Begin incorporating target information into BBVectorize.

This is the first of several steps to incorporate information from the new
TargetTransformInfo infrastructure into BBVectorize. Two things are done here:

 1. Target information is used to determine if it is profitable to fuse two
    instructions. This means that the cost of the vector operation must not
    be more expensive than the cost of the two original operations. Pairs that
    are not profitable are no longer considered (because current cost information
    is incomplete, for intrinsics for example, equal-cost pairs are still
    considered).

 2. The 'cost savings' computed for the profitability check are also used to
    rank the DAGs that represent the potential vectorization plans. Specifically,
    for nodes of non-trivial depth, the cost savings is used as the node
    weight.

The next step will be to incorporate the shuffle costs into the DAG weighting;
this will give the edges of the DAG weights as well. Once that is done, when
target information is available, we should be able to dispense with the
depth heuristic.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166716 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 10 insertions, 0 deletions

diff --git a/test/Transforms/BBVectorize/loop1.ll b/test/Transforms/BBVectorize/loop1.ll
index bebc91ad91..a30af5091f 100644
--- a/test/Transforms/BBVectorize/loop1.ll
+++ b/test/Transforms/BBVectorize/loop1.ll
@@ -1,8 +1,11 @@
 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-unknown-linux-gnu"
 ; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s
 ; RUN: opt < %s -basicaa -loop-unroll -unroll-threshold=45 -unroll-allow-partial -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-UNRL
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -basicaa -loop-unroll -unroll-threshold=45 -unroll-allow-partial -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-UNRL
 ; The second check covers the use of alias analysis (with loop unrolling).
+; Both checks are run with and without target information.
 
 define void @test1(double* noalias %out, double* noalias %in1, double* noalias %in2) nounwind uwtable {
 entry:
diff --git a/test/Transforms/BBVectorize/simple.ll b/test/Transforms/BBVectorize/simple.ll
index 88eb9c90f7..702796b57d 100644
--- a/test/Transforms/BBVectorize/simple.ll
+++ b/test/Transforms/BBVectorize/simple.ll
@@ -1,5 +1,6 @@
 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"
 ; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-TI
 
 ; Basic depth-3 chain
 define double @test1(double %A1, double %A2, double %B1, double %B2) {
@@ -23,6 +24,9 @@ define double @test1(double %A1, double %A2, double %B1, double %B2) {
 ; CHECK: %R = fmul double %Z1.v.r1, %Z1.v.r2
 	ret double %R
 ; CHECK: ret double %R
+; CHECK-TI: @test1
+; CHECK-TI: fsub <2 x double>
+; CHECK-TI: ret double
 }
 
 ; Basic depth-3 chain (last pair permuted)
@@ -146,6 +150,9 @@ define <8 x i8> @test6(<8 x i8> %A1, <8 x i8> %A2, <8 x i8> %B1, <8 x i8> %B2) {
 ; CHECK: %R = mul <8 x i8> %Q1.v.r1, %Q1.v.r2
 	ret <8 x i8> %R
 ; CHECK: ret <8 x i8> %R
+; CHECK-TI: @test6
+; CHECK-TI-NOT: sub <16 x i8>
+; CHECK-TI: ret <8 x i8>
 }