; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load float, ptr %in0, align 4" --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v0 = load float, float\* %in0, align 4"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
; REQUIRES: asserts
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x float] zeroinitializer, align 128
@B = global [1024 x i8] zeroinitializer, align 128
define void @test() {
; CHECK-LABEL: 'test'
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, ptr %in0, align 4
; CHECK: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load float, ptr %in0, align 4
; CHECK: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load float, ptr %in0, align 4
; CHECK: LV: Found an estimated cost of 3 for VF 8 For instruction: %v0 = load float, ptr %in0, align 4
; CHECK: LV: Found an estimated cost of 5 for VF 16 For instruction: %v0 = load float, ptr %in0, align 4
; CHECK: LV: Found an estimated cost of 22 for VF 32 For instruction: %v0 = load float, ptr %in0, align 4
; CHECK: LV: Found an estimated cost of 92 for VF 64 For instruction: %v0 = load float, ptr %in0, align 4
;
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%iv.0 = add nuw nsw i64 %iv, 0
%iv.1 = add nuw nsw i64 %iv, 1
%in0 = getelementptr inbounds [1024 x float], ptr @A, i64 0, i64 %iv.0
%in1 = getelementptr inbounds [1024 x float], ptr @A, i64 0, i64 %iv.1
%v0 = load float, ptr %in0
%v1 = load float, ptr %in1
%reduce.add.0 = fadd float %v0, %v1
%reduce.add.0.narrow = fptoui float %reduce.add.0 to i8
%out = getelementptr inbounds [1024 x i8], ptr @B, i64 0, i64 %iv.0
store i8 %reduce.add.0.narrow, ptr %out
%iv.next = add nuw nsw i64 %iv.0, 2
%cmp = icmp ult i64 %iv.next, 1024
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
ret void
}
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; AVX512: {{.*}}
Codebase Browser
llvm