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
41 lines
1.8 KiB
LLVM
41 lines
1.8 KiB
LLVM
; RUN: opt -S -loop-reduce < %s | FileCheck %s
|
|
; Complex addressing mode are costly.
|
|
; Make loop-reduce prefer unscaled accesses.
|
|
; On X86, reg1 + 1*reg2 has the same cost as reg1 + 8*reg2.
|
|
; Therefore, LSR currently prefers to fold as much computation as possible
|
|
; in the addressing mode.
|
|
; <rdar://problem/16730541>
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx"
|
|
|
|
define void @mulDouble(ptr nocapture %a, ptr nocapture %b, ptr nocapture %c) {
|
|
; CHECK: @mulDouble
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
; CHECK: [[IV:%[^ ]+]] = phi i64 [ [[IVNEXT:%[^,]+]], %for.body ], [ 0, %entry ]
|
|
; Only one induction variable should have been generated.
|
|
; CHECK-NOT: phi
|
|
%indvars.iv = phi i64 [ 1, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%tmp = add nsw i64 %indvars.iv, -1
|
|
%arrayidx = getelementptr inbounds double, ptr %b, i64 %tmp
|
|
%tmp1 = load double, ptr %arrayidx, align 8
|
|
; The induction variable should carry the scaling factor: 1.
|
|
; CHECK: [[IVNEXT]] = add nuw nsw i64 [[IV]], 1
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%arrayidx2 = getelementptr inbounds double, ptr %c, i64 %indvars.iv.next
|
|
%tmp2 = load double, ptr %arrayidx2, align 8
|
|
%mul = fmul double %tmp1, %tmp2
|
|
%arrayidx4 = getelementptr inbounds double, ptr %a, i64 %indvars.iv
|
|
store double %mul, ptr %arrayidx4, align 8
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
; Comparison should be 19 * 1 = 19.
|
|
; CHECK: icmp eq i32 {{%[^,]+}}, 19
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 20
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|