mirror of
https://github.com/RPCSX/llvm.git
synced 2024-12-13 23:18:51 +00:00
b893afb0a5
Reappy r284044 after revert in r284051. Krzysztof fixed the error in r284049.
The original summary:
This patch tries to fully unroll loops having break statement like this
for (int i = 0; i < 8; i++) {
if (a[i] == value) {
found = true;
break;
}
}
GCC can fully unroll such loops, but currently LLVM cannot because LLVM only
supports loops having exact constant trip counts.
The upper bound of the trip count can be obtained from calling
ScalarEvolution::getMaxBackedgeTakenCount(). Part of the patch is the
refactoring work in SCEV to prevent duplicating code.
The feature of using the upper bound is enabled under the same circumstance
when runtime unrolling is enabled since both are used to unroll loops without
knowing the exact constant trip count.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@284053 91177308-0d34-0410-b5e6-96231b3b80d8
44 lines
1.2 KiB
LLVM
44 lines
1.2 KiB
LLVM
; RUN: opt -loop-unroll -S -mtriple aarch64 -mcpu=cortex-a57 %s | FileCheck %s -check-prefix=UNROLL
|
|
; RUN: opt -loop-unroll -unroll-max-upperbound=0 -S -mtriple aarch64 -mcpu=cortex-a57 %s | FileCheck %s -check-prefix=NOUNROLL
|
|
|
|
; This IR comes from this C code:
|
|
;
|
|
; for (int i = 0; i < 4; i++) {
|
|
; if (src[i] == 1) {
|
|
; *dst = i;
|
|
; break;
|
|
; }
|
|
; }
|
|
;
|
|
; This test is meant to check that this loop is unrolled into four iterations.
|
|
|
|
; UNROLL-LABEL: @test
|
|
; UNROLL: load i32, i32*
|
|
; UNROLL: load i32, i32*
|
|
; UNROLL: load i32, i32*
|
|
; UNROLL: load i32, i32*
|
|
; UNROLL-NOT: load i32, i32*
|
|
; NOUNROLL-LABEL: @test
|
|
; NOUNROLL: load i32, i32*
|
|
; NOUNROLL-NOT: load i32, i32*
|
|
|
|
define void @test(i32* %dst, i32* %src) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %entry, %for.body
|
|
%i = phi i32 [ 0, %entry ], [ %inc, %for.body ]
|
|
%0 = sext i32 %i to i64
|
|
%1 = getelementptr inbounds i32, i32* %src, i64 %0
|
|
%2 = load i32, i32* %1
|
|
%inc = add nsw i32 %i, 1
|
|
%cmp1 = icmp slt i32 %inc, 4
|
|
%cmp3 = icmp eq i32 %2, 1
|
|
%or.cond = and i1 %cmp3, %cmp1
|
|
br i1 %or.cond, label %for.body, label %exit
|
|
|
|
exit: ; preds = %for.body
|
|
store i32 %i, i32* %dst
|
|
ret void
|
|
}
|