maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/SLPVectorizer/X86/simplebb.ll

47 lines
1.7 KiB
LLVM
Raw Normal View History

Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } llvm-svn: 179117
2013-04-10 03:44:35 +08:00
; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
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-macosx10.8.0"
; Simple 3-pair chain with loads and stores
; CHECK: test1
; CHECK: store <2 x double>
; CHECK: ret
Remove unused function attributes. llvm-svn: 179476
2013-04-14 13:47:04 +08:00
define void @test1(double* %a, double* %b, double* %c) {
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } llvm-svn: 179117
2013-04-10 03:44:35 +08:00
entry:
%i0 = load double* %a, align 8
%i1 = load double* %b, align 8
%mul = fmul double %i0, %i1
%arrayidx3 = getelementptr inbounds double* %a, i64 1
%i3 = load double* %arrayidx3, align 8
%arrayidx4 = getelementptr inbounds double* %b, i64 1
%i4 = load double* %arrayidx4, align 8
%mul5 = fmul double %i3, %i4
store double %mul, double* %c, align 8
%arrayidx5 = getelementptr inbounds double* %c, i64 1
store double %mul5, double* %arrayidx5, align 8
ret void
}
SLPVectorizer: Make store chain finding more aggressive with GetUnderlyingObject. This recursively strips all GEPs like the existing code. It also handles bitcasts and other operations that do not change the pointer value. llvm-svn: 191847
2013-10-03 03:06:06 +08:00
; Simple 3-pair chain with loads and stores, obfuscated with bitcasts
; CHECK: test2
; CHECK: store <2 x double>
; CHECK: ret
define void @test2(double* %a, double* %b, i8* %e) {
entry:
%i0 = load double* %a, align 8
%i1 = load double* %b, align 8
%mul = fmul double %i0, %i1
%arrayidx3 = getelementptr inbounds double* %a, i64 1
%i3 = load double* %arrayidx3, align 8
%arrayidx4 = getelementptr inbounds double* %b, i64 1
%i4 = load double* %arrayidx4, align 8
%mul5 = fmul double %i3, %i4
%c = bitcast i8* %e to double*
store double %mul, double* %c, align 8
%carrayidx5 = getelementptr inbounds i8* %e, i64 8
%arrayidx5 = bitcast i8* %carrayidx5 to double*
store double %mul5, double* %arrayidx5, align 8
ret void
}