RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00
Code Issues Projects Releases Wiki Activity

This patch builds on top of D13378 to handle constant condition.

Browse Source 
With this patch, clang -O3 optimizes correctly providing > 1000x speedup on this artificial benchmark):

for (a=0; a<n; a++)
    for (b=0; b<n; b++)
        for (c=0; c<n; c++)
            for (d=0; d<n; d++)
                for (e=0; e<n; e++)
                    for (f=0; f<n; f++)
                        x++;
From test-suite/SingleSource/Benchmarks/Shootout/nestedloop.c

Reviewers: sanjoyd

Differential Revision: http://reviews.llvm.org/D13390

From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 249431
This commit is contained in:
Mehdi Amini 2015-10-06 17:19:20 +00:00
parent 0610aa5644
commit 92479849da
2 changed files with 56 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/Analysis/ScalarEvolution.cpp
View File

@ -3904,6 +3904,11 @@ const SCEV *ScalarEvolution::createNodeForSelectOrPHI(Instruction *I,
Value *Cond, Value *Cond,
Value *TrueVal, Value *TrueVal,
Value *FalseVal) { Value *FalseVal) {
// Handle "constant" branch or select. This can occur for instance when a
// loop pass transforms an inner loop and moves on to process the outer loop.
if (auto *CI = dyn_cast<ConstantInt>(Cond))
return getSCEV(CI->isOne() ? TrueVal : FalseVal);
// Try to match some simple smax or umax patterns. // Try to match some simple smax or umax patterns.
auto *ICI = dyn_cast<ICmpInst>(Cond); auto *ICI = dyn_cast<ICmpInst>(Cond);
if (!ICI) if (!ICI)

51
test/Analysis/ScalarEvolution/constant_condition.ll Normal file
View File

@ -0,0 +1,51 @@
; RUN: opt -analyze -scalar-evolution < %s | FileCheck %s
define i32 @branch_true(i32 %x, i32 %y) {
; CHECK-LABEL: Classifying expressions for: @branch_true
entry:
br i1 true, label %add, label %merge
add:
%sum = add i32 %x, %y
br label %merge
merge:
%v = phi i32 [ %sum, %add ], [ %x, %entry ]
; CHECK: %v = phi i32 [ %sum, %add ], [ %x, %entry ]
; CHECK-NEXT: --> (%x + %y) U: full-set S: full-set
ret i32 %v
}
define i32 @branch_false(i32 %x, i32 %y) {
; CHECK-LABEL: Classifying expressions for: @branch_false
entry:
br i1 false, label %add, label %merge
add:
%sum = add i32 %x, %y
br label %merge
merge:
%v = phi i32 [ %sum, %add ], [ %x, %entry ]
; CHECK: %v = phi i32 [ %sum, %add ], [ %x, %entry ]
; CHECK-NEXT: --> %x U: full-set S: full-set
ret i32 %v
}
define i32 @select_true(i32 %x, i32 %y) {
; CHECK-LABEL: Classifying expressions for: @select_true
entry:
%v = select i1 true, i32 %x, i32 %y
; CHECK: %v = select i1 true, i32 %x, i32 %y
; CHECK-NEXT: --> %x U: full-set S: full-set
ret i32 %v
}
define i32 @select_false(i32 %x, i32 %y) {
; CHECK-LABEL: Classifying expressions for: @select_false
entry:
%v = select i1 false, i32 %x, i32 %y
; CHECK: %v = select i1 false, i32 %x, i32 %y
; CHECK-NEXT: --> %y U: full-set S: full-set
ret i32 %v
}