Files
clang-p2996/llvm/test/Transforms/SLPVectorizer/X86/reduced-value-replace-extractelement.ll
Alexey Bataev b10ecfa914 [SLP]Represent externally used values as original scalars, if profitable.
Currently SLP vectorizer tries to keep only GEPs as scalar, if they are
vectorized but used externally. Same approach can be used for all scalar
values. This patch tries to keep original scalars if all its operands
remain scalar or externally used, the cost of the original scalar is
lower than the cost of the extractelement instruction, or if the number
of externally used scalars in the same entry is power of 2. Last
criterion allows better revectorization for multiply used scalars.

Reviewers: RKSimon

Reviewed By: RKSimon

Pull Request: https://github.com/llvm/llvm-project/pull/100904
2024-08-12 10:15:02 -04:00

36 lines
1.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -S --passes=slp-vectorizer -slp-threshold=-99999 < %s -mtriple=x86_64-unknown-linux-gnu | FileCheck %s
define void @test() {
; CHECK-LABEL: define void @test() {
; CHECK-NEXT: [[BB:.*]]:
; CHECK-NEXT: [[TRUNC:%.*]] = trunc i64 0 to i32
; CHECK-NEXT: br label %[[BB1:.*]]
; CHECK: [[BB1]]:
; CHECK-NEXT: [[TMP0:%.*]] = phi <2 x i32> [ zeroinitializer, %[[BB]] ], [ [[TMP4:%.*]], %[[BB1]] ]
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x i32> [[TMP0]], i32 1
; CHECK-NEXT: [[TMP2:%.*]] = call i8 @llvm.vector.reduce.mul.v4i8(<4 x i8> zeroinitializer)
; CHECK-NEXT: [[TMP3:%.*]] = zext i8 [[TMP2]] to i32
; CHECK-NEXT: [[OP_RDX:%.*]] = mul i32 [[TMP3]], [[TMP1]]
; CHECK-NEXT: [[OP_RDX1:%.*]] = mul i32 [[OP_RDX]], [[TRUNC]]
; CHECK-NEXT: [[TMP4]] = insertelement <2 x i32> <i32 0, i32 poison>, i32 [[OP_RDX1]], i32 1
; CHECK-NEXT: br label %[[BB1]]
;
bb:
br label %bb1
bb1:
%phi = phi i32 [ 0, %bb ], [ %mul9, %bb1 ]
%phi2 = phi i32 [ 0, %bb ], [ 0, %bb1 ]
%trunc = trunc i64 0 to i32
%mul = mul i32 0, %trunc
%mul3 = mul i32 %trunc, %phi
%mul4 = mul i32 %mul3, %mul
%mul5 = mul i32 %mul4, %mul
%trunc6 = trunc i64 0 to i32
%mul7 = mul i32 0, %trunc6
%mul8 = mul i32 %mul5, %mul7
%mul9 = mul i32 %mul8, %mul7
br label %bb1
}