[llvm] r213784 - [NVPTX] mul.wide generation works for any smaller integer source types, not just the next smaller power of two

[Justin Holewinski]

Author: jholewinski
Date: Wed Jul 23 13:46:03 2014
New Revision: 213784

URL: http://llvm.org/viewvc/llvm-project?rev=213784&view=rev
Log:
[NVPTX] mul.wide generation works for any smaller integer source types, not just the next smaller power of two

Modified:
    llvm/trunk/lib/Target/NVPTX/NVPTXISelLowering.cpp
    llvm/trunk/test/CodeGen/NVPTX/mulwide.ll

Modified: llvm/trunk/lib/Target/NVPTX/NVPTXISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTXISelLowering.cpp?rev=213784&r1=213783&r2=213784&view=diff
==============================================================================
--- llvm/trunk/lib/Target/NVPTX/NVPTXISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/NVPTX/NVPTXISelLowering.cpp Wed Jul 23 13:46:03 2014
@@ -4053,13 +4053,13 @@ static bool IsMulWideOperandDemotable(SD
   if (Op.getOpcode() == ISD::SIGN_EXTEND ||
       Op.getOpcode() == ISD::SIGN_EXTEND_INREG) {
     EVT OrigVT = Op.getOperand(0).getValueType();
-    if (OrigVT.getSizeInBits() == OptSize) {
+    if (OrigVT.getSizeInBits() <= OptSize) {
       S = Signed;
       return true;
     }
   } else if (Op.getOpcode() == ISD::ZERO_EXTEND) {
     EVT OrigVT = Op.getOperand(0).getValueType();
-    if (OrigVT.getSizeInBits() == OptSize) {
+    if (OrigVT.getSizeInBits() <= OptSize) {
       S = Unsigned;
       return true;
     }

Modified: llvm/trunk/test/CodeGen/NVPTX/mulwide.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/NVPTX/mulwide.ll?rev=213784&r1=213783&r2=213784&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/NVPTX/mulwide.ll (original)
+++ llvm/trunk/test/CodeGen/NVPTX/mulwide.ll Wed Jul 23 13:46:03 2014
@@ -23,6 +23,28 @@ define i32 @mulwideu16(i16 %a, i16 %b) {
   ret i32 %val2
 }
 
+; OPT-LABEL: @mulwide8
+; NOOPT-LABEL: @mulwide8
+define i32 @mulwide8(i8 %a, i8 %b) {
+; OPT: mul.wide.s16
+; NOOPT: mul.lo.s32
+  %val0 = sext i8 %a to i32
+  %val1 = sext i8 %b to i32
+  %val2 = mul i32 %val0, %val1
+  ret i32 %val2
+}
+
+; OPT-LABEL: @mulwideu8
+; NOOPT-LABEL: @mulwideu8
+define i32 @mulwideu8(i8 %a, i8 %b) {
+; OPT: mul.wide.u16
+; NOOPT: mul.lo.s32
+  %val0 = zext i8 %a to i32
+  %val1 = zext i8 %b to i32
+  %val2 = mul i32 %val0, %val1
+  ret i32 %val2
+}
+
 ; OPT-LABEL: @mulwide32
 ; NOOPT-LABEL: @mulwide32
 define i64 @mulwide32(i32 %a, i32 %b) {