[x86] Teach my test updating script about another quirk of the printed

asm and port the mmx vector shuffle test to it.

Not thrilled with how it handles the stack manipulation logic, but I'm
much less bothered by that than I am by updating the test manually. =]
If anyone wants to teach the test checks management script about stack
adjustment patterns, that'd be cool too.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@229268 91177308-0d34-0410-b5e6-96231b3b80d8

test/CodeGen/X86/vector-shuffle-mmx.ll

@@ -1,15 +1,23 @@
-; RUN: llc < %s -mtriple=i686-darwin -mattr=+mmx,+sse2 | FileCheck -check-prefix=X32 %s
-; RUN: llc < %s -mtriple=x86_64-darwin -mattr=+mmx,+sse2 | FileCheck -check-prefix=X64 %s
+; RUN: llc < %s -mtriple=i686-darwin -mattr=+mmx,+sse2 | FileCheck --check-prefix=X32 %s
+; RUN: llc < %s -mtriple=x86_64-darwin -mattr=+mmx,+sse2 | FileCheck --check-prefix=X64 %s
 
 ; If there is no explicit MMX type usage, always promote to XMM.
 
 define void @test0(<1 x i64>* %x) {
-; X32-LABEL: test0
-; X64-LABEL: test0
-; X32: pshufd $213
-; X64: pshufd $213
-; X32-NEXT: movlpd %xmm
-; X64-NEXT: movq %xmm
+; X32-LABEL: test0:
+; X32:       ## BB#0: ## %entry
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
+; X32-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,1,1,3]
+; X32-NEXT:    movlpd %xmm0, (%eax)
+; X32-NEXT:    retl
+;
+; X64-LABEL: test0:
+; X64:       ## BB#0: ## %entry
+; X64-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
+; X64-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,1,1,3]
+; X64-NEXT:    movq %xmm0, (%rdi)
+; X64-NEXT:    retq
 entry:
   %tmp2 = load <1 x i64>* %x
   %tmp6 = bitcast <1 x i64> %tmp2 to <2 x i32>
@@ -21,10 +29,42 @@ entry:
 
 define void @test1() {
 ; X32-LABEL: test1:
-; X32:    pshuflw
-; X32-NEXT:    pshufhw
-; X32-NEXT:    pshufd
-; X32:    maskmovq
+; X32:       ## BB#0: ## %entry
+; X32-NEXT:    pushl %edi
+; X32-NEXT:  Ltmp0:
+; X32-NEXT:    .cfi_def_cfa_offset 8
+; X32-NEXT:    subl $16, %esp
+; X32-NEXT:  Ltmp1:
+; X32-NEXT:    .cfi_def_cfa_offset 24
+; X32-NEXT:  Ltmp2:
+; X32-NEXT:    .cfi_offset %edi, -8
+; X32-NEXT:    xorpd %xmm0, %xmm0
+; X32-NEXT:    movlpd %xmm0, (%esp)
+; X32-NEXT:    movq (%esp), %mm0
+; X32-NEXT:    pshuflw {{.*#+}} xmm0 = mem[0,2,2,3,4,5,6,7]
+; X32-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
+; X32-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; X32-NEXT:    movlpd %xmm0, {{[0-9]+}}(%esp)
+; X32-NEXT:    movq {{[0-9]+}}(%esp), %mm1
+; X32-NEXT:    xorl %edi, %edi
+; X32-NEXT:    maskmovq %mm1, %mm0
+; X32-NEXT:    addl $16, %esp
+; X32-NEXT:    popl %edi
+; X32-NEXT:    retl
+;
+; X64-LABEL: test1:
+; X64:       ## BB#0: ## %entry
+; X64-NEXT:    xorps %xmm0, %xmm0
+; X64-NEXT:    movq %xmm0, -{{[0-9]+}}(%rsp)
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %mm0
+; X64-NEXT:    pshuflw {{.*#+}} xmm0 = mem[0,2,2,3,4,5,6,7]
+; X64-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
+; X64-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; X64-NEXT:    movq %xmm0, -{{[0-9]+}}(%rsp)
+; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %mm1
+; X64-NEXT:    xorl %edi, %edi
+; X64-NEXT:    maskmovq %mm1, %mm0
+; X64-NEXT:    retq
 entry:
   %tmp528 = bitcast <8 x i8> zeroinitializer to <2 x i32>
   %tmp529 = and <2 x i32> %tmp528, bitcast (<4 x i16> < i16 -32640, i16 16448, i16 8224, i16 4112 > to <2 x i32>)
@@ -41,10 +81,21 @@ entry:
 
 define void @test2() nounwind {
 ; X32-LABEL: test2:
-; X32:    movsd
+; X32:       ## BB#0: ## %entry
+; X32-NEXT:    movl L_tmp_V2i$non_lazy_ptr, %eax
+; X32-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
 ; X32-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0,0]
 ; X32-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
 ; X32-NEXT:    movlpd %xmm0, (%eax)
+; X32-NEXT:    retl
+;
+; X64-LABEL: test2:
+; X64:       ## BB#0: ## %entry
+; X64-NEXT:    movq _tmp_V2i@{{.*}}(%rip), %rax
+; X64-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
+; X64-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,0,0,1]
+; X64-NEXT:    movq %xmm0, (%rax)
+; X64-NEXT:    retq
 entry:
   %0 = load <2 x i32>* @tmp_V2i, align 8
   %1 = shufflevector <2 x i32> %0, <2 x i32> undef, <2 x i32> zeroinitializer

utils/update_llc_test_checks.py

@@ -69,7 +69,7 @@ def main():
   asm_function_re = re.compile(
       r'^_?(?P<f>[^:]+):[ \t]*#+[ \t]*@(?P=f)\n[^:]*?'
       r'(?P<body>^##?[ \t]+[^:]+:.*?)\s*'
-      r'^\s*(?:[^:\n]+?:\s*\n\s*\.size|\.cfi_endproc|\.globl|\.(?:sub)?section)',
+      r'^\s*(?:[^:\n]+?:\s*\n\s*\.size|\.cfi_endproc|\.globl|\.comm|\.(?:sub)?section)',
       flags=(re.M | re.S))
   check_prefix_re = re.compile('--check-prefix=(\S+)')
   check_re = re.compile(r'^\s*;\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL)?:')