mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-19 17:33:29 +00:00
b89304eb7c
The SLP vectorizer should propagate IR-level optimization hints/flags (nsw, nuw, exact, fast-math) when converting scalar instructions into vectors. But this isn't a simple copy - we need to take the intersection (the logical 'and') of the sets of flags on the scalars. The solution is further complicated because we can have non-uniform (non-SIMD) vector ops after: http://reviews.llvm.org/D4015 http://llvm.org/viewvc/llvm-project?view=revision&revision=211339 The vast majority of changed files are existing tests that were not propagating IR flags, but I've also added a new test file for focused testing of IR flag possibilities. Differential Revision: http://reviews.llvm.org/D5172 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217051 91177308-0d34-0410-b5e6-96231b3b80d8
44 lines
1.6 KiB
LLVM
44 lines
1.6 KiB
LLVM
; RUN: opt < %s -basicaa -slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7-avx | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
;CHECK-LABEL: @powof2div(
|
|
;CHECK: load <4 x i32>*
|
|
;CHECK: add nsw <4 x i32>
|
|
;CHECK: sdiv <4 x i32>
|
|
define void @powof2div(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* noalias nocapture readonly %c){
|
|
entry:
|
|
%0 = load i32* %b, align 4
|
|
%1 = load i32* %c, align 4
|
|
%add = add nsw i32 %1, %0
|
|
%div = sdiv i32 %add, 2
|
|
store i32 %div, i32* %a, align 4
|
|
%arrayidx3 = getelementptr inbounds i32* %b, i64 1
|
|
%2 = load i32* %arrayidx3, align 4
|
|
%arrayidx4 = getelementptr inbounds i32* %c, i64 1
|
|
%3 = load i32* %arrayidx4, align 4
|
|
%add5 = add nsw i32 %3, %2
|
|
%div6 = sdiv i32 %add5, 2
|
|
%arrayidx7 = getelementptr inbounds i32* %a, i64 1
|
|
store i32 %div6, i32* %arrayidx7, align 4
|
|
%arrayidx8 = getelementptr inbounds i32* %b, i64 2
|
|
%4 = load i32* %arrayidx8, align 4
|
|
%arrayidx9 = getelementptr inbounds i32* %c, i64 2
|
|
%5 = load i32* %arrayidx9, align 4
|
|
%add10 = add nsw i32 %5, %4
|
|
%div11 = sdiv i32 %add10, 2
|
|
%arrayidx12 = getelementptr inbounds i32* %a, i64 2
|
|
store i32 %div11, i32* %arrayidx12, align 4
|
|
%arrayidx13 = getelementptr inbounds i32* %b, i64 3
|
|
%6 = load i32* %arrayidx13, align 4
|
|
%arrayidx14 = getelementptr inbounds i32* %c, i64 3
|
|
%7 = load i32* %arrayidx14, align 4
|
|
%add15 = add nsw i32 %7, %6
|
|
%div16 = sdiv i32 %add15, 2
|
|
%arrayidx17 = getelementptr inbounds i32* %a, i64 3
|
|
store i32 %div16, i32* %arrayidx17, align 4
|
|
ret void
|
|
}
|
|
|