Add support for bottom-up SLP vectorization infrastructure.

This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations.
The infrastructure has three potential users:

  1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]).

  2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute.

  3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization.

This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code:

void SAXPY(int *x, int *y, int a, int i) {
  x[i]   = a * x[i]   + y[i];
  x[i+1] = a * x[i+1] + y[i+1];
  x[i+2] = a * x[i+2] + y[i+2];
  x[i+3] = a * x[i+3] + y[i+3];
}

llvm-svn: 179117

1 files changed, 25 insertions, 0 deletions

diff --git a/llvm/test/Transforms/SLPVectorizer/X86/simplebb.ll b/llvm/test/Transforms/SLPVectorizer/X86/simplebb.ll
new file mode 100644
index 00000000000..0af30ab2bb1
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/X86/simplebb.ll
@@ -0,0 +1,25 @@
+; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | 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"
+
+; Simple 3-pair chain with loads and stores
+; CHECK: test1
+; CHECK: store <2 x double>
+; CHECK: ret
+define void @test1(double* %a, double* %b, double* %c) nounwind uwtable readonly {
+entry:
+  %i0 = load double* %a, align 8
+  %i1 = load double* %b, align 8
+  %mul = fmul double %i0, %i1
+  %arrayidx3 = getelementptr inbounds double* %a, i64 1
+  %i3 = load double* %arrayidx3, align 8
+  %arrayidx4 = getelementptr inbounds double* %b, i64 1
+  %i4 = load double* %arrayidx4, align 8
+  %mul5 = fmul double %i3, %i4
+  store double %mul, double* %c, align 8
+  %arrayidx5 = getelementptr inbounds double* %c, i64 1
+  store double %mul5, double* %arrayidx5, align 8
+  ret void
+}
+