summaryrefslogtreecommitdiffstats
path: root/test/Transforms/SimplifyCFG/speculate-store.ll
diff options
context:
space:
mode:
authorArnold Schwaighofer <aschwaighofer@apple.com>2013-04-20 21:42:09 +0000
committerArnold Schwaighofer <aschwaighofer@apple.com>2013-04-20 21:42:09 +0000
commitf7af1987ddcec768d8608d608ce187115510b21d (patch)
tree9abcd078a446043bbe143130b84a9b2e7e09945d /test/Transforms/SimplifyCFG/speculate-store.ll
parent335dd0d1a60b317dd5fed7016e6b29af5d509828 (diff)
downloadexternal_llvm-f7af1987ddcec768d8608d608ce187115510b21d.zip
external_llvm-f7af1987ddcec768d8608d608ce187115510b21d.tar.gz
external_llvm-f7af1987ddcec768d8608d608ce187115510b21d.tar.bz2
SimplifyCFG: If convert single conditional stores
This transformation will transform a conditional store with a preceeding uncondtional store to the same location: a[i] = may-alias with a[i] load if (cond) a[i] = Y into an unconditional store. a[i] = X may-alias with a[i] load tmp = cond ? Y : X; a[i] = tmp We assume that on average the cost of a mispredicted branch is going to be higher than the cost of a second store to the same location, and that the secondary benefits of creating a bigger basic block for other optimizations to work on outway the potential case were the branch would be correctly predicted and the cost of the executing the second store would be noticably reflected in performance. hmmer's execution time improves by 30% on an imac12,2 on ref data sets. With this change we are on par with gcc's performance (gcc also performs this transformation). There was a 1.2 % performance improvement on a ARM swift chip. Other tests in the test-suite+external seem to be mostly uninfluenced in my experiments: This optimization was triggered on 41 tests such that the executable was different before/after the patch. Only 1 out of the 40 tests (dealII) was reproducable below 100% (by about .4%). Given that hmmer benefits so much I believe this to be a fair trade off. I am going to watch performance numbers across the builtbots and will revert this if anything unexpected comes up. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179957 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/SimplifyCFG/speculate-store.ll')
-rw-r--r--test/Transforms/SimplifyCFG/speculate-store.ll83
1 files changed, 83 insertions, 0 deletions
diff --git a/test/Transforms/SimplifyCFG/speculate-store.ll b/test/Transforms/SimplifyCFG/speculate-store.ll
new file mode 100644
index 0000000..57ae91c
--- /dev/null
+++ b/test/Transforms/SimplifyCFG/speculate-store.ll
@@ -0,0 +1,83 @@
+; RUN: opt -simplifycfg -S < %s | FileCheck %s
+
+define void @ifconvertstore(i32 %m, i32* %A, i32* %B, i32 %C, i32 %D) {
+entry:
+ %arrayidx = getelementptr inbounds i32* %B, i64 0
+ %0 = load i32* %arrayidx, align 4
+ %add = add nsw i32 %0, %C
+ %arrayidx2 = getelementptr inbounds i32* %A, i64 0
+
+; First store to the location.
+ store i32 %add, i32* %arrayidx2, align 4
+ %arrayidx4 = getelementptr inbounds i32* %B, i64 1
+ %1 = load i32* %arrayidx4, align 4
+ %add5 = add nsw i32 %1, %D
+ %cmp6 = icmp sgt i32 %add5, %C
+ br i1 %cmp6, label %if.then, label %ret.end
+
+; Make sure we speculate stores like the following one. It is cheap compared to
+; a mispredicated branch.
+; CHECK: @ifconvertstore
+; CHECK: %add5.add = select i1 %cmp6, i32 %add5, i32 %add
+; CHECK: store i32 %add5.add, i32* %arrayidx2, align 4
+if.then:
+ store i32 %add5, i32* %arrayidx2, align 4
+ br label %ret.end
+
+ret.end:
+ ret void
+}
+
+define void @noifconvertstore1(i32 %m, i32* %A, i32* %B, i32 %C, i32 %D) {
+entry:
+ %arrayidx = getelementptr inbounds i32* %B, i64 0
+ %0 = load i32* %arrayidx, align 4
+ %add = add nsw i32 %0, %C
+ %arrayidx2 = getelementptr inbounds i32* %A, i64 0
+
+; Store to a different location.
+ store i32 %add, i32* %arrayidx, align 4
+ %arrayidx4 = getelementptr inbounds i32* %B, i64 1
+ %1 = load i32* %arrayidx4, align 4
+ %add5 = add nsw i32 %1, %D
+ %cmp6 = icmp sgt i32 %add5, %C
+ br i1 %cmp6, label %if.then, label %ret.end
+
+; CHECK: @noifconvertstore1
+; CHECK-NOT: select
+if.then:
+ store i32 %add5, i32* %arrayidx2, align 4
+ br label %ret.end
+
+ret.end:
+ ret void
+}
+
+declare void @unknown_fun()
+
+define void @noifconvertstore2(i32 %m, i32* %A, i32* %B, i32 %C, i32 %D) {
+entry:
+ %arrayidx = getelementptr inbounds i32* %B, i64 0
+ %0 = load i32* %arrayidx, align 4
+ %add = add nsw i32 %0, %C
+ %arrayidx2 = getelementptr inbounds i32* %A, i64 0
+
+; First store to the location.
+ store i32 %add, i32* %arrayidx2, align 4
+ call void @unknown_fun()
+ %arrayidx4 = getelementptr inbounds i32* %B, i64 1
+ %1 = load i32* %arrayidx4, align 4
+ %add5 = add nsw i32 %1, %D
+ %cmp6 = icmp sgt i32 %add5, %C
+ br i1 %cmp6, label %if.then, label %ret.end
+
+; CHECK: @noifconvertstore2
+; CHECK-NOT: select
+if.then:
+ store i32 %add5, i32* %arrayidx2, align 4
+ br label %ret.end
+
+ret.end:
+ ret void
+}
+