LoopVectorize: Add support for write-only loops when the write destination is a single pointer.

Speedup SciMark by 1%

llvm-svn: 167035

2 files changed, 33 insertions, 0 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index ac82a66b805..9e05cacbbe9 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -1348,6 +1348,13 @@ bool LoopVectorizationLegality::canVectorizeMemory(BasicBlock &BB) {
       Reads.push_back(Ptr);
   }
 
+  // If we write (or read-write) to a single destination and there are no
+  // other reads in this loop then is it safe to vectorize.
+  if (ReadWrites.size() == 1 && Reads.size() == 0) {
+    DEBUG(dbgs() << "LV: Found a write-only loop!\n");
+    return true;
+  }
+
   // Now that the pointers are in two lists (Reads and ReadWrites), we
   // can check that there are no conflicts between each of the writes and
   // between the writes to the reads.
diff --git a/llvm/test/Transforms/LoopVectorize/write-only.ll b/llvm/test/Transforms/LoopVectorize/write-only.ll
new file mode 100644
index 00000000000..eb027604134
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/write-only.ll
@@ -0,0 +1,26 @@
+; RUN: opt < %s  -loop-vectorize -force-vector-width=4 -dce -instcombine -licm -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"
+
+;CHECK: @read_mod_write_single_ptr
+;CHECK: load <4 x float>
+;CHECK: ret i32
+define i32 @read_mod_write_single_ptr(float* nocapture %a, i32 %n) nounwind uwtable 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 float* %a, i64 %indvars.iv
+  %3 = load float* %2, align 4
+  %4 = fmul float %3, 3.000000e+00
+  store float %4, float* %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 i32 undef
+}