL %0, %1
%xmm0 = COPY %2(<4 x s32>)
RET 0, implicit %xmm0
...
---
name: test_mul_v2i64
# CHECK-LABEL: name: test_mul_v2i64
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr128x, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr128x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLQZ128rr %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_MUL %0, %1
%xmm0 = COPY %2(<2 x s64>)
RET 0, implicit %xmm0
...
---
name: test_mul_v16i16
# CHECK-LABEL: name: test_mul_v16i16
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr256, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr256, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr256, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLWYrr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<16 x s16>) = COPY %ymm0
%1(<16 x s16>) = COPY %ymm1
%2(<16 x s16>) = G_MUL %0, %1
%ymm0 = COPY %2(<16 x s16>)
RET 0, implicit %ymm0
...
---
name: test_mul_v16i16_avx512bwvl
# CHECK-LABEL: name: test_mul_v16i16_avx512bwvl
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr256x, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr256x, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr256x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLWZ256rr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<16 x s16>) = COPY %ymm0
%1(<16 x s16>) = COPY %ymm1
%2(<16 x s16>) = G_MUL %0, %1
%ymm0 = COPY %2(<16 x s16>)
RET 0, implicit %ymm0
...
---
name: test_mul_v8i32
# CHECK-LABEL: name: test_mul_v8i32
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr256, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr256, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr256, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLDYrr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<8 x s32>) = COPY %ymm0
%1(<8 x s32>) = COPY %ymm1
%2(<8 x s32>) = G_MUL %0, %1
%ymm0 = COPY %2(<8 x s32>)
RET 0, implicit %ymm0
...
---
name: test_mul_v8i32_avx512vl
# CHECK-LABEL: name: test_mul_v8i32_avx512vl
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr256x, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr256x, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr256x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLDZ256rr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<8 x s32>) = COPY %ymm0
%1(<8 x s32>) = COPY %ymm1
%2(<8 x s32>) = G_MUL %0, %1
%ymm0 = COPY %2(<8 x s32>)
RET 0, implicit %ymm0
...
---
name: test_mul_v4i64
# CHECK-LABEL: name: test_mul_v4i64
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr256x, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr256x, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr256x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLQZ256rr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<4 x s64>) = COPY %ymm0
%1(<4 x s64>) = COPY %ymm1
%2(<4 x s64>) = G_MUL %0, %1
%ymm0 = COPY %2(<4 x s64>)
RET 0, implicit %ymm0
...
---
name: test_mul_v32i16
# CHECK-LABEL: name: test_mul_v32i16
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr512, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr512, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLWZrr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %zmm0, %zmm1
%0(<32 x s16>) = COPY %zmm0
%1(<32 x s16>) = COPY %zmm1
%2(<32 x s16>) = G_MUL %0, %1
%zmm0 = COPY %2(<32 x s16>)
RET 0, implicit %zmm0
...
---
name: test_mul_v16i32
# CHECK-LABEL: name: test_mul_v16i32
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr512, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr512, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLDZrr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %zmm0, %zmm1
%0(<16 x s32>) = COPY %zmm0
%1(<16 x s32>) = COPY %zmm1
%2(<16 x s32>) = G_MUL %0, %1
%zmm0 = COPY %2(<16 x s32>)
RET 0, implicit %zmm0
...
---
name: test_mul_v8i64
# CHECK-LABEL: name: test_mul_v8i64
alignment: 4
legalized: true
regBankSelected: true
# CHECK: registers:
# CHECK-NEXT: - { id: 0, class: vr512, preferred-register: '' }
# CHECK-NEXT: - { id: 1, class: vr512, preferred-register: '' }
# CHECK-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# CHECK: %2 = VPMULLQZrr %0, %1
body: |
bb.1 (%ir-block.0):
liveins: %zmm0, %zmm1
%0(<8 x s64>) = COPY %zmm0
%1(<8 x s64>) = COPY %zmm1
%2(<8 x s64>) = G_MUL %0, %1
%zmm0 = COPY %2(<8 x s64>)
RET 0, implicit %zmm0
...