rip out a ton of intrinsic modernization logic from AutoUpgrade.cpp, which is
for pre-2.9 bitcode files.  We keep x86 unaligned loads, movnt, crc32, and the
target indep prefetch change.

As usual, updating the testsuite is a PITA.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133337 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/ARM/dyn-stackalloc.ll b/test/CodeGen/ARM/dyn-stackalloc.ll
index 92e2d13..de2820e 100644
--- a/test/CodeGen/ARM/dyn-stackalloc.ll
+++ b/test/CodeGen/ARM/dyn-stackalloc.ll
@@ -1,48 +1,48 @@
 ; RUN: llc < %s -march=arm
 
-	%struct.state = type { i32, %struct.info*, float**, i32, i32, i32, i32, i32, i32, i32, i32, i32, i64, i64, i64, i64, i64, i64, i8* }
-	%struct.info = type { i32, i32, i32, i32, i32, i32, i32, i8* }
+%struct.comment = type { i8**, i32*, i32, i8* }
+%struct.info = type { i32, i32, i32, i32, i32, i32, i32, i8* }
+%struct.state = type { i32, %struct.info*, float**, i32, i32, i32, i32, i32, i32, i32, i32, i32, i64, i64, i64, i64, i64, i64, i8* }
+
+@str215 = external global [2 x i8]
 
 define void @t1(%struct.state* %v) {
-	%tmp6 = load i32* null
-	%tmp8 = alloca float, i32 %tmp6
-	store i32 1, i32* null
-	br i1 false, label %bb123.preheader, label %return
+  %tmp6 = load i32* null
+  %tmp8 = alloca float, i32 %tmp6
+  store i32 1, i32* null
+  br i1 false, label %bb123.preheader, label %return
 
-bb123.preheader:
-	br i1 false, label %bb43, label %return
+bb123.preheader:                                  ; preds = %0
+  br i1 false, label %bb43, label %return
 
-bb43:
-	call fastcc void @f1( float* %tmp8, float* null, i32 0 )
-	%tmp70 = load i32* null
-	%tmp85 = getelementptr float* %tmp8, i32 0
-	call fastcc void @f2( float* null, float* null, float* %tmp85, i32 %tmp70 )
-	ret void
+bb43:                                             ; preds = %bb123.preheader
+  call fastcc void @f1(float* %tmp8, float* null, i32 0)
+  %tmp70 = load i32* null
+  %tmp85 = getelementptr float* %tmp8, i32 0
+  call fastcc void @f2(float* null, float* null, float* %tmp85, i32 %tmp70)
+  ret void
 
-return:
-	ret void
+return:                                           ; preds = %bb123.preheader, %0
+  ret void
 }
 
 declare fastcc void @f1(float*, float*, i32)
 
 declare fastcc void @f2(float*, float*, float*, i32)
 
-	%struct.comment = type { i8**, i32*, i32, i8* }
-@str215 = external global [2 x i8]
-
 define void @t2(%struct.comment* %vc, i8* %tag, i8* %contents) {
-	%tmp1 = call i32 @strlen( i8* %tag )
-	%tmp3 = call i32 @strlen( i8* %contents )
-	%tmp4 = add i32 %tmp1, 2
-	%tmp5 = add i32 %tmp4, %tmp3
-	%tmp6 = alloca i8, i32 %tmp5
-	%tmp9 = call i8* @strcpy( i8* %tmp6, i8* %tag )
-	%tmp6.len = call i32 @strlen( i8* %tmp6 )
-	%tmp6.indexed = getelementptr i8* %tmp6, i32 %tmp6.len
-	call void @llvm.memcpy.i32( i8* %tmp6.indexed, i8* getelementptr ([2 x i8]* @str215, i32 0, i32 0), i32 2, i32 1 )
-	%tmp15 = call i8* @strcat( i8* %tmp6, i8* %contents )
-	call fastcc void @comment_add( %struct.comment* %vc, i8* %tmp6 )
-	ret void
+  %tmp1 = call i32 @strlen(i8* %tag)
+  %tmp3 = call i32 @strlen(i8* %contents)
+  %tmp4 = add i32 %tmp1, 2
+  %tmp5 = add i32 %tmp4, %tmp3
+  %tmp6 = alloca i8, i32 %tmp5
+  %tmp9 = call i8* @strcpy(i8* %tmp6, i8* %tag)
+  %tmp6.len = call i32 @strlen(i8* %tmp6)
+  %tmp6.indexed = getelementptr i8* %tmp6, i32 %tmp6.len
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp6.indexed, i8* getelementptr inbounds ([2 x i8]* @str215, i32 0, i32 0), i32 2, i32 1, i1 false)
+  %tmp15 = call i8* @strcat(i8* %tmp6, i8* %contents)
+  call fastcc void @comment_add(%struct.comment* %vc, i8* %tmp6)
+  ret void
 }
 
 declare i32 @strlen(i8*)
@@ -51,6 +51,6 @@
 
 declare fastcc void @comment_add(%struct.comment*, i8*)
 
-declare void @llvm.memcpy.i32(i8*, i8*, i32, i32)
-
 declare i8* @strcpy(i8*, i8*)
+
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind