it turns out that when ".with.overflow" intrinsics were added to the X86

backend that they were all implemented except umul.  This one fell back
to the default implementation that did a hi/lo multiply and compared the
top.  Fix this to check the overflow flag that the 'mul' instruction
sets, so we can avoid an explicit test.  Now we compile:

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

into:

__Z4funcl:                              ## @_Z4funcl
	movl	$4, %ecx                ## encoding: [0xb9,0x04,0x00,0x00,0x00]
	movq	%rdi, %rax              ## encoding: [0x48,0x89,0xf8]
	mulq	%rcx                    ## encoding: [0x48,0xf7,0xe1]
	seto	%cl                     ## encoding: [0x0f,0x90,0xc1]
	testb	%cl, %cl                ## encoding: [0x84,0xc9]
	movq	$-1, %rdi               ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff]
	cmoveq	%rax, %rdi              ## encoding: [0x48,0x0f,0x44,0xf8]
	jmp	__Znam                  ## TAILCALL

instead of:

__Z4funcl:                              ## @_Z4funcl
	movl	$4, %ecx                ## encoding: [0xb9,0x04,0x00,0x00,0x00]
	movq	%rdi, %rax              ## encoding: [0x48,0x89,0xf8]
	mulq	%rcx                    ## encoding: [0x48,0xf7,0xe1]
	testq	%rdx, %rdx              ## encoding: [0x48,0x85,0xd2]
	movq	$-1, %rdi               ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff]
	cmoveq	%rax, %rdi              ## encoding: [0x48,0x0f,0x44,0xf8]
	jmp	__Znam                  ## TAILCALL

Other than the silly seto+test, this is using the o bit directly, so it's going in the right
direction.




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120935 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 7 insertions, 1 deletions

diff --git a/test/CodeGen/X86/umul-with-overflow.ll b/test/CodeGen/X86/umul-with-overflow.ll
index d522bd8..c997661 100644
--- a/test/CodeGen/X86/umul-with-overflow.ll
+++ b/test/CodeGen/X86/umul-with-overflow.ll
@@ -1,8 +1,14 @@
-; RUN: llc < %s -march=x86 | grep "\\\\\\\<mul"
+; RUN: llc < %s -march=x86 | FileCheck %s
 
 declare {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
 define i1 @a(i32 %x) zeroext nounwind {
   %res = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %x, i32 3)
   %obil = extractvalue {i32, i1} %res, 1
   ret i1 %obil
+  
+; CHECK: a:
+; CHECK: mull
+; CHECK: seto %al
+; CHECK: movzbl	%al, %eax
+; CHECK: ret
 }