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
50 lines
2.4 KiB
LLVM
50 lines
2.4 KiB
LLVM
; REQUIRES: asserts
|
|
; RUN: llc -mtriple=hexagon -mcpu=hexagonv5 -disable-hsdr --stats -o - 2>&1 < %s | FileCheck %s
|
|
|
|
; Check that store is post-incremented.
|
|
; CHECK-NOT: extractu(r{{[0-9]+}},#32,
|
|
; CHECK-NOT: insert
|
|
; CHECK-NOT: Number of node order issues found
|
|
; CHECK: Number of loops software pipelined
|
|
; CHECK-NOT: Number of node order issues found
|
|
target datalayout = "e-p:32:32:32-i64:64:64-i32:32:32-i16:16:16-i1:32:32-f64:64:64-f32:32:32-v64:64:64-v32:32:32-a0:0-n16:32"
|
|
target triple = "hexagon"
|
|
|
|
define i32 @foo(ptr noalias nocapture %src, ptr noalias nocapture %dstImg, i32 %width, i32 %idx, i32 %flush) #0 {
|
|
entry:
|
|
%0 = tail call i64 @llvm.hexagon.A2.combinew(i32 %flush, i32 %flush)
|
|
%1 = bitcast i64 %0 to <2 x i32>
|
|
br label %polly.loop_body
|
|
|
|
polly.loop_after: ; preds = %polly.loop_body
|
|
ret i32 0
|
|
|
|
polly.loop_body: ; preds = %entry, %polly.loop_body
|
|
%p_arrayidx35.phi = phi ptr [ %dstImg, %entry ], [ %p_arrayidx35.inc, %polly.loop_body ]
|
|
%p_arrayidx.phi = phi ptr [ %src, %entry ], [ %p_arrayidx.inc, %polly.loop_body ]
|
|
%polly.loopiv56 = phi i32 [ 0, %entry ], [ %polly.next_loopiv, %polly.loop_body ]
|
|
%polly.next_loopiv = add nsw i32 %polly.loopiv56, 4
|
|
%_p_vec_full = load <4 x i16>, ptr %p_arrayidx.phi, align 2
|
|
%_high_half = shufflevector <4 x i16> %_p_vec_full, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
|
|
%_low_half = shufflevector <4 x i16> %_p_vec_full, <4 x i16> undef, <2 x i32> <i32 0, i32 1>
|
|
%2 = zext <2 x i16> %_low_half to <2 x i32>
|
|
%3 = zext <2 x i16> %_high_half to <2 x i32>
|
|
%add33p_vec = add <2 x i32> %2, %1
|
|
%add33p_vec48 = add <2 x i32> %3, %1
|
|
%4 = trunc <2 x i32> %add33p_vec to <2 x i16>
|
|
%5 = trunc <2 x i32> %add33p_vec48 to <2 x i16>
|
|
%_combined_vec = shufflevector <2 x i16> %4, <2 x i16> %5, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
store <4 x i16> %_combined_vec, ptr %p_arrayidx35.phi, align 2
|
|
%6 = icmp slt i32 %polly.next_loopiv, 1024
|
|
%p_arrayidx35.inc = getelementptr i16, ptr %p_arrayidx35.phi, i32 4
|
|
%p_arrayidx.inc = getelementptr i16, ptr %p_arrayidx.phi, i32 4
|
|
br i1 %6, label %polly.loop_body, label %polly.loop_after
|
|
}
|
|
|
|
declare i64 @llvm.hexagon.A2.combinew(i32, i32) #1
|
|
|
|
attributes #0 = { nounwind "less-precise-fpmad"="false" "frame-pointer"="non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "use-soft-float"="false" }
|
|
attributes #1 = { nounwind readnone }
|
|
|
|
|