diff options
author | Nadav Rotem <nrotem@apple.com> | 2013-08-26 22:33:26 +0000 |
---|---|---|
committer | Nadav Rotem <nrotem@apple.com> | 2013-08-26 22:33:26 +0000 |
commit | 4bf6326d0871961a7402c797a0399a2bdaf53574 (patch) | |
tree | ab31e87a17bcdc7dfaf8359ce931dfa0c88d5c41 /test/Transforms/LoopVectorize/unroll_novec.ll | |
parent | 03be5e5b6e2d604313df5b7758bffcf5b0bb0ef0 (diff) | |
download | external_llvm-4bf6326d0871961a7402c797a0399a2bdaf53574.zip external_llvm-4bf6326d0871961a7402c797a0399a2bdaf53574.tar.gz external_llvm-4bf6326d0871961a7402c797a0399a2bdaf53574.tar.bz2 |
LoopVectorize: Implement partial loop unrolling when vectorization is not profitable.
This patch enables unrolling of loops when vectorization is legal but not profitable.
We add a new class InnerLoopUnroller, that extends InnerLoopVectorizer and replaces some of the vector-specific logic with scalars.
This patch does not introduce any runtime regressions and improves the following workloads:
SingleSource/Benchmarks/Shootout/matrix -22.64%
SingleSource/Benchmarks/Shootout-C++/matrix -13.06%
External/SPEC/CINT2006/464_h264ref/464_h264ref -3.99%
SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding -1.95%
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189281 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/LoopVectorize/unroll_novec.ll')
-rw-r--r-- | test/Transforms/LoopVectorize/unroll_novec.ll | 39 |
1 files changed, 39 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/unroll_novec.ll b/test/Transforms/LoopVectorize/unroll_novec.ll new file mode 100644 index 0000000..33f128d --- /dev/null +++ b/test/Transforms/LoopVectorize/unroll_novec.ll @@ -0,0 +1,39 @@ +; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-vector-unroll=2 -dce -instcombine -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" +target triple = "x86_64-apple-macosx10.8.0" + +@a = common global [2048 x i32] zeroinitializer, align 16 + +; This is the loop. +; for (i=0; i<n; i++){ +; a[i] += i; +; } +;CHECK-LABEL: @inc( +;CHECK: load i32* +;CHECK: load i32* +;CHECK: add nsw i32 +;CHECK: add nsw i32 +;CHECK: store i32 +;CHECK: store i32 +;CHECK: ret void +define void @inc(i32 %n) nounwind uwtable noinline ssp { + %1 = icmp sgt i32 %n, 0 + br i1 %1, label %.lr.ph, label %._crit_edge + +.lr.ph: ; preds = %0, %.lr.ph + %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ] + %2 = getelementptr inbounds [2048 x i32]* @a, i64 0, i64 %indvars.iv + %3 = load i32* %2, align 4 + %4 = trunc i64 %indvars.iv to i32 + %5 = add nsw i32 %3, %4 + store i32 %5, i32* %2, align 4 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %._crit_edge, label %.lr.ph + +._crit_edge: ; preds = %.lr.ph, %0 + ret void +} + |