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
36 lines
1.3 KiB
LLVM
36 lines
1.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s
|
|
|
|
; FIXME: Currently, we avoid narrowing this v4i32 load, in the
|
|
; hopes of being able to fold the shift, despite it requiring stack
|
|
; storage + loads. Ideally, we should narrow here and load the i32
|
|
; directly from the variable offset e.g:
|
|
;
|
|
; add x8, x0, x1, lsl #4
|
|
; and x9, x2, #0x3
|
|
; ldr w0, [x8, x9, lsl #2]
|
|
;
|
|
; The AArch64TargetLowering::shouldReduceLoadWidth heuristic should
|
|
; probably be updated to choose load-narrowing instead of folding the
|
|
; lsl in larger vector cases.
|
|
;
|
|
define i32 @narrow_load_v4_i32_single_ele_variable_idx(ptr %ptr, i64 %off, i32 %ele) {
|
|
; CHECK-LABEL: narrow_load_v4_i32_single_ele_variable_idx:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: ldr q0, [x0, x1, lsl #4]
|
|
; CHECK-NEXT: mov x8, sp
|
|
; CHECK-NEXT: // kill: def $w2 killed $w2 def $x2
|
|
; CHECK-NEXT: bfi x8, x2, #2, #2
|
|
; CHECK-NEXT: str q0, [sp]
|
|
; CHECK-NEXT: ldr w0, [x8]
|
|
; CHECK-NEXT: add sp, sp, #16
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%idx = getelementptr inbounds <4 x i32>, ptr %ptr, i64 %off
|
|
%x = load <4 x i32>, ptr %idx, align 8
|
|
%res = extractelement <4 x i32> %x, i32 %ele
|
|
ret i32 %res
|
|
}
|