From: Sanjay Patel <spatel@rotateright.com>
Date: Fri, 14 Aug 2015 23:03:01 +0000 (+0000)
Subject: make current codegen visible in the checks, so we can decide if it's right
X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=3b0b6f081abf8d7a8d1c17250cfa28dc05cead5a;p=oota-llvm.git

make current codegen visible in the checks, so we can decide if it's right


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@245120 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/test/CodeGen/X86/memcpy-2.ll b/test/CodeGen/X86/memcpy-2.ll
index 0111c0d433f..1d3033fd77b 100644
--- a/test/CodeGen/X86/memcpy-2.ll
+++ b/test/CodeGen/X86/memcpy-2.ll
@@ -3,6 +3,17 @@
 ; RUN: llc < %s -mattr=+sse,-sse2 -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE1
 ; RUN: llc < %s -mattr=-sse       -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=NOSSE
 ; RUN: llc < %s                 -mtriple=x86_64-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=X86-64
+; RUN: llc < %s                 -mtriple=x86_64-apple-darwin -mcpu=nehalem | FileCheck %s -check-prefix=NHM_64
+
+;;; TODO: The last run line chooses cpu=nehalem to reveal possible bugs in the "t4" test case.
+;;;
+;;; Nehalem has a 'fast unaligned memory' attribute, so (1) some of the loads and stores
+;;; are certainly unaligned and (2) the first load and first store overlap with the second
+;;; load and second store respectively.
+;;;
+;;; Is either of the sequences ideal?
+;;; Is the ideal code being generated for all CPU models?
+
 
 @.str = internal constant [25 x i8] c"image\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00"
 @.str2 = internal constant [30 x i8] c"xxxxxxxxxxxxxxxxxxxxxxxxxxxxx\00", align 4
@@ -186,6 +197,13 @@ entry:
 ; X86-64: movq %rax
 ; X86-64: movw $120
 ; X86-64: movl $2021161080
+
+; NHM_64-LABEL: t4:
+; NHM_64: movups   _.str2+14(%rip), %xmm0
+; NHM_64: movups   %xmm0, -26(%rsp)
+; NHM_64: movups   _.str2(%rip), %xmm0
+; NHM_64: movaps   %xmm0, -40(%rsp)
+
   %tmp1 = alloca [30 x i8]
   %tmp2 = bitcast [30 x i8]* %tmp1 to i8*
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp2, i8* getelementptr inbounds ([30 x i8], [30 x i8]* @.str2, i32 0, i32 0), i32 30, i32 1, i1 false)