derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
142 lines
5.9 KiB
LLVM
142 lines
5.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX
|
|
|
|
declare { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32>, <4 x i32>)
|
|
declare { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32>, <4 x i32>)
|
|
|
|
define <4 x i32> @umul_v4i32_0(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: umul_v4i32_0:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> zeroinitializer)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|
|
|
|
define <4 x i32> @umul_v4i32_1(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: umul_v4i32_1:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> <i32 1, i32 1, i32 1, i32 1>)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|
|
|
|
define <4 x i32> @umul_v4i32_2(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: umul_v4i32_2:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpaddd %xmm0, %xmm0, %xmm2
|
|
; AVX-NEXT: vpmaxud %xmm0, %xmm2, %xmm0
|
|
; AVX-NEXT: vpcmpeqd %xmm0, %xmm2, %xmm0
|
|
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> <i32 2, i32 2, i32 2, i32 2>)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|
|
|
|
define <4 x i32> @umul_v4i32_8(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: umul_v4i32_8:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpslld $3, %xmm0, %xmm2
|
|
; AVX-NEXT: vpsrld $3, %xmm2, %xmm3
|
|
; AVX-NEXT: vpcmpeqd %xmm0, %xmm3, %xmm0
|
|
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> <i32 8, i32 8, i32 8, i32 8>)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|
|
|
|
define <4 x i32> @umul_v4i32_2pow31(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: umul_v4i32_2pow31:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpslld $31, %xmm0, %xmm2
|
|
; AVX-NEXT: vpsrld $31, %xmm2, %xmm3
|
|
; AVX-NEXT: vpcmpeqd %xmm0, %xmm3, %xmm0
|
|
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> <i32 2147483648, i32 2147483648, i32 2147483648, i32 2147483648>)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|
|
|
|
define <4 x i32> @smul_v4i32_0(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: smul_v4i32_0:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> zeroinitializer)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|
|
|
|
define <4 x i32> @smul_v4i32_1(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: smul_v4i32_1:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> <i32 1, i32 1, i32 1, i32 1>)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|
|
|
|
define <4 x i32> @smul_v4i32_2(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: smul_v4i32_2:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpaddd %xmm0, %xmm0, %xmm2
|
|
; AVX-NEXT: vpcmpgtd %xmm2, %xmm0, %xmm3
|
|
; AVX-NEXT: vpxor %xmm3, %xmm0, %xmm0
|
|
; AVX-NEXT: vblendvps %xmm0, %xmm1, %xmm2, %xmm0
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> <i32 2, i32 2, i32 2, i32 2>)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|
|
|
|
define <4 x i32> @smul_v4i32_8(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: smul_v4i32_8:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpslld $3, %xmm0, %xmm2
|
|
; AVX-NEXT: vpsrad $3, %xmm2, %xmm3
|
|
; AVX-NEXT: vpcmpeqd %xmm0, %xmm3, %xmm0
|
|
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> <i32 8, i32 8, i32 8, i32 8>)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|
|
|
|
define <4 x i32> @smul_v4i32_2pow31(<4 x i32> %a, <4 x i32> %b) nounwind {
|
|
; AVX-LABEL: smul_v4i32_2pow31:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpslld $31, %xmm0, %xmm2
|
|
; AVX-NEXT: vpsrld $31, %xmm2, %xmm3
|
|
; AVX-NEXT: vpcmpeqd %xmm0, %xmm3, %xmm0
|
|
; AVX-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX-NEXT: retq
|
|
%x = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>)
|
|
%y = extractvalue { <4 x i32>, <4 x i1> } %x, 0
|
|
%z = extractvalue { <4 x i32>, <4 x i1> } %x, 1
|
|
%u = select <4 x i1> %z, <4 x i32> %b, <4 x i32> %y
|
|
ret <4 x i32> %u
|
|
}
|