From 1bf4d19172879e42eeb595e6337e8b358f6469c9 Mon Sep 17 00:00:00 2001
From: Chandler Carruth <chandlerc@gmail.com>
Date: Sat, 26 Jul 2014 01:52:13 +0000
Subject: [x86] Fix PR20355 (and dups) by not using unsigned multiplication
 when signed multiplication is requested. While there is not a difference in
 the *low* half of the result, the *high* half (used specifically to implement
 the signed division by these constants) certainly is used. The test case I've
 nuked was actively asserting wrong code.

There is a delightful solution to doing signed multiplication even when
we don't have it that Richard Smith has crafted, but I'll add the
machinery back and implement that in a follow-up patch. This at least
restores correctness.

llvm-svn: 214007
---
 llvm/test/CodeGen/X86/pmul.ll        |  8 ++++----
 llvm/test/CodeGen/X86/vector-idiv.ll | 16 +++++-----------
 2 files changed, 9 insertions(+), 15 deletions(-)

(limited to 'llvm/test/CodeGen')

diff --git a/llvm/test/CodeGen/X86/pmul.ll b/llvm/test/CodeGen/X86/pmul.ll
index 4944d6b9083..e129d5618aa 100644
--- a/llvm/test/CodeGen/X86/pmul.ll
+++ b/llvm/test/CodeGen/X86/pmul.ll
@@ -84,10 +84,10 @@ entry:
 }
 
 define <2 x i64> @f(<2 x i64> %i, <2 x i64> %j) nounwind  {
-; CHECK-LABEL: f:
-; CHECK:         pmuludq
-; CHECK:         pmuludq
-; CHECK:         pmuludq
+; ALL-LABEL: f:
+; ALL:         pmuludq
+; ALL:         pmuludq
+; ALL:         pmuludq
 entry:
   ; Use a call to force spills.
   call void @foo()
diff --git a/llvm/test/CodeGen/X86/vector-idiv.ll b/llvm/test/CodeGen/X86/vector-idiv.ll
index ec1ce3da5e1..0214a47f44c 100644
--- a/llvm/test/CodeGen/X86/vector-idiv.ll
+++ b/llvm/test/CodeGen/X86/vector-idiv.ll
@@ -131,18 +131,12 @@ define <4 x i32> @test8(<4 x i32> %a) {
 ; SSE41: psrad $2
 ; SSE41: padd
 
+; FIXME: scalarized -- there is no signed multiply in SSE.
 ; SSE-LABEL: test8:
-; SSE: pmuludq
-; SSE: pshufd	$49
-; SSE: pshufd	$49
-; SSE: pmuludq
-; SSE: shufps	$-35
-; SSE: pshufd	$-40
-; SSE: psubd
-; SSE: padd
-; SSE: psrld $31
-; SSE: psrad $2
-; SSE: padd
+; SSE: imulq
+; SSE: imulq
+; SSE: imulq
+; SSE: imulq
 
 ; AVX-LABEL: test8:
 ; AVX: vpmuldq
-- 
cgit v1.2.3