diff options
| author | Dan Gohman <dan433584@gmail.com> | 2017-12-20 01:36:25 +0000 |
|---|---|---|
| committer | Dan Gohman <dan433584@gmail.com> | 2017-12-20 01:36:25 +0000 |
| commit | aa3922819e1e80ccf7cf7e8bf61e86cd240b056b (patch) | |
| tree | c6ffcd1acc31d099209cb806ad09855822edb34a /llvm/test/Transforms/MemCpyOpt/mixed-sizes.ll | |
| parent | b1ae03fd6141a5511b6de6bc600b29a476b7ee70 (diff) | |
| download | bcm5719-llvm-aa3922819e1e80ccf7cf7e8bf61e86cd240b056b.tar.gz bcm5719-llvm-aa3922819e1e80ccf7cf7e8bf61e86cd240b056b.zip | |
[memcpyopt] Teach memcpyopt to optimize across basic blocks
This teaches memcpyopt to make a non-local memdep query when a local query
indicates that the dependency is non-local. This notably allows it to
eliminate many more llvm.memcpy calls in common Rust code, often by 20-30%.
This is r319482 and r319483, along with fixes for PR35519: fix the
optimization that merges stores into memsets to preserve cached memdep
info, and fix memdep's non-local caching strategy to not assume that larger
queries are always more conservative than smaller ones.
Fixes PR28958 and PR35519.
Differential Revision: https://reviews.llvm.org/D40802
llvm-svn: 321138
Diffstat (limited to 'llvm/test/Transforms/MemCpyOpt/mixed-sizes.ll')
| -rw-r--r-- | llvm/test/Transforms/MemCpyOpt/mixed-sizes.ll | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/llvm/test/Transforms/MemCpyOpt/mixed-sizes.ll b/llvm/test/Transforms/MemCpyOpt/mixed-sizes.ll new file mode 100644 index 00000000000..9091fe7f56c --- /dev/null +++ b/llvm/test/Transforms/MemCpyOpt/mixed-sizes.ll @@ -0,0 +1,36 @@ +; RUN: opt < %s -memcpyopt -S | FileCheck %s +; Handle memcpy-memcpy dependencies of differing sizes correctly. + +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" + +; Don't delete the second memcpy, even though there's an earlier +; memcpy with a larger size from the same address. + +; CHECK-LABEL: @foo +define i32 @foo(i1 %z) { +entry: + %a = alloca [10 x i32] + %s = alloca [10 x i32] + %0 = bitcast [10 x i32]* %a to i8* + %1 = bitcast [10 x i32]* %s to i8* + call void @llvm.memset.p0i8.i64(i8* nonnull %1, i8 0, i64 40, i32 16, i1 false) + %arrayidx = getelementptr inbounds [10 x i32], [10 x i32]* %a, i64 0, i64 0 + store i32 1, i32* %arrayidx + %scevgep = getelementptr [10 x i32], [10 x i32]* %s, i64 0, i64 1 + %scevgep7 = bitcast i32* %scevgep to i8* + br i1 %z, label %for.body3.lr.ph, label %for.inc7.1 + +for.body3.lr.ph: ; preds = %entry + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %scevgep7, i64 17179869180, i32 4, i1 false) + br label %for.inc7.1 + +for.inc7.1: +; CHECK: for.inc7.1: + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %scevgep7, i64 4, i32 4, i1 false) +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %scevgep7, i64 4, i32 4, i1 false) + %2 = load i32, i32* %arrayidx + ret i32 %2 +} + +declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i32, i1) +declare void @llvm.memset.p0i8.i64(i8*, i8, i64, i32, i1) |
