Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/Thumb2/LowOverheadLoops/sibling-loops.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

104 lines
4.2 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+lob --verify-machineinstrs %s -o - | FileCheck %s
define arm_aapcs_vfpcc void @test(ptr noalias nocapture readonly %off, ptr noalias nocapture %data, ptr noalias nocapture %dst, i32 %n) {
; CHECK-LABEL: test:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: cmp r3, #1
; CHECK-NEXT: it lt
; CHECK-NEXT: bxlt lr
; CHECK-NEXT: .LBB0_1: @ %for.cond1.preheader.us.preheader
; CHECK-NEXT: push.w {r4, r5, r6, r7, r8, r9, r10, lr}
; CHECK-NEXT: sub.w r9, r1, #2
; CHECK-NEXT: sub.w r8, r0, #2
; CHECK-NEXT: subs r5, r2, #2
; CHECK-NEXT: mov r10, r3
; CHECK-NEXT: lsl.w r12, r3, #1
; CHECK-NEXT: movs r0, #0
; CHECK-NEXT: mov r4, r9
; CHECK-NEXT: .LBB0_2: @ %for.cond1.preheader.us
; CHECK-NEXT: @ =>This Loop Header: Depth=1
; CHECK-NEXT: @ Child Loop BB0_3 Depth 2
; CHECK-NEXT: @ Child Loop BB0_5 Depth 2
; CHECK-NEXT: dls lr, r10
; CHECK-NEXT: mov r6, r8
; CHECK-NEXT: mov r7, r9
; CHECK-NEXT: mov r2, r4
; CHECK-NEXT: .LBB0_3: @ %for.body4.us
; CHECK-NEXT: @ Parent Loop BB0_2 Depth=1
; CHECK-NEXT: @ => This Inner Loop Header: Depth=2
; CHECK-NEXT: ldrh r1, [r6, #2]!
; CHECK-NEXT: ldrh r3, [r7, #2]!
; CHECK-NEXT: add r1, r3
; CHECK-NEXT: strh r1, [r2, #2]!
; CHECK-NEXT: le lr, .LBB0_3
; CHECK-NEXT: @ %bb.4: @ %for.body15.us.preheader
; CHECK-NEXT: @ in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: dls lr, r10
; CHECK-NEXT: mov r6, r8
; CHECK-NEXT: mov r7, r9
; CHECK-NEXT: mov r2, r5
; CHECK-NEXT: .LBB0_5: @ %for.body15.us
; CHECK-NEXT: @ Parent Loop BB0_2 Depth=1
; CHECK-NEXT: @ => This Inner Loop Header: Depth=2
; CHECK-NEXT: ldrh r1, [r6, #2]!
; CHECK-NEXT: ldrh r3, [r7, #2]!
; CHECK-NEXT: add r1, r3
; CHECK-NEXT: strh r1, [r2, #2]!
; CHECK-NEXT: le lr, .LBB0_5
; CHECK-NEXT: @ %bb.6: @ %for.cond.cleanup14.us
; CHECK-NEXT: @ in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: adds r0, #1
; CHECK-NEXT: add r5, r12
; CHECK-NEXT: add r4, r12
; CHECK-NEXT: cmp r0, r10
; CHECK-NEXT: bne .LBB0_2
; CHECK-NEXT: @ %bb.7:
; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, r9, r10, lr}
; CHECK-NEXT: bx lr
entry:
%cmp252 = icmp sgt i32 %n, 0
br i1 %cmp252, label %for.cond1.preheader.us, label %for.cond.cleanup
for.cond1.preheader.us: ; preds = %entry, %for.cond.cleanup14.us
%i.057.us = phi i32 [ %inc29.us, %for.cond.cleanup14.us ], [ 0, %entry ]
%mul.us = mul i32 %i.057.us, %n
br label %for.body4.us
for.cond.cleanup14.us: ; preds = %for.body15.us
%inc29.us = add nuw i32 %i.057.us, 1
%exitcond94 = icmp eq i32 %inc29.us, %n
br i1 %exitcond94, label %for.cond.cleanup, label %for.cond1.preheader.us
for.body15.us: ; preds = %for.body4.us, %for.body15.us
%j10.055.us = phi i32 [ %inc26.us, %for.body15.us ], [ 0, %for.body4.us ]
%arrayidx16.us = getelementptr inbounds i16, ptr %off, i32 %j10.055.us
%0 = load i16, ptr %arrayidx16.us, align 2
%arrayidx18.us = getelementptr inbounds i16, ptr %data, i32 %j10.055.us
%1 = load i16, ptr %arrayidx18.us, align 2
%add20.us = add i16 %1, %0
%add23.us = add i32 %j10.055.us, %mul.us
%arrayidx24.us = getelementptr inbounds i16, ptr %dst, i32 %add23.us
store i16 %add20.us, ptr %arrayidx24.us, align 2
%inc26.us = add nuw nsw i32 %j10.055.us, 1
%exitcond93 = icmp eq i32 %inc26.us, %n
br i1 %exitcond93, label %for.cond.cleanup14.us, label %for.body15.us
for.body4.us: ; preds = %for.body4.us, %for.cond1.preheader.us
%j.053.us = phi i32 [ 0, %for.cond1.preheader.us ], [ %inc.us, %for.body4.us ]
%arrayidx.us = getelementptr inbounds i16, ptr %off, i32 %j.053.us
%2 = load i16, ptr %arrayidx.us, align 2
%arrayidx5.us = getelementptr inbounds i16, ptr %data, i32 %j.053.us
%3 = load i16, ptr %arrayidx5.us, align 2
%add.us = add i16 %3, %2
%add8.us = add i32 %j.053.us, %mul.us
%arrayidx9.us = getelementptr inbounds i16, ptr %data, i32 %add8.us
store i16 %add.us, ptr %arrayidx9.us, align 2
%inc.us = add nuw nsw i32 %j.053.us, 1
%exitcond = icmp eq i32 %inc.us, %n
br i1 %exitcond, label %for.body15.us, label %for.body4.us
for.cond.cleanup: ; preds = %for.cond.cleanup14.us, %entry
ret void
}