[llvm] r245120 - make current codegen visible in the checks, so we can decide if it's right

[Sanjay Patel via llvm-commits]

Author: spatel
Date: Fri Aug 14 18:03:01 2015
New Revision: 245120

URL: http://llvm.org/viewvc/llvm-project?rev=245120&view=rev
Log:
make current codegen visible in the checks, so we can decide if it's right

Modified:
    llvm/trunk/test/CodeGen/X86/memcpy-2.ll

Modified: llvm/trunk/test/CodeGen/X86/memcpy-2.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/memcpy-2.ll?rev=245120&r1=245119&r2=245120&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/memcpy-2.ll (original)
+++ llvm/trunk/test/CodeGen/X86/memcpy-2.ll Fri Aug 14 18:03:01 2015
@@ -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)