From: Justin Holewinski <jholewinski@nvidia.com>
Date: Wed, 23 Jul 2014 17:40:45 +0000 (+0000)
Subject: [NVPTX] Make sure we do not generate MULWIDE ISD nodes when optimizations are disabled
X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=6b50a7d1792217abff02dc30a81aca9c0fdb8cb9;p=oota-llvm.git

[NVPTX] Make sure we do not generate MULWIDE ISD nodes when optimizations are disabled

With optimizations disabled, we disable the isel patterns for mul.wide; but we
were still generating MULWIDE ISD nodes.  Now, we only try to generate MULWIDE
ISD nodes in DAGCombine if the optimization level is not zero.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213773 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/NVPTX/NVPTXISelLowering.cpp b/lib/Target/NVPTX/NVPTXISelLowering.cpp
index 05bad16ddd8..d76b20a29eb 100644
--- a/lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ b/lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -4213,8 +4213,7 @@ static SDValue PerformSHLCombine(SDNode *N,
 
 SDValue NVPTXTargetLowering::PerformDAGCombine(SDNode *N,
                                                DAGCombinerInfo &DCI) const {
-  // FIXME: Get this from the DAG somehow
-  CodeGenOpt::Level OptLevel = CodeGenOpt::Aggressive;
+  CodeGenOpt::Level OptLevel = getTargetMachine().getOptLevel();
   switch (N->getOpcode()) {
     default: break;
     case ISD::ADD:
diff --git a/test/CodeGen/NVPTX/mulwide.ll b/test/CodeGen/NVPTX/mulwide.ll
index 927946c8fb3..43bb63098f6 100644
--- a/test/CodeGen/NVPTX/mulwide.ll
+++ b/test/CodeGen/NVPTX/mulwide.ll
@@ -1,35 +1,44 @@
-; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 -O3 | FileCheck %s --check-prefix=OPT
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 -O0 | FileCheck %s --check-prefix=NOOPT
 
-; CHECK: mulwide16
+; OPT-LABEL: @mulwide16
+; NOOPT-LABEL: @mulwide16
 define i32 @mulwide16(i16 %a, i16 %b) {
-; CHECK: mul.wide.s16
+; OPT: mul.wide.s16
+; NOOPT: mul.lo.s32
   %val0 = sext i16 %a to i32
   %val1 = sext i16 %b to i32
   %val2 = mul i32 %val0, %val1
   ret i32 %val2
 }
 
-; CHECK: mulwideu16
+; OPT-LABEL: @mulwideu16
+; NOOPT-LABEL: @mulwideu16
 define i32 @mulwideu16(i16 %a, i16 %b) {
-; CHECK: mul.wide.u16
+; OPT: mul.wide.u16
+; NOOPT: mul.lo.s32
   %val0 = zext i16 %a to i32
   %val1 = zext i16 %b to i32
   %val2 = mul i32 %val0, %val1
   ret i32 %val2
 }
 
-; CHECK: mulwide32
+; OPT-LABEL: @mulwide32
+; NOOPT-LABEL: @mulwide32
 define i64 @mulwide32(i32 %a, i32 %b) {
-; CHECK: mul.wide.s32
+; OPT: mul.wide.s32
+; NOOPT: mul.lo.s64
   %val0 = sext i32 %a to i64
   %val1 = sext i32 %b to i64
   %val2 = mul i64 %val0, %val1
   ret i64 %val2
 }
 
-; CHECK: mulwideu32
+; OPT-LABEL: @mulwideu32
+; NOOPT-LABEL: @mulwideu32
 define i64 @mulwideu32(i32 %a, i32 %b) {
-; CHECK: mul.wide.u32
+; OPT: mul.wide.u32
+; NOOPT: mul.lo.s64
   %val0 = zext i32 %a to i64
   %val1 = zext i32 %b to i64
   %val2 = mul i64 %val0, %val1