Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/X86/znver3-gather.ll
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

116 lines
5.0 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=znver3 | FileCheck %s --check-prefix=X64
define <8 x i32> @simple(ptr %base, <8 x i32> %offsets) {
; X64-LABEL: simple:
; X64: # %bb.0:
; X64-NEXT: vextracti128 $1, %ymm0, %xmm2
; X64-NEXT: vpmovsxdq %xmm0, %ymm0
; X64-NEXT: vmovq %rdi, %xmm1
; X64-NEXT: vpbroadcastq %xmm1, %ymm1
; X64-NEXT: vpmovsxdq %xmm2, %ymm2
; X64-NEXT: vpsllq $2, %ymm0, %ymm0
; X64-NEXT: vpaddq %ymm0, %ymm1, %ymm0
; X64-NEXT: vmovq %xmm0, %rax
; X64-NEXT: vpextrq $1, %xmm0, %rcx
; X64-NEXT: vextracti128 $1, %ymm0, %xmm0
; X64-NEXT: vpsllq $2, %ymm2, %ymm2
; X64-NEXT: vpaddq %ymm2, %ymm1, %ymm2
; X64-NEXT: vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X64-NEXT: vpextrq $1, %xmm0, %rdx
; X64-NEXT: vmovq %xmm0, %rsi
; X64-NEXT: vextracti128 $1, %ymm2, %xmm0
; X64-NEXT: vmovq %xmm2, %rdi
; X64-NEXT: vpextrq $1, %xmm2, %r8
; X64-NEXT: vpinsrd $1, (%rcx), %xmm1, %xmm1
; X64-NEXT: vmovq %xmm0, %r9
; X64-NEXT: vpextrq $1, %xmm0, %r10
; X64-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: vpinsrd $2, (%rsi), %xmm1, %xmm1
; X64-NEXT: vpinsrd $1, (%r8), %xmm0, %xmm0
; X64-NEXT: vpinsrd $3, (%rdx), %xmm1, %xmm1
; X64-NEXT: vpinsrd $2, (%r9), %xmm0, %xmm0
; X64-NEXT: vpinsrd $3, (%r10), %xmm0, %xmm0
; X64-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; X64-NEXT: retq
%ptrs = getelementptr inbounds i32, ptr %base, <8 x i32> %offsets
%wide.masked.gather = call <8 x i32> @llvm.masked.gather.v8i32.v8p0(<8 x ptr> %ptrs, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> undef)
ret <8 x i32> %wide.masked.gather
}
define <8 x i32> @optsize(ptr %base, <8 x i32> %offsets) optsize {
; X64-LABEL: optsize:
; X64: # %bb.0:
; X64-NEXT: vextracti128 $1, %ymm0, %xmm2
; X64-NEXT: vpmovsxdq %xmm0, %ymm0
; X64-NEXT: vmovq %rdi, %xmm1
; X64-NEXT: vpbroadcastq %xmm1, %ymm1
; X64-NEXT: vpmovsxdq %xmm2, %ymm2
; X64-NEXT: vpsllq $2, %ymm0, %ymm0
; X64-NEXT: vpaddq %ymm0, %ymm1, %ymm0
; X64-NEXT: vmovq %xmm0, %rax
; X64-NEXT: vpextrq $1, %xmm0, %rcx
; X64-NEXT: vextracti128 $1, %ymm0, %xmm0
; X64-NEXT: vpsllq $2, %ymm2, %ymm2
; X64-NEXT: vpaddq %ymm2, %ymm1, %ymm2
; X64-NEXT: vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X64-NEXT: vpextrq $1, %xmm0, %rdx
; X64-NEXT: vmovq %xmm0, %rsi
; X64-NEXT: vextracti128 $1, %ymm2, %xmm0
; X64-NEXT: vmovq %xmm2, %rdi
; X64-NEXT: vpextrq $1, %xmm2, %r8
; X64-NEXT: vpinsrd $1, (%rcx), %xmm1, %xmm1
; X64-NEXT: vmovq %xmm0, %r9
; X64-NEXT: vpextrq $1, %xmm0, %r10
; X64-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: vpinsrd $2, (%rsi), %xmm1, %xmm1
; X64-NEXT: vpinsrd $1, (%r8), %xmm0, %xmm0
; X64-NEXT: vpinsrd $3, (%rdx), %xmm1, %xmm1
; X64-NEXT: vpinsrd $2, (%r9), %xmm0, %xmm0
; X64-NEXT: vpinsrd $3, (%r10), %xmm0, %xmm0
; X64-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; X64-NEXT: retq
%ptrs = getelementptr inbounds i32, ptr %base, <8 x i32> %offsets
%wide.masked.gather = call <8 x i32> @llvm.masked.gather.v8i32.v8p0(<8 x ptr> %ptrs, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> undef)
ret <8 x i32> %wide.masked.gather
}
define <8 x i32> @minsize(ptr %base, <8 x i32> %offsets) minsize {
; X64-LABEL: minsize:
; X64: # %bb.0:
; X64-NEXT: vextracti128 $1, %ymm0, %xmm2
; X64-NEXT: vpmovsxdq %xmm0, %ymm0
; X64-NEXT: vmovq %rdi, %xmm1
; X64-NEXT: vpbroadcastq %xmm1, %ymm1
; X64-NEXT: vpmovsxdq %xmm2, %ymm2
; X64-NEXT: vpsllq $2, %ymm0, %ymm0
; X64-NEXT: vpaddq %ymm0, %ymm1, %ymm0
; X64-NEXT: vmovq %xmm0, %rax
; X64-NEXT: vpextrq $1, %xmm0, %rcx
; X64-NEXT: vextracti128 $1, %ymm0, %xmm0
; X64-NEXT: vpsllq $2, %ymm2, %ymm2
; X64-NEXT: vpaddq %ymm2, %ymm1, %ymm2
; X64-NEXT: vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X64-NEXT: vpextrq $1, %xmm0, %rdx
; X64-NEXT: vmovq %xmm0, %rsi
; X64-NEXT: vextracti128 $1, %ymm2, %xmm0
; X64-NEXT: vmovq %xmm2, %rdi
; X64-NEXT: vpextrq $1, %xmm2, %r8
; X64-NEXT: vpinsrd $1, (%rcx), %xmm1, %xmm1
; X64-NEXT: vmovq %xmm0, %r9
; X64-NEXT: vpextrq $1, %xmm0, %r10
; X64-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: vpinsrd $2, (%rsi), %xmm1, %xmm1
; X64-NEXT: vpinsrd $1, (%r8), %xmm0, %xmm0
; X64-NEXT: vpinsrd $3, (%rdx), %xmm1, %xmm1
; X64-NEXT: vpinsrd $2, (%r9), %xmm0, %xmm0
; X64-NEXT: vpinsrd $3, (%r10), %xmm0, %xmm0
; X64-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; X64-NEXT: retq
%ptrs = getelementptr inbounds i32, ptr %base, <8 x i32> %offsets
%wide.masked.gather = call <8 x i32> @llvm.masked.gather.v8i32.v8p0(<8 x ptr> %ptrs, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> undef)
ret <8 x i32> %wide.masked.gather
}
declare <8 x i32> @llvm.masked.gather.v8i32.v8p0(<8 x ptr>, i32 immarg, <8 x i1>, <8 x i32>)