RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-27 15:02:16 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

LoopVectorize: Math functions only read rounding mode

Browse Source 
Math functions are mark as readonly because they read the floating point
rounding mode. Because we don't vectorize loops that would contain function
calls that set the rounding mode it is safe to ignore this memory read.

llvm-svn: 185299
This commit is contained in:
Arnold Schwaighofer 2013-07-01 00:54:44 +00:00
parent 8a53bf61f4
commit 26461b04c7
2 changed files with 39 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -3520,6 +3520,13 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
// but is not a load, then we quit. Notice that we don't handle function
// calls that read or write.
if (it->mayReadFromMemory()) {
// Many math library functions read the rounding mode. We will only
// vectorize a loop if it contains known function calls that don't set
// the flag. Therefore, it is safe to ignore this read from memory.
CallInst *Call = dyn_cast<CallInst>(it);
if (Call && getIntrinsicIDForCall(Call, TLI))
continue;
LoadInst *Ld = dyn_cast<LoadInst>(it);
if (!Ld) return false;
if (!Ld->isSimple() && !IsAnnotatedParallel) {

32
test/Transforms/LoopVectorize/funcall.ll Normal file
View File

@ -0,0 +1,32 @@
; RUN: opt -S -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 < %s | 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"
; Make sure we can vectorize loops with functions to math library functions.
; They might read the rounding mode but we are only vectorizing loops that
; contain a limited set of function calls and none of them sets the rounding
; mode, so vectorizing them is safe.
; CHECK: test
; CHECK: <2 x double>
define void @test(double* %d, double %t) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds double* %d, i64 %indvars.iv
%0 = load double* %arrayidx, align 8
%1 = tail call double @llvm.pow.f64(double %0, double %t)
store double %1, double* %arrayidx, align 8
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 128
br i1 %exitcond, label %for.body, label %for.end
for.end:
ret void
}
declare double @llvm.pow.f64(double, double)