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
60 lines
2.5 KiB
LLVM
60 lines
2.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=arm64-eabi -aarch64-neon-syntax=apple | FileCheck %s
|
|
|
|
; DAGCombine to transform a conversion of an extract_vector_elt to an
|
|
; extract_vector_elt of a conversion, which saves a round trip of copies
|
|
; of the value to a GPR and back to and FPR.
|
|
; rdar://11855286
|
|
define double @foo0(<2 x i64> %a) nounwind {
|
|
; CHECK-LABEL: foo0:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: scvtf.2d v0, v0, #9
|
|
; CHECK-NEXT: mov d0, v0[1]
|
|
; CHECK-NEXT: ret
|
|
%vecext = extractelement <2 x i64> %a, i32 1
|
|
%fcvt_n = tail call double @llvm.aarch64.neon.vcvtfxs2fp.f64.i64(i64 %vecext, i32 9)
|
|
ret double %fcvt_n
|
|
}
|
|
|
|
define double @bar(ptr %iVals, ptr %fVals, ptr %dVals) {
|
|
; CHECK-LABEL: bar:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ldr d0, [x2, #128]
|
|
; CHECK-NEXT: frinti d0, d0
|
|
; CHECK-NEXT: fcvtzs d0, d0
|
|
; CHECK-NEXT: sri d0, d0, #1
|
|
; CHECK-NEXT: scvtf.2d v0, v0, #1
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%arrayidx = getelementptr inbounds double, ptr %dVals, i64 16
|
|
%0 = load <1 x double>, ptr %arrayidx, align 8
|
|
%vrndi_v1.i = call <1 x double> @llvm.nearbyint.v1f64(<1 x double> %0)
|
|
%vget_lane = extractelement <1 x double> %vrndi_v1.i, i64 0
|
|
%vcvtd_s64_f64.i = call i64 @llvm.aarch64.neon.fcvtzs.i64.f64(double %vget_lane)
|
|
%1 = insertelement <1 x i64> poison, i64 %vcvtd_s64_f64.i, i64 0
|
|
%vsrid_n_s647 = call <1 x i64> @llvm.aarch64.neon.vsri.v1i64(<1 x i64> %1, <1 x i64> %1, i32 1)
|
|
%2 = extractelement <1 x i64> %vsrid_n_s647, i64 0
|
|
%vcvtd_n_f64_s64 = call double @llvm.aarch64.neon.vcvtfxs2fp.f64.i64(i64 %2, i32 1)
|
|
ret double %vcvtd_n_f64_s64
|
|
}
|
|
|
|
define float @do_stuff(<8 x i16> noundef %var_135) {
|
|
; CHECK-LABEL: do_stuff:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: umaxv.8h h0, v0
|
|
; CHECK-NEXT: ucvtf s0, s0, #1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%vmaxv.i = call i32 @llvm.aarch64.neon.umaxv.i32.v8i16(<8 x i16> %var_135) #2
|
|
%vcvts_n_f32_u32 = call float @llvm.aarch64.neon.vcvtfxu2fp.f32.i32(i32 %vmaxv.i, i32 1)
|
|
ret float %vcvts_n_f32_u32
|
|
}
|
|
|
|
declare <1 x i64> @llvm.aarch64.neon.vsri.v1i64(<1 x i64>, <1 x i64>, i32)
|
|
declare double @llvm.aarch64.neon.vcvtfxs2fp.f64.i64(i64, i32)
|
|
declare <1 x double> @llvm.nearbyint.v1f64(<1 x double>)
|
|
declare i64 @llvm.aarch64.neon.fcvtzs.i64.f64(double)
|
|
declare i32 @llvm.aarch64.neon.umaxv.i32.v8i16(<8 x i16>) #1
|
|
declare float @llvm.aarch64.neon.vcvtfxu2fp.f32.i32(i32, i32) #1
|