Teach X86ISelLowering that the second result of X86ISD::UMUL is a flags

result.  This allows us to compile:

void *test12(long count) {
      return new int[count];
}

into:

test12:
	movl	$4, %ecx
	movq	%rdi, %rax
	mulq	%rcx
	movq	$-1, %rdi
	cmovnoq	%rax, %rdi
	jmp	__Znam                  ## TAILCALL

instead of:

test12:
	movl	$4, %ecx
	movq	%rdi, %rax
	mulq	%rcx
	seto	%cl
	testb	%cl, %cl
	movq	$-1, %rdi
	cmoveq	%rax, %rdi
	jmp	__Znam

Of course it would be even better if the regalloc inverted the cmov to 'cmovoq',
which would eliminate the need for the 'movq %rdi, %rax'.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120936 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 58b8cb11121b716136b55f346941b6471765a89a..6e1420cb75a32e03c0c60a97f4cefbdf8d5a92c1 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -7207,6 +7207,9 @@ static bool isX86LogicalCmp(SDValue Op) {
        Opc == X86ISD::AND))
     return true;
 
+  if (Op.getResNo() == 2 && Opc == X86ISD::UMUL)
+    return true;
+    
   return false;
 }
 

diff --git a/test/CodeGen/X86/select.ll b/test/CodeGen/X86/select.ll
index b2f87bc2cf4565a1899fe44273da007a9f492287..9df23f1746811b4ed21ebcc3e80104706ebcc02d 100644 (file)
--- a/test/CodeGen/X86/select.ll
+++ b/test/CodeGen/X86/select.ll
@@ -178,4 +178,26 @@ define i64 @test11a(i64 %x, i64 %y) nounwind readnone ssp noredzone {
 }
 
 
+declare noalias i8* @_Znam(i64) noredzone
+
+define noalias i8* @test12(i64 %count) nounwind ssp noredzone {
+entry:
+  %A = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %count, i64 4)
+  %B = extractvalue { i64, i1 } %A, 1
+  %C = extractvalue { i64, i1 } %A, 0
+  %D = select i1 %B, i64 -1, i64 %C
+  %call = tail call noalias i8* @_Znam(i64 %D) nounwind noredzone
+  ret i8* %call
+; CHECK: test12:
+; CHECK: mulq
+; CHECK: movq $-1, %rdi
+; CHECK: cmovnoq       %rax, %rdi
+; CHECK: jmp   __Znam
+}
+
+declare { i64, i1 } @llvm.umul.with.overflow.i64(i64, i64) nounwind readnone
+
+
+
+