[vectorizer] Add an override for the target instruction cost and use it

to stabilize a test that really is trying to test generic behavior and
not a specific target's behavior.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200215 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index 1ba0b77503e59c17d08bfa168c9864908e293e0d..750fc40d261534dc632ef2fe1eb06a560d9b2232 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -160,6 +160,12 @@ static cl::opt<unsigned> ForceTargetMaxVectorUnrollFactor(
     cl::desc("A flag that overrides the target's max unroll factor for "
              "vectorized loops."));
 
+static cl::opt<unsigned> ForceTargetInstructionCost(
+    "force-target-instruction-cost", cl::init(0), cl::Hidden,
+    cl::desc("A flag that overrides the target's expected cost for "
+             "an instruction to a single constant value. Mostly "
+             "useful for getting consistent testing."));
+
 static cl::opt<unsigned> SmallLoopCost(
     "small-loop-cost", cl::init(20), cl::Hidden,
     cl::desc("The cost of a loop that is considered 'small' by the unroller."));
@@ -5185,6 +5191,11 @@ unsigned LoopVectorizationCostModel::expectedCost(unsigned VF) {
         continue;
 
       unsigned C = getInstructionCost(it, VF);
+
+      // Check if we should override the cost.
+      if (ForceTargetInstructionCost.getNumOccurrences() > 0)
+        C = ForceTargetInstructionCost;
+
       BlockCost += C;
       DEBUG(dbgs() << "LV: Found an estimated cost of " << C << " for VF " <<
             VF << " For instruction: " << *it << '\n');

diff --git a/test/Transforms/LoopVectorize/unroll_novec.ll b/test/Transforms/LoopVectorize/unroll_novec.ll
index be5bbb68e65bfc4f8989d43cc64c372d863db380..89f4678526de23041b6f04c3367f9bdaff59efb3 100644 (file)
--- a/test/Transforms/LoopVectorize/unroll_novec.ll
+++ b/test/Transforms/LoopVectorize/unroll_novec.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s  -loop-vectorize -force-vector-width=1 -force-target-num-scalar-regs=16 -force-target-max-scalar-unroll=8 -small-loop-cost=20 -dce -instcombine -S | FileCheck %s
+; RUN: opt < %s  -loop-vectorize -force-vector-width=1 -force-target-num-scalar-regs=16 -force-target-max-scalar-unroll=8 -force-target-instruction-cost=1 -small-loop-cost=40 -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"