[opaque pointer type] Add textual IR support for explicit type parameter to load instruction

Essentially the same as the GEP change in r230786.

A similar migration script can be used to update test cases, though a few more
test case improvements/changes were required this time around: (r229269-r229278)

import fileinput
import sys
import re

pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)")

for line in sys.stdin:
  sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line))

Reviewers: rafael, dexonsmith, grosser

Differential Revision: http://reviews.llvm.org/D7649

llvm-svn: 230794
diff --git a/llvm/test/CodeGen/Thumb2/crash.ll b/llvm/test/CodeGen/Thumb2/crash.ll
index a3ab78d..8571f2c 100644
--- a/llvm/test/CodeGen/Thumb2/crash.ll
+++ b/llvm/test/CodeGen/Thumb2/crash.ll
@@ -7,13 +7,13 @@
 define arm_apcscc void @NEON_vst4q_u32(i32* nocapture %sp0, i32* nocapture %sp1, i32* nocapture %sp2, i32* nocapture %sp3, i32* %dp) nounwind {
 entry:
   %0 = bitcast i32* %sp0 to <4 x i32>*            ; <<4 x i32>*> [#uses=1]
-  %1 = load <4 x i32>* %0, align 16               ; <<4 x i32>> [#uses=1]
+  %1 = load <4 x i32>, <4 x i32>* %0, align 16               ; <<4 x i32>> [#uses=1]
   %2 = bitcast i32* %sp1 to <4 x i32>*            ; <<4 x i32>*> [#uses=1]
-  %3 = load <4 x i32>* %2, align 16               ; <<4 x i32>> [#uses=1]
+  %3 = load <4 x i32>, <4 x i32>* %2, align 16               ; <<4 x i32>> [#uses=1]
   %4 = bitcast i32* %sp2 to <4 x i32>*            ; <<4 x i32>*> [#uses=1]
-  %5 = load <4 x i32>* %4, align 16               ; <<4 x i32>> [#uses=1]
+  %5 = load <4 x i32>, <4 x i32>* %4, align 16               ; <<4 x i32>> [#uses=1]
   %6 = bitcast i32* %sp3 to <4 x i32>*            ; <<4 x i32>*> [#uses=1]
-  %7 = load <4 x i32>* %6, align 16               ; <<4 x i32>> [#uses=1]
+  %7 = load <4 x i32>, <4 x i32>* %6, align 16               ; <<4 x i32>> [#uses=1]
   %8 = bitcast i32* %dp to i8*                    ; <i8*> [#uses=1]
   tail call void @llvm.arm.neon.vst4.v4i32(i8* %8, <4 x i32> %1, <4 x i32> %3, <4 x i32> %5, <4 x i32> %7, i32 1)
   ret void
@@ -41,10 +41,10 @@
   br i1 %exitcond, label %bb2, label %bb
 
 bb2:                                              ; preds = %bb
-  %2 = load <4 x i32>* bitcast ([16 x i32]* @sbuf to <4 x i32>*), align 16 ; <<4 x i32>> [#uses=1]
-  %3 = load <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32]* @sbuf, i32 0, i32 4) to <4 x i32>*), align 16 ; <<4 x i32>> [#uses=1]
-  %4 = load <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32]* @sbuf, i32 0, i32 8) to <4 x i32>*), align 16 ; <<4 x i32>> [#uses=1]
-  %5 = load <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32]* @sbuf, i32 0, i32 12) to <4 x i32>*), align 16 ; <<4 x i32>> [#uses=1]
+  %2 = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @sbuf to <4 x i32>*), align 16 ; <<4 x i32>> [#uses=1]
+  %3 = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32]* @sbuf, i32 0, i32 4) to <4 x i32>*), align 16 ; <<4 x i32>> [#uses=1]
+  %4 = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32]* @sbuf, i32 0, i32 8) to <4 x i32>*), align 16 ; <<4 x i32>> [#uses=1]
+  %5 = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32]* @sbuf, i32 0, i32 12) to <4 x i32>*), align 16 ; <<4 x i32>> [#uses=1]
   tail call void @llvm.arm.neon.vst4.v4i32(i8* bitcast ([16 x i32]* @dbuf to i8*), <4 x i32> %2, <4 x i32> %3, <4 x i32> %4, <4 x i32> %5, i32 1) nounwind
   ret i32 0
 }