From a79ac14fa68297f9888bc70a10df5ed9b8864e38 Mon Sep 17 00:00:00 2001
From: David Blaikie <dblaikie@gmail.com>
Date: Fri, 27 Feb 2015 21:17:42 +0000
Subject: [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
---
 .../LoopVectorize/X86/already-vectorized.ll        |   2 +-
 llvm/test/Transforms/LoopVectorize/X86/assume.ll   |   8 +-
 llvm/test/Transforms/LoopVectorize/X86/avx1.ll     |   4 +-
 .../LoopVectorize/X86/constant-vector-operand.ll   |   2 +-
 .../Transforms/LoopVectorize/X86/cost-model.ll     |   6 +-
 .../LoopVectorize/X86/fp32_to_uint32-cost-model.ll |   2 +-
 .../LoopVectorize/X86/fp64_to_uint32-cost-model.ll |   4 +-
 .../LoopVectorize/X86/fp_to_sint8-cost-model.ll    |   2 +-
 .../Transforms/LoopVectorize/X86/gather-cost.ll    |  14 +-
 .../Transforms/LoopVectorize/X86/gcc-examples.ll   |   6 +-
 .../X86/illegal-parallel-loop-uniform-write.ll     |   4 +-
 .../LoopVectorize/X86/masked_load_store.ll         | 150 ++++++++++-----------
 .../LoopVectorize/X86/metadata-enable.ll           |  12 +-
 .../LoopVectorize/X86/min-trip-count-switch.ll     |   2 +-
 .../test/Transforms/LoopVectorize/X86/no-vector.ll |   2 +-
 .../X86/parallel-loops-after-reg2mem.ll            |  14 +-
 .../Transforms/LoopVectorize/X86/parallel-loops.ll |  18 +--
 .../test/Transforms/LoopVectorize/X86/powof2div.ll |   4 +-
 .../LoopVectorize/X86/reduction-crash.ll           |   4 +-
 .../Transforms/LoopVectorize/X86/small-size.ll     |  16 +--
 .../test/Transforms/LoopVectorize/X86/tripcount.ll |   2 +-
 .../LoopVectorize/X86/uint64_to_fp64-cost-model.ll |   2 +-
 .../test/Transforms/LoopVectorize/X86/unroll-pm.ll |   2 +-
 .../LoopVectorize/X86/unroll-small-loops.ll        |  10 +-
 .../LoopVectorize/X86/unroll_selection.ll          |   4 +-
 .../Transforms/LoopVectorize/X86/vect.omp.force.ll |   4 +-
 .../LoopVectorize/X86/vect.omp.force.small-tc.ll   |   8 +-
 .../LoopVectorize/X86/vector-scalar-select-cost.ll |   8 +-
 .../LoopVectorize/X86/vector_ptr_load_store.ll     |   8 +-
 .../X86/vectorization-remarks-missed.ll            |   4 +-
 .../LoopVectorize/X86/vectorization-remarks.ll     |   4 +-
 31 files changed, 166 insertions(+), 166 deletions(-)

(limited to 'llvm/test/Transforms/LoopVectorize/X86')

diff --git a/llvm/test/Transforms/LoopVectorize/X86/already-vectorized.ll b/llvm/test/Transforms/LoopVectorize/X86/already-vectorized.ll
index dcf2c6e70c4..248d6dc90bd 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/already-vectorized.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/already-vectorized.ll
@@ -22,7 +22,7 @@ for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %red.05 = phi i32 [ 0, %entry ], [ %add, %for.body ]
   %arrayidx = getelementptr inbounds [255 x i32], [255 x i32]* @a, i64 0, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %0 = load i32, i32* %arrayidx, align 4
   %add = add nsw i32 %0, %red.05
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
   %exitcond = icmp eq i64 %indvars.iv.next, 255
diff --git a/llvm/test/Transforms/LoopVectorize/X86/assume.ll b/llvm/test/Transforms/LoopVectorize/X86/assume.ll
index c036bba07ce..4fd378d1a0a 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/assume.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/assume.ll
@@ -23,7 +23,7 @@ entry:
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds float, float* %b, i64 %indvars.iv
-  %0 = load float* %arrayidx, align 4
+  %0 = load float, float* %arrayidx, align 4
   %cmp1 = fcmp ogt float %0, 1.000000e+02
   tail call void @llvm.assume(i1 %cmp1)
   %add = fadd float %0, 1.000000e+00
@@ -49,12 +49,12 @@ attributes #1 = { nounwind }
 define void @test2(%struct.data* nocapture readonly %d) #0 {
 entry:
   %b = getelementptr inbounds %struct.data, %struct.data* %d, i64 0, i32 1
-  %0 = load float** %b, align 8
+  %0 = load float*, float** %b, align 8
   %ptrint = ptrtoint float* %0 to i64
   %maskedptr = and i64 %ptrint, 31
   %maskcond = icmp eq i64 %maskedptr, 0
   %a = getelementptr inbounds %struct.data, %struct.data* %d, i64 0, i32 0
-  %1 = load float** %a, align 8
+  %1 = load float*, float** %a, align 8
   %ptrint2 = ptrtoint float* %1 to i64
   %maskedptr3 = and i64 %ptrint2, 31
   %maskcond4 = icmp eq i64 %maskedptr3, 0
@@ -85,7 +85,7 @@ for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   tail call void @llvm.assume(i1 %maskcond)
   %arrayidx = getelementptr inbounds float, float* %0, i64 %indvars.iv
-  %2 = load float* %arrayidx, align 4
+  %2 = load float, float* %arrayidx, align 4
   %add = fadd float %2, 1.000000e+00
   tail call void @llvm.assume(i1 %maskcond4)
   %arrayidx5 = getelementptr inbounds float, float* %1, i64 %indvars.iv
diff --git a/llvm/test/Transforms/LoopVectorize/X86/avx1.ll b/llvm/test/Transforms/LoopVectorize/X86/avx1.ll
index 95088df5c3f..37977c43ac3 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/avx1.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/avx1.ll
@@ -13,7 +13,7 @@ define i32 @read_mod_write_single_ptr(float* nocapture %a, i32 %n) nounwind uwta
 .lr.ph:                                           ; preds = %0, %.lr.ph
   %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
   %2 = getelementptr inbounds float, float* %a, i64 %indvars.iv
-  %3 = load float* %2, align 4
+  %3 = load float, float* %2, align 4
   %4 = fmul float %3, 3.000000e+00
   store float %4, float* %2, align 4
   %indvars.iv.next = add i64 %indvars.iv, 1
@@ -36,7 +36,7 @@ define i32 @read_mod_i64(i64* nocapture %a, i32 %n) nounwind uwtable ssp {
 .lr.ph:                                           ; preds = %0, %.lr.ph
   %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
   %2 = getelementptr inbounds i64, i64* %a, i64 %indvars.iv
-  %3 = load i64* %2, align 4
+  %3 = load i64, i64* %2, align 4
   %4 = add i64 %3, 3
   store i64 %4, i64* %2, align 4
   %indvars.iv.next = add i64 %indvars.iv, 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/constant-vector-operand.ll b/llvm/test/Transforms/LoopVectorize/X86/constant-vector-operand.ll
index 106bd84fc7c..d75b1d940ae 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/constant-vector-operand.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/constant-vector-operand.ll
@@ -16,7 +16,7 @@ entry:
 for.body:
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds [1024 x i32], [1024 x i32]* @B, i64 0, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %0 = load i32, i32* %arrayidx, align 4
   %shl = ashr i32 %0, 3
   %arrayidx2 = getelementptr inbounds [1024 x i32], [1024 x i32]* @A, i64 0, i64 %indvars.iv
   store i32 %shl, i32* %arrayidx2, align 4
diff --git a/llvm/test/Transforms/LoopVectorize/X86/cost-model.ll b/llvm/test/Transforms/LoopVectorize/X86/cost-model.ll
index 190e130b609..013657102e6 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/cost-model.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/cost-model.ll
@@ -22,12 +22,12 @@ for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %0 = shl nsw i64 %indvars.iv, 1
   %arrayidx = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 %0
-  %1 = load i32* %arrayidx, align 8
+  %1 = load i32, i32* %arrayidx, align 8
   %idxprom1 = sext i32 %1 to i64
   %arrayidx2 = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 %idxprom1
-  %2 = load i32* %arrayidx2, align 4
+  %2 = load i32, i32* %arrayidx2, align 4
   %arrayidx4 = getelementptr inbounds [2048 x i32], [2048 x i32]* @d, i64 0, i64 %indvars.iv
-  %3 = load i32* %arrayidx4, align 4
+  %3 = load i32, i32* %arrayidx4, align 4
   %idxprom5 = sext i32 %3 to i64
   %arrayidx6 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %idxprom5
   store i32 %2, i32* %arrayidx6, align 4
diff --git a/llvm/test/Transforms/LoopVectorize/X86/fp32_to_uint32-cost-model.ll b/llvm/test/Transforms/LoopVectorize/X86/fp32_to_uint32-cost-model.ll
index 627ae0076b0..4a56d6b5ebf 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/fp32_to_uint32-cost-model.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/fp32_to_uint32-cost-model.ll
@@ -21,7 +21,7 @@ for.body.preheader:                               ; preds = %entry
 for.body:                                         ; preds = %for.body.preheader, %for.body
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
   %arrayidx = getelementptr inbounds [10000 x float], [10000 x float]* @float_array, i64 0, i64 %indvars.iv
-  %1 = load float* %arrayidx, align 4
+  %1 = load float, float* %arrayidx, align 4
   %conv = fptoui float %1 to i32
   %arrayidx2 = getelementptr inbounds [10000 x i32], [10000 x i32]* @unsigned_array, i64 0, i64 %indvars.iv
   store i32 %conv, i32* %arrayidx2, align 4
diff --git a/llvm/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll b/llvm/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll
index 7c1dfe39236..c066afcfa63 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll
@@ -13,7 +13,7 @@ target triple = "x86_64-apple-macosx"
 
 define void @convert() {
 entry:
-  %0 = load i32* @n, align 4
+  %0 = load i32, i32* @n, align 4
   %cmp4 = icmp eq i32 %0, 0
   br i1 %cmp4, label %for.end, label %for.body.preheader
 
@@ -23,7 +23,7 @@ for.body.preheader:                               ; preds = %entry
 for.body:                                         ; preds = %for.body.preheader, %for.body
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
   %arrayidx = getelementptr inbounds [10000 x double], [10000 x double]* @double_array, i64 0, i64 %indvars.iv
-  %1 = load double* %arrayidx, align 8
+  %1 = load double, double* %arrayidx, align 8
   %conv = fptoui double %1 to i32
   %arrayidx2 = getelementptr inbounds [10000 x i32], [10000 x i32]* @unsigned_array, i64 0, i64 %indvars.iv
   store i32 %conv, i32* %arrayidx2, align 4
diff --git a/llvm/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll b/llvm/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll
index 106c9d66623..b3a0710545d 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll
@@ -12,7 +12,7 @@ entry:
 for.body:
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds float, float* %b, i64 %indvars.iv
-  %tmp = load float* %arrayidx, align 4
+  %tmp = load float, float* %arrayidx, align 4
   %conv = fptosi float %tmp to i8
   %arrayidx2 = getelementptr inbounds i8, i8* %a, i64 %indvars.iv
   store i8 %conv, i8* %arrayidx2, align 4
diff --git a/llvm/test/Transforms/LoopVectorize/X86/gather-cost.ll b/llvm/test/Transforms/LoopVectorize/X86/gather-cost.ll
index 8c9cb653da0..f0e6c8f205c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/gather-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/gather-cost.ll
@@ -32,23 +32,23 @@ for.body:
   %add = add i64 %v.055, %offset
   %mul = mul i64 %add, 3
   %arrayidx = getelementptr inbounds [1536 x float], [1536 x float]* @src_data, i64 0, i64 %mul
-  %0 = load float* %arrayidx, align 4
+  %0 = load float, float* %arrayidx, align 4
   %arrayidx2 = getelementptr inbounds [512 x float], [512 x float]* @kernel, i64 0, i64 %v.055
-  %1 = load float* %arrayidx2, align 4
+  %1 = load float, float* %arrayidx2, align 4
   %mul3 = fmul fast float %0, %1
   %arrayidx4 = getelementptr inbounds [512 x float], [512 x float]* @kernel2, i64 0, i64 %v.055
-  %2 = load float* %arrayidx4, align 4
+  %2 = load float, float* %arrayidx4, align 4
   %mul5 = fmul fast float %mul3, %2
   %arrayidx6 = getelementptr inbounds [512 x float], [512 x float]* @kernel3, i64 0, i64 %v.055
-  %3 = load float* %arrayidx6, align 4
+  %3 = load float, float* %arrayidx6, align 4
   %mul7 = fmul fast float %mul5, %3
   %arrayidx8 = getelementptr inbounds [512 x float], [512 x float]* @kernel4, i64 0, i64 %v.055
-  %4 = load float* %arrayidx8, align 4
+  %4 = load float, float* %arrayidx8, align 4
   %mul9 = fmul fast float %mul7, %4
   %add10 = fadd fast float %r.057, %mul9
   %arrayidx.sum = add i64 %mul, 1
   %arrayidx11 = getelementptr inbounds [1536 x float], [1536 x float]* @src_data, i64 0, i64 %arrayidx.sum
-  %5 = load float* %arrayidx11, align 4
+  %5 = load float, float* %arrayidx11, align 4
   %mul13 = fmul fast float %1, %5
   %mul15 = fmul fast float %2, %mul13
   %mul17 = fmul fast float %3, %mul15
@@ -56,7 +56,7 @@ for.body:
   %add20 = fadd fast float %g.056, %mul19
   %arrayidx.sum52 = add i64 %mul, 2
   %arrayidx21 = getelementptr inbounds [1536 x float], [1536 x float]* @src_data, i64 0, i64 %arrayidx.sum52
-  %6 = load float* %arrayidx21, align 4
+  %6 = load float, float* %arrayidx21, align 4
   %mul23 = fmul fast float %1, %6
   %mul25 = fmul fast float %2, %mul23
   %mul27 = fmul fast float %3, %mul25
diff --git a/llvm/test/Transforms/LoopVectorize/X86/gcc-examples.ll b/llvm/test/Transforms/LoopVectorize/X86/gcc-examples.ll
index eb846622262..c581f4bf2a6 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/gcc-examples.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/gcc-examples.ll
@@ -29,9 +29,9 @@ define void @example1() nounwind uwtable ssp {
 ; <label>:1                                       ; preds = %1, %0
   %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
   %2 = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 %indvars.iv
-  %3 = load i32* %2, align 4
+  %3 = load i32, i32* %2, align 4
   %4 = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 %indvars.iv
-  %5 = load i32* %4, align 4
+  %5 = load i32, i32* %4, align 4
   %6 = add nsw i32 %5, %3
   %7 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %indvars.iv
   store i32 %6, i32* %7, align 4
@@ -62,7 +62,7 @@ define void @example10b(i16* noalias nocapture %sa, i16* noalias nocapture %sb,
 ; <label>:1                                       ; preds = %1, %0
   %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
   %2 = getelementptr inbounds i16, i16* %sb, i64 %indvars.iv
-  %3 = load i16* %2, align 2
+  %3 = load i16, i16* %2, align 2
   %4 = sext i16 %3 to i32
   %5 = getelementptr inbounds i32, i32* %ia, i64 %indvars.iv
   store i32 %4, i32* %5, align 4
diff --git a/llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll b/llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
index f2163b0bf81..cbba5300b9c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
@@ -15,7 +15,7 @@ entry:
 
 for.end.us:                                       ; preds = %for.body3.us
   %arrayidx9.us = getelementptr inbounds i32, i32* %b, i64 %indvars.iv33
-  %0 = load i32* %arrayidx9.us, align 4, !llvm.mem.parallel_loop_access !3
+  %0 = load i32, i32* %arrayidx9.us, align 4, !llvm.mem.parallel_loop_access !3
   %add10.us = add nsw i32 %0, 3
   store i32 %add10.us, i32* %arrayidx9.us, align 4, !llvm.mem.parallel_loop_access !3
   %indvars.iv.next34 = add i64 %indvars.iv33, 1
@@ -29,7 +29,7 @@ for.body3.us:                                     ; preds = %for.body3.us, %for.
   %add4.us = add i32 %add.us, %1
   %idxprom.us = sext i32 %add4.us to i64
   %arrayidx.us = getelementptr inbounds i32, i32* %a, i64 %idxprom.us
-  %2 = load i32* %arrayidx.us, align 4, !llvm.mem.parallel_loop_access !3
+  %2 = load i32, i32* %arrayidx.us, align 4, !llvm.mem.parallel_loop_access !3
   %add5.us = add nsw i32 %2, 1
   store i32 %add5.us, i32* %arrayidx7.us, align 4, !llvm.mem.parallel_loop_access !3
   %indvars.iv.next30 = add i64 %indvars.iv29, 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll b/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll
index c3ee6f81a79..c3175b02036 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll
@@ -46,34 +46,34 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 10000
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* %i, align 4
+  %1 = load i32, i32* %i, align 4
   %idxprom = sext i32 %1 to i64
-  %2 = load i32** %trigger.addr, align 8
+  %2 = load i32*, i32** %trigger.addr, align 8
   %arrayidx = getelementptr inbounds i32, i32* %2, i64 %idxprom
-  %3 = load i32* %arrayidx, align 4
+  %3 = load i32, i32* %arrayidx, align 4
   %cmp1 = icmp slt i32 %3, 100
   br i1 %cmp1, label %if.then, label %if.end
 
 if.then:                                          ; preds = %for.body
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %idxprom2 = sext i32 %4 to i64
-  %5 = load i32** %B.addr, align 8
+  %5 = load i32*, i32** %B.addr, align 8
   %arrayidx3 = getelementptr inbounds i32, i32* %5, i64 %idxprom2
-  %6 = load i32* %arrayidx3, align 4
-  %7 = load i32* %i, align 4
+  %6 = load i32, i32* %arrayidx3, align 4
+  %7 = load i32, i32* %i, align 4
   %idxprom4 = sext i32 %7 to i64
-  %8 = load i32** %trigger.addr, align 8
+  %8 = load i32*, i32** %trigger.addr, align 8
   %arrayidx5 = getelementptr inbounds i32, i32* %8, i64 %idxprom4
-  %9 = load i32* %arrayidx5, align 4
+  %9 = load i32, i32* %arrayidx5, align 4
   %add = add nsw i32 %6, %9
-  %10 = load i32* %i, align 4
+  %10 = load i32, i32* %i, align 4
   %idxprom6 = sext i32 %10 to i64
-  %11 = load i32** %A.addr, align 8
+  %11 = load i32*, i32** %A.addr, align 8
   %arrayidx7 = getelementptr inbounds i32, i32* %11, i64 %idxprom6
   store i32 %add, i32* %arrayidx7, align 4
   br label %if.end
@@ -82,7 +82,7 @@ if.end:                                           ; preds = %if.then, %for.body
   br label %for.inc
 
 for.inc:                                          ; preds = %if.end
-  %12 = load i32* %i, align 4
+  %12 = load i32, i32* %i, align 4
   %inc = add nsw i32 %12, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
@@ -130,35 +130,35 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 10000
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* %i, align 4
+  %1 = load i32, i32* %i, align 4
   %idxprom = sext i32 %1 to i64
-  %2 = load i32** %trigger.addr, align 8
+  %2 = load i32*, i32** %trigger.addr, align 8
   %arrayidx = getelementptr inbounds i32, i32* %2, i64 %idxprom
-  %3 = load i32* %arrayidx, align 4
+  %3 = load i32, i32* %arrayidx, align 4
   %cmp1 = icmp slt i32 %3, 100
   br i1 %cmp1, label %if.then, label %if.end
 
 if.then:                                          ; preds = %for.body
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %idxprom2 = sext i32 %4 to i64
-  %5 = load float** %B.addr, align 8
+  %5 = load float*, float** %B.addr, align 8
   %arrayidx3 = getelementptr inbounds float, float* %5, i64 %idxprom2
-  %6 = load float* %arrayidx3, align 4
-  %7 = load i32* %i, align 4
+  %6 = load float, float* %arrayidx3, align 4
+  %7 = load i32, i32* %i, align 4
   %idxprom4 = sext i32 %7 to i64
-  %8 = load i32** %trigger.addr, align 8
+  %8 = load i32*, i32** %trigger.addr, align 8
   %arrayidx5 = getelementptr inbounds i32, i32* %8, i64 %idxprom4
-  %9 = load i32* %arrayidx5, align 4
+  %9 = load i32, i32* %arrayidx5, align 4
   %conv = sitofp i32 %9 to float
   %add = fadd float %6, %conv
-  %10 = load i32* %i, align 4
+  %10 = load i32, i32* %i, align 4
   %idxprom6 = sext i32 %10 to i64
-  %11 = load float** %A.addr, align 8
+  %11 = load float*, float** %A.addr, align 8
   %arrayidx7 = getelementptr inbounds float, float* %11, i64 %idxprom6
   store float %add, float* %arrayidx7, align 4
   br label %if.end
@@ -167,7 +167,7 @@ if.end:                                           ; preds = %if.then, %for.body
   br label %for.inc
 
 for.inc:                                          ; preds = %if.end
-  %12 = load i32* %i, align 4
+  %12 = load i32, i32* %i, align 4
   %inc = add nsw i32 %12, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
@@ -218,35 +218,35 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 10000
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* %i, align 4
+  %1 = load i32, i32* %i, align 4
   %idxprom = sext i32 %1 to i64
-  %2 = load i32** %trigger.addr, align 8
+  %2 = load i32*, i32** %trigger.addr, align 8
   %arrayidx = getelementptr inbounds i32, i32* %2, i64 %idxprom
-  %3 = load i32* %arrayidx, align 4
+  %3 = load i32, i32* %arrayidx, align 4
   %cmp1 = icmp slt i32 %3, 100
   br i1 %cmp1, label %if.then, label %if.end
 
 if.then:                                          ; preds = %for.body
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %idxprom2 = sext i32 %4 to i64
-  %5 = load double** %B.addr, align 8
+  %5 = load double*, double** %B.addr, align 8
   %arrayidx3 = getelementptr inbounds double, double* %5, i64 %idxprom2
-  %6 = load double* %arrayidx3, align 8
-  %7 = load i32* %i, align 4
+  %6 = load double, double* %arrayidx3, align 8
+  %7 = load i32, i32* %i, align 4
   %idxprom4 = sext i32 %7 to i64
-  %8 = load i32** %trigger.addr, align 8
+  %8 = load i32*, i32** %trigger.addr, align 8
   %arrayidx5 = getelementptr inbounds i32, i32* %8, i64 %idxprom4
-  %9 = load i32* %arrayidx5, align 4
+  %9 = load i32, i32* %arrayidx5, align 4
   %conv = sitofp i32 %9 to double
   %add = fadd double %6, %conv
-  %10 = load i32* %i, align 4
+  %10 = load i32, i32* %i, align 4
   %idxprom6 = sext i32 %10 to i64
-  %11 = load double** %A.addr, align 8
+  %11 = load double*, double** %A.addr, align 8
   %arrayidx7 = getelementptr inbounds double, double* %11, i64 %idxprom6
   store double %add, double* %arrayidx7, align 8
   br label %if.end
@@ -255,7 +255,7 @@ if.end:                                           ; preds = %if.then, %for.body
   br label %for.inc
 
 for.inc:                                          ; preds = %if.end
-  %12 = load i32* %i, align 4
+  %12 = load i32, i32* %i, align 4
   %inc = add nsw i32 %12, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
@@ -297,36 +297,36 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 10000
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* %i, align 4
+  %1 = load i32, i32* %i, align 4
   %idxprom = sext i32 %1 to i64
-  %2 = load i32** %trigger.addr, align 8
+  %2 = load i32*, i32** %trigger.addr, align 8
   %arrayidx = getelementptr inbounds i32, i32* %2, i64 %idxprom
-  %3 = load i32* %arrayidx, align 4
+  %3 = load i32, i32* %arrayidx, align 4
   %cmp1 = icmp slt i32 %3, 100
   br i1 %cmp1, label %if.then, label %if.end
 
 if.then:                                          ; preds = %for.body
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %mul = mul nsw i32 %4, 2
   %idxprom2 = sext i32 %mul to i64
-  %5 = load double** %B.addr, align 8
+  %5 = load double*, double** %B.addr, align 8
   %arrayidx3 = getelementptr inbounds double, double* %5, i64 %idxprom2
-  %6 = load double* %arrayidx3, align 8
-  %7 = load i32* %i, align 4
+  %6 = load double, double* %arrayidx3, align 8
+  %7 = load i32, i32* %i, align 4
   %idxprom4 = sext i32 %7 to i64
-  %8 = load i32** %trigger.addr, align 8
+  %8 = load i32*, i32** %trigger.addr, align 8
   %arrayidx5 = getelementptr inbounds i32, i32* %8, i64 %idxprom4
-  %9 = load i32* %arrayidx5, align 4
+  %9 = load i32, i32* %arrayidx5, align 4
   %conv = sitofp i32 %9 to double
   %add = fadd double %6, %conv
-  %10 = load i32* %i, align 4
+  %10 = load i32, i32* %i, align 4
   %idxprom6 = sext i32 %10 to i64
-  %11 = load double** %A.addr, align 8
+  %11 = load double*, double** %A.addr, align 8
   %arrayidx7 = getelementptr inbounds double, double* %11, i64 %idxprom6
   store double %add, double* %arrayidx7, align 8
   br label %if.end
@@ -335,7 +335,7 @@ if.end:                                           ; preds = %if.then, %for.body
   br label %for.inc
 
 for.inc:                                          ; preds = %if.end
-  %12 = load i32* %i, align 4
+  %12 = load i32, i32* %i, align 4
   %inc = add nsw i32 %12, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
@@ -373,34 +373,34 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 10000
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* %i, align 4
+  %1 = load i32, i32* %i, align 4
   %idxprom = sext i32 %1 to i64
-  %2 = load i32** %trigger.addr, align 8
+  %2 = load i32*, i32** %trigger.addr, align 8
   %arrayidx = getelementptr inbounds i32, i32* %2, i64 %idxprom
-  %3 = load i32* %arrayidx, align 4
+  %3 = load i32, i32* %arrayidx, align 4
   %cmp1 = icmp slt i32 %3, 100
   br i1 %cmp1, label %if.then, label %if.end
 
 if.then:                                          ; preds = %for.body
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %idxprom2 = sext i32 %4 to i64
-  %5 = load i32** %B.addr, align 8
+  %5 = load i32*, i32** %B.addr, align 8
   %arrayidx3 = getelementptr inbounds i32, i32* %5, i64 %idxprom2
-  %6 = load i32* %arrayidx3, align 4
-  %7 = load i32* %i, align 4
+  %6 = load i32, i32* %arrayidx3, align 4
+  %7 = load i32, i32* %i, align 4
   %idxprom4 = sext i32 %7 to i64
-  %8 = load i32** %trigger.addr, align 8
+  %8 = load i32*, i32** %trigger.addr, align 8
   %arrayidx5 = getelementptr inbounds i32, i32* %8, i64 %idxprom4
-  %9 = load i32* %arrayidx5, align 4
+  %9 = load i32, i32* %arrayidx5, align 4
   %add = add nsw i32 %6, %9
-  %10 = load i32* %i, align 4
+  %10 = load i32, i32* %i, align 4
   %idxprom6 = sext i32 %10 to i64
-  %11 = load i32** %A.addr, align 8
+  %11 = load i32*, i32** %A.addr, align 8
   %arrayidx7 = getelementptr inbounds i32, i32* %11, i64 %idxprom6
   store i32 sdiv (i32 1, i32 zext (i1 icmp eq (i32** getelementptr inbounds ([1 x i32*]* @a, i64 0, i64 1), i32** @c) to i32)), i32* %arrayidx7, align 4
   br label %if.end
@@ -409,7 +409,7 @@ if.end:                                           ; preds = %if.then, %for.body
   br label %for.inc
 
 for.inc:                                          ; preds = %if.end
-  %12 = load i32* %i, align 4
+  %12 = load i32, i32* %i, align 4
   %inc = add nsw i32 %12, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond
@@ -459,29 +459,29 @@ entry:
   br label %for.cond
 
 for.cond:                                         ; preds = %for.inc, %entry
-  %0 = load i32* %i, align 4
+  %0 = load i32, i32* %i, align 4
   %cmp = icmp sge i32 %0, 0
   br i1 %cmp, label %for.body, label %for.end
 
 for.body:                                         ; preds = %for.cond
-  %1 = load i32* %i, align 4
+  %1 = load i32, i32* %i, align 4
   %idxprom = sext i32 %1 to i64
-  %2 = load i32** %trigger.addr, align 8
+  %2 = load i32*, i32** %trigger.addr, align 8
   %arrayidx = getelementptr inbounds i32, i32* %2, i64 %idxprom
-  %3 = load i32* %arrayidx, align 4
+  %3 = load i32, i32* %arrayidx, align 4
   %cmp1 = icmp sgt i32 %3, 0
   br i1 %cmp1, label %if.then, label %if.end
 
 if.then:                                          ; preds = %for.body
-  %4 = load i32* %i, align 4
+  %4 = load i32, i32* %i, align 4
   %idxprom2 = sext i32 %4 to i64
-  %5 = load double** %in.addr, align 8
+  %5 = load double*, double** %in.addr, align 8
   %arrayidx3 = getelementptr inbounds double, double* %5, i64 %idxprom2
-  %6 = load double* %arrayidx3, align 8
+  %6 = load double, double* %arrayidx3, align 8
   %add = fadd double %6, 5.000000e-01
-  %7 = load i32* %i, align 4
+  %7 = load i32, i32* %i, align 4
   %idxprom4 = sext i32 %7 to i64
-  %8 = load double** %out.addr, align 8
+  %8 = load double*, double** %out.addr, align 8
   %arrayidx5 = getelementptr inbounds double, double* %8, i64 %idxprom4
   store double %add, double* %arrayidx5, align 8
   br label %if.end
@@ -490,7 +490,7 @@ if.end:                                           ; preds = %if.then, %for.body
   br label %for.inc
 
 for.inc:                                          ; preds = %if.end
-  %9 = load i32* %i, align 4
+  %9 = load i32, i32* %i, align 4
   %dec = add nsw i32 %9, -1
   store i32 %dec, i32* %i, align 4
   br label %for.cond
diff --git a/llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll b/llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll
index bdce3ad3d04..ba8e11e5874 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/metadata-enable.ll
@@ -55,7 +55,7 @@ entry:
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %0 = load i32, i32* %arrayidx, align 4
   %add = add nsw i32 %0, %N
   %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
   store i32 %add, i32* %arrayidx2, align 4
@@ -64,7 +64,7 @@ for.body:                                         ; preds = %for.body, %entry
   br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
 
 for.end:                                          ; preds = %for.body
-  %1 = load i32* %a, align 4
+  %1 = load i32, i32* %a, align 4
   ret i32 %1
 }
 
@@ -106,7 +106,7 @@ entry:
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %0 = load i32, i32* %arrayidx, align 4
   %add = add nsw i32 %0, %N
   %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
   store i32 %add, i32* %arrayidx2, align 4
@@ -115,7 +115,7 @@ for.body:                                         ; preds = %for.body, %entry
   br i1 %exitcond, label %for.end, label %for.body
 
 for.end:                                          ; preds = %for.body
-  %1 = load i32* %a, align 4
+  %1 = load i32, i32* %a, align 4
   ret i32 %1
 }
 
@@ -157,7 +157,7 @@ entry:
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %0 = load i32, i32* %arrayidx, align 4
   %add = add nsw i32 %0, %N
   %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
   store i32 %add, i32* %arrayidx2, align 4
@@ -166,7 +166,7 @@ for.body:                                         ; preds = %for.body, %entry
   br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !2
 
 for.end:                                          ; preds = %for.body
-  %1 = load i32* %a, align 4
+  %1 = load i32, i32* %a, align 4
   ret i32 %1
 }
 
diff --git a/llvm/test/Transforms/LoopVectorize/X86/min-trip-count-switch.ll b/llvm/test/Transforms/LoopVectorize/X86/min-trip-count-switch.ll
index 3207025f167..bb972c4488a 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/min-trip-count-switch.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/min-trip-count-switch.ll
@@ -11,7 +11,7 @@ entry:
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds float, float* %a, i64 %indvars.iv
-  %0 = load float* %arrayidx, align 4
+  %0 = load float, float* %arrayidx, align 4
   %add = fadd float %0, 1.000000e+00
   store float %add, float* %arrayidx, align 4
   %indvars.iv.next = add i64 %indvars.iv, 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/no-vector.ll b/llvm/test/Transforms/LoopVectorize/X86/no-vector.ll
index 1ac18f27f83..4b464b01267 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/no-vector.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/no-vector.ll
@@ -9,7 +9,7 @@ for.body:                                         ; preds = %entry, %for.body
   %i.06 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
   %r.05 = phi i32 [ %xor, %for.body ], [ 0, %entry ]
   %arrayidx = getelementptr inbounds i8, i8* %s, i32 %i.06
-  %0 = load i8* %arrayidx, align 1
+  %0 = load i8, i8* %arrayidx, align 1
   %conv = sext i8 %0 to i32
   %xor = xor i32 %conv, %r.05
   %inc = add nsw i32 %i.06, 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll b/llvm/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll
index a7f636290ba..631361c9d47 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll
@@ -17,28 +17,28 @@ entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body.for.body_crit_edge, %entry
-  %indvars.iv.reload = load i64* %indvars.iv.reg2mem
+  %indvars.iv.reload = load i64, i64* %indvars.iv.reg2mem
   %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv.reload
-  %0 = load i32* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+  %0 = load i32, i32* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
   %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv.reload
-  %1 = load i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %1 = load i32, i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
   %idxprom3 = sext i32 %1 to i64
   %arrayidx4 = getelementptr inbounds i32, i32* %a, i64 %idxprom3
   store i32 %0, i32* %arrayidx4, align 4, !llvm.mem.parallel_loop_access !3
   %indvars.iv.next = add i64 %indvars.iv.reload, 1
   ; A new store without the parallel metadata here:
   store i64 %indvars.iv.next, i64* %indvars.iv.next.reg2mem
-  %indvars.iv.next.reload1 = load i64* %indvars.iv.next.reg2mem
+  %indvars.iv.next.reload1 = load i64, i64* %indvars.iv.next.reg2mem
   %arrayidx6 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv.next.reload1
-  %2 = load i32* %arrayidx6, align 4, !llvm.mem.parallel_loop_access !3
+  %2 = load i32, i32* %arrayidx6, align 4, !llvm.mem.parallel_loop_access !3
   store i32 %2, i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
-  %indvars.iv.next.reload = load i64* %indvars.iv.next.reg2mem
+  %indvars.iv.next.reload = load i64, i64* %indvars.iv.next.reg2mem
   %lftr.wideiv = trunc i64 %indvars.iv.next.reload to i32
   %exitcond = icmp eq i32 %lftr.wideiv, 512
   br i1 %exitcond, label %for.end, label %for.body.for.body_crit_edge, !llvm.loop !3
 
 for.body.for.body_crit_edge:                      ; preds = %for.body
-  %indvars.iv.next.reload2 = load i64* %indvars.iv.next.reg2mem
+  %indvars.iv.next.reload2 = load i64, i64* %indvars.iv.next.reg2mem
   store i64 %indvars.iv.next.reload2, i64* %indvars.iv.reg2mem
   br label %for.body
 
diff --git a/llvm/test/Transforms/LoopVectorize/X86/parallel-loops.ll b/llvm/test/Transforms/LoopVectorize/X86/parallel-loops.ll
index 83bed435de4..53061edc35c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/parallel-loops.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/parallel-loops.ll
@@ -21,15 +21,15 @@ entry:
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %0 = load i32, i32* %arrayidx, align 4
   %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
-  %1 = load i32* %arrayidx2, align 4
+  %1 = load i32, i32* %arrayidx2, align 4
   %idxprom3 = sext i32 %1 to i64
   %arrayidx4 = getelementptr inbounds i32, i32* %a, i64 %idxprom3
   store i32 %0, i32* %arrayidx4, align 4
   %indvars.iv.next = add i64 %indvars.iv, 1
   %arrayidx6 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv.next
-  %2 = load i32* %arrayidx6, align 4
+  %2 = load i32, i32* %arrayidx6, align 4
   store i32 %2, i32* %arrayidx2, align 4
   %lftr.wideiv = trunc i64 %indvars.iv.next to i32
   %exitcond = icmp eq i32 %lftr.wideiv, 512
@@ -51,9 +51,9 @@ entry:
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+  %0 = load i32, i32* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
   %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
-  %1 = load i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %1 = load i32, i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
   %idxprom3 = sext i32 %1 to i64
   %arrayidx4 = getelementptr inbounds i32, i32* %a, i64 %idxprom3
   ; This store might have originated from inlining a function with a parallel
@@ -61,7 +61,7 @@ for.body:                                         ; preds = %for.body, %entry
   store i32 %0, i32* %arrayidx4, align 4, !llvm.mem.parallel_loop_access !5
   %indvars.iv.next = add i64 %indvars.iv, 1
   %arrayidx6 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv.next
-  %2 = load i32* %arrayidx6, align 4, !llvm.mem.parallel_loop_access !3
+  %2 = load i32, i32* %arrayidx6, align 4, !llvm.mem.parallel_loop_access !3
   store i32 %2, i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
   %lftr.wideiv = trunc i64 %indvars.iv.next to i32
   %exitcond = icmp eq i32 %lftr.wideiv, 512
@@ -84,9 +84,9 @@ entry:
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4, !llvm.mem.parallel_loop_access !6
+  %0 = load i32, i32* %arrayidx, align 4, !llvm.mem.parallel_loop_access !6
   %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
-  %1 = load i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !6
+  %1 = load i32, i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !6
   %idxprom3 = sext i32 %1 to i64
   %arrayidx4 = getelementptr inbounds i32, i32* %a, i64 %idxprom3
   ; This refers to the loop marked with !7 which we are not in at the moment.
@@ -94,7 +94,7 @@ for.body:                                         ; preds = %for.body, %entry
   store i32 %0, i32* %arrayidx4, align 4, !llvm.mem.parallel_loop_access !7
   %indvars.iv.next = add i64 %indvars.iv, 1
   %arrayidx6 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv.next
-  %2 = load i32* %arrayidx6, align 4, !llvm.mem.parallel_loop_access !6
+  %2 = load i32, i32* %arrayidx6, align 4, !llvm.mem.parallel_loop_access !6
   store i32 %2, i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !6
   %lftr.wideiv = trunc i64 %indvars.iv.next to i32
   %exitcond = icmp eq i32 %lftr.wideiv, 512
diff --git a/llvm/test/Transforms/LoopVectorize/X86/powof2div.ll b/llvm/test/Transforms/LoopVectorize/X86/powof2div.ll
index af3cfe06ef9..6bc738a7d14 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/powof2div.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/powof2div.ll
@@ -7,7 +7,7 @@ target triple = "x86_64-unknown-linux-gnu"
 @Foo = common global %struct.anon zeroinitializer, align 4
 
 ;CHECK-LABEL: @foo(
-;CHECK: load <4 x i32>*
+;CHECK: load <4 x i32>, <4 x i32>*
 ;CHECK: sdiv <4 x i32>
 ;CHECK: store <4 x i32>
 
@@ -18,7 +18,7 @@ entry:
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds %struct.anon, %struct.anon* @Foo, i64 0, i32 2, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %0 = load i32, i32* %arrayidx, align 4
   %div = sdiv i32 %0, 2
   %arrayidx2 = getelementptr inbounds %struct.anon, %struct.anon* @Foo, i64 0, i32 0, i64 %indvars.iv
   store i32 %div, i32* %arrayidx2, align 4
diff --git a/llvm/test/Transforms/LoopVectorize/X86/reduction-crash.ll b/llvm/test/Transforms/LoopVectorize/X86/reduction-crash.ll
index ce2aa8963e2..3741b95d985 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/reduction-crash.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/reduction-crash.ll
@@ -14,14 +14,14 @@ bb:
   br label %bb2
 
 bb2:                                              ; preds = %bb
-  %tmp = load double* null, align 8
+  %tmp = load double, double* null, align 8
   br i1 undef, label %bb3, label %bb12
 
 bb3:                                              ; preds = %bb3, %bb2
   %tmp4 = phi double [ %tmp9, %bb3 ], [ %tmp, %bb2 ]
   %tmp5 = phi i32 [ %tmp8, %bb3 ], [ 0, %bb2 ]
   %tmp6 = getelementptr inbounds [16 x double], [16 x double]* undef, i32 0, i32 %tmp5
-  %tmp7 = load double* %tmp6, align 4
+  %tmp7 = load double, double* %tmp6, align 4
   %tmp8 = add nsw i32 %tmp5, 1
   %tmp9 = fadd fast double %tmp4, undef
   %tmp10 = getelementptr inbounds float, float* %arg, i32 %tmp5
diff --git a/llvm/test/Transforms/LoopVectorize/X86/small-size.ll b/llvm/test/Transforms/LoopVectorize/X86/small-size.ll
index 38e3c086347..47c262b11b4 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/small-size.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/small-size.ll
@@ -31,9 +31,9 @@ define void @example1() optsize {
 ; <label>:1                                       ; preds = %1, %0
   %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
   %2 = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 %indvars.iv
-  %3 = load i32* %2, align 4
+  %3 = load i32, i32* %2, align 4
   %4 = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 %indvars.iv
-  %5 = load i32* %4, align 4
+  %5 = load i32, i32* %4, align 4
   %6 = add nsw i32 %5, %3
   %7 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %indvars.iv
   store i32 %6, i32* %7, align 4
@@ -77,9 +77,9 @@ define void @example2(i32 %n, i32 %x) optsize {
   %.02 = phi i32 [ %4, %.lr.ph ], [ %n, %.preheader ]
   %4 = add nsw i32 %.02, -1
   %5 = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 %indvars.iv
-  %6 = load i32* %5, align 4
+  %6 = load i32, i32* %5, align 4
   %7 = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 %indvars.iv
-  %8 = load i32* %7, align 4
+  %8 = load i32, i32* %7, align 4
   %9 = and i32 %8, %6
   %10 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %indvars.iv
   store i32 %9, i32* %10, align 4
@@ -105,7 +105,7 @@ define void @example3(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture
   %.023 = phi i32* [ %3, %.lr.ph ], [ %q, %0 ]
   %2 = add nsw i32 %.05, -1
   %3 = getelementptr inbounds i32, i32* %.023, i64 1
-  %4 = load i32* %.023, align 16
+  %4 = load i32, i32* %.023, align 16
   %5 = getelementptr inbounds i32, i32* %.014, i64 1
   store i32 %4, i32* %.014, align 16
   %6 = icmp eq i32 %2, 0
@@ -129,7 +129,7 @@ define void @example4(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture
   %.023 = phi i32* [ %3, %.lr.ph ], [ %q, %0 ]
   %2 = add nsw i32 %.05, -1
   %3 = getelementptr inbounds i32, i32* %.023, i64 1
-  %4 = load i32* %.023, align 16
+  %4 = load i32, i32* %.023, align 16
   %5 = getelementptr inbounds i32, i32* %.014, i64 1
   store i32 %4, i32* %.014, align 16
   %6 = icmp eq i32 %2, 0
@@ -153,7 +153,7 @@ define void @example23(i16* nocapture %src, i32* nocapture %dst) optsize {
   %.013 = phi i32* [ %dst, %0 ], [ %6, %1 ]
   %i.02 = phi i32 [ 0, %0 ], [ %7, %1 ]
   %2 = getelementptr inbounds i16, i16* %.04, i64 1
-  %3 = load i16* %.04, align 2
+  %3 = load i16, i16* %.04, align 2
   %4 = zext i16 %3 to i32
   %5 = shl nuw nsw i32 %4, 7
   %6 = getelementptr inbounds i32, i32* %.013, i64 1
@@ -179,7 +179,7 @@ define void @example23b(i16* noalias nocapture %src, i32* noalias nocapture %dst
   %.013 = phi i32* [ %dst, %0 ], [ %6, %1 ]
   %i.02 = phi i32 [ 0, %0 ], [ %7, %1 ]
   %2 = getelementptr inbounds i16, i16* %.04, i64 1
-  %3 = load i16* %.04, align 2
+  %3 = load i16, i16* %.04, align 2
   %4 = zext i16 %3 to i32
   %5 = shl nuw nsw i32 %4, 7
   %6 = getelementptr inbounds i32, i32* %.013, i64 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/tripcount.ll b/llvm/test/Transforms/LoopVectorize/X86/tripcount.ll
index 9984e2d04e8..c0bbb92c2c5 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/tripcount.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/tripcount.ll
@@ -23,7 +23,7 @@ for.body.preheader:
 for.body:
   %i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
   %arrayidx = getelementptr inbounds [0 x i32], [0 x i32]* @big, i32 0, i32 %i.07
-  %0 = load i32* %arrayidx, align 4
+  %0 = load i32, i32* %arrayidx, align 4
   %neg = xor i32 %0, -1
   store i32 %neg, i32* %arrayidx, align 4
   %inc = add nsw i32 %i.07, 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/uint64_to_fp64-cost-model.ll b/llvm/test/Transforms/LoopVectorize/X86/uint64_to_fp64-cost-model.ll
index 40421d4cff0..38af11c443d 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/uint64_to_fp64-cost-model.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/uint64_to_fp64-cost-model.ll
@@ -13,7 +13,7 @@ entry:
 for.body:
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds i64, i64* %a, i64 %indvars.iv
-  %tmp = load i64* %arrayidx, align 4
+  %tmp = load i64, i64* %arrayidx, align 4
   %conv = uitofp i64 %tmp to double
   %arrayidx2 = getelementptr inbounds double, double* %b, i64 %indvars.iv
   store double %conv, double* %arrayidx2, align 4
diff --git a/llvm/test/Transforms/LoopVectorize/X86/unroll-pm.ll b/llvm/test/Transforms/LoopVectorize/X86/unroll-pm.ll
index 50fdf187499..52914b6a7c6 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/unroll-pm.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/unroll-pm.ll
@@ -18,7 +18,7 @@ define i32 @bar(i32* nocapture %A, i32 %n) nounwind uwtable ssp {
 .lr.ph:                                           ; preds = %0, %.lr.ph
   %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
   %2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
-  %3 = load i32* %2, align 4
+  %3 = load i32, i32* %2, align 4
   %4 = add nsw i32 %3, 6
   store i32 %4, i32* %2, align 4
   %indvars.iv.next = add i64 %indvars.iv, 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll b/llvm/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll
index eff6ca49edc..4411da3f0a9 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll
@@ -16,8 +16,8 @@ target triple = "x86_64-apple-macosx10.8.0"
 ; CHECK-VECTOR: ret
 ;
 ; CHECK-SCALAR-LABEL: @foo(
-; CHECK-SCALAR: load i32*
-; CHECK-SCALAR-NOT: load i32*
+; CHECK-SCALAR: load i32, i32*
+; CHECK-SCALAR-NOT: load i32, i32*
 ; CHECK-SCALAR: store i32
 ; CHECK-SCALAR-NOT: store i32
 ; CHECK-SCALAR: ret
@@ -27,7 +27,7 @@ define i32 @foo(i32* nocapture %A) nounwind uwtable ssp {
 ; <label>:1                                       ; preds = %1, %0
   %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
   %2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
-  %3 = load i32* %2, align 4
+  %3 = load i32, i32* %2, align 4
   %4 = add nsw i32 %3, 6
   store i32 %4, i32* %2, align 4
   %indvars.iv.next = add i64 %indvars.iv, 1
@@ -58,7 +58,7 @@ define i32 @bar(i32* nocapture %A, i32 %n) nounwind uwtable ssp {
 .lr.ph:                                           ; preds = %0, %.lr.ph
   %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
   %2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
-  %3 = load i32* %2, align 4
+  %3 = load i32, i32* %2, align 4
   %4 = add nsw i32 %3, 6
   store i32 %4, i32* %2, align 4
   %indvars.iv.next = add i64 %indvars.iv, 1
@@ -87,7 +87,7 @@ entry:
 for.body:
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds float, float* %B, i64 %indvars.iv
-  %0 = load float* %arrayidx, align 4
+  %0 = load float, float* %arrayidx, align 4
   %mul = fmul float %0, %N
   %arrayidx2 = getelementptr inbounds float, float* %A, i64 %indvars.iv
   store float %mul, float* %arrayidx2, align 4
diff --git a/llvm/test/Transforms/LoopVectorize/X86/unroll_selection.ll b/llvm/test/Transforms/LoopVectorize/X86/unroll_selection.ll
index 360d66d3571..71b829071e2 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/unroll_selection.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/unroll_selection.ll
@@ -17,7 +17,7 @@ define void @reg_pressure(double* nocapture %A, i32 %n) nounwind uwtable ssp {
 ; <label>:2                                       ; preds = %2, %0
   %indvars.iv = phi i64 [ %indvars.iv.next, %2 ], [ %1, %0 ]
   %3 = getelementptr inbounds double, double* %A, i64 %indvars.iv
-  %4 = load double* %3, align 8
+  %4 = load double, double* %3, align 8
   %5 = fadd double %4, 3.000000e+00
   %6 = fmul double %4, 2.000000e+00
   %7 = fadd double %5, %6
@@ -59,7 +59,7 @@ define void @small_loop(i16* nocapture %A, i64 %n) nounwind uwtable ssp {
 .lr.ph:                                           ; preds = %0, %.lr.ph
   %i.01 = phi i64 [ %5, %.lr.ph ], [ 0, %0 ]
   %2 = getelementptr inbounds i16, i16* %A, i64 %i.01
-  %3 = load i16* %2, align 2
+  %3 = load i16, i16* %2, align 2
   %4 = xor i16 %3, 3
   store i16 %4, i16* %2, align 2
   %5 = add i64 %i.01, 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.ll b/llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.ll
index e6a0d475161..10307568b85 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.ll
@@ -36,7 +36,7 @@ for.body.preheader:
 for.body:
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
   %arrayidx = getelementptr inbounds float, float* %B, i64 %indvars.iv
-  %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
+  %0 = load float, float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
   %call = tail call float @llvm.sin.f32(float %0)
   %arrayidx2 = getelementptr inbounds float, float* %A, i64 %indvars.iv
   store float %call, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
@@ -70,7 +70,7 @@ for.body.preheader:
 for.body:
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
   %arrayidx = getelementptr inbounds float, float* %B, i64 %indvars.iv
-  %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+  %0 = load float, float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
   %call = tail call float @llvm.sin.f32(float %0)
   %arrayidx2 = getelementptr inbounds float, float* %A, i64 %indvars.iv
   store float %call, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
diff --git a/llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll b/llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll
index f4bc1600c3c..8d139ac7e5a 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll
@@ -30,9 +30,9 @@ entry:
 for.body:
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds float, float* %B, i64 %indvars.iv
-  %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
+  %0 = load float, float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
   %arrayidx2 = getelementptr inbounds float, float* %A, i64 %indvars.iv
-  %1 = load float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
+  %1 = load float, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
   %add = fadd fast float %0, %1
   store float %add, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
@@ -56,9 +56,9 @@ entry:
 for.body:
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %arrayidx = getelementptr inbounds float, float* %B, i64 %indvars.iv
-  %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+  %0 = load float, float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
   %arrayidx2 = getelementptr inbounds float, float* %A, i64 %indvars.iv
-  %1 = load float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %1 = load float, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
   %add = fadd fast float %0, %1
   store float %add, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll b/llvm/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll
index 86cebf342a6..5efabe16d32 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll
@@ -16,9 +16,9 @@ define void @scalarselect(i1 %cond) {
 ; <label>:1
   %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
   %2 = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 %indvars.iv
-  %3 = load i32* %2, align 4
+  %3 = load i32, i32* %2, align 4
   %4 = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 %indvars.iv
-  %5 = load i32* %4, align 4
+  %5 = load i32, i32* %4, align 4
   %6 = add nsw i32 %5, %3
   %7 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %indvars.iv
 
@@ -43,9 +43,9 @@ define void @vectorselect(i1 %cond) {
 ; <label>:1
   %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
   %2 = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 %indvars.iv
-  %3 = load i32* %2, align 4
+  %3 = load i32, i32* %2, align 4
   %4 = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 %indvars.iv
-  %5 = load i32* %4, align 4
+  %5 = load i32, i32* %4, align 4
   %6 = add nsw i32 %5, %3
   %7 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %indvars.iv
   %8 = icmp ult i64 %indvars.iv, 8
diff --git a/llvm/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll b/llvm/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll
index 048c2603bbd..6cd3c9c3bc0 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll
@@ -19,7 +19,7 @@ target triple = "x86_64-apple-macosx10.8.0"
 ; CHECK: test_consecutive_store
 ; CHECK: The Widest type: 64 bits
 define void @test_consecutive_store(%0**, %0**, %0** nocapture) nounwind ssp uwtable align 2 {
-  %4 = load %0** %2, align 8
+  %4 = load %0*, %0** %2, align 8
   %5 = icmp eq %0** %0, %1
   br i1 %5, label %12, label %6
 
@@ -62,7 +62,7 @@ define void @test_nonconsecutive_store() nounwind ssp uwtable {
 ; <label>:3                                       ; preds = %3, %1
   %4 = phi i64 [ 0, %1 ], [ %11, %3 ]
   %5 = getelementptr inbounds [2048 x i16], [2048 x i16]* @q, i64 0, i64 %4
-  %6 = load i16* %5, align 2
+  %6 = load i16, i16* %5, align 2
   %7 = sext i16 %6 to i64
   %8 = add i64 %7, 1
   %9 = inttoptr i64 %8 to i32*
@@ -101,7 +101,7 @@ define i8 @test_consecutive_ptr_load() nounwind readonly ssp uwtable {
   %2 = phi i64 [ 0, %0 ], [ %10, %1 ]
   %3 = phi i8 [ 0, %0 ], [ %9, %1 ]
   %4 = getelementptr inbounds [1024 x i32*], [1024 x i32*]* @ia, i32 0, i64 %2
-  %5 = load i32** %4, align 4
+  %5 = load i32*, i32** %4, align 4
   %6 = ptrtoint i32* %5 to i64
   %7 = trunc i64 %6 to i8
   %8 = add i8 %3, 1
@@ -129,7 +129,7 @@ define void @test_nonconsecutive_ptr_load() nounwind ssp uwtable {
   %4 = phi i64 [ 0, %1 ], [ %10, %3 ]
   %5 = getelementptr inbounds [2048 x [8 x i32*]], [2048 x [8 x i32*]]* @p2, i64 0, i64 %4, i64 %2
   %6 = getelementptr inbounds [2048 x i16], [2048 x i16]* @q2, i64 0, i64 %4
-  %7 = load i32** %5, align 2
+  %7 = load i32*, i32** %5, align 2
   %8 = ptrtoint i32* %7 to i64
   %9 = trunc i64 %8 to i16
   store i16 %9, i16* %6, align 8
diff --git a/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll
index 92eba528c0d..2ab0ee3ea30 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll
@@ -98,10 +98,10 @@ for.body.preheader:                               ; preds = %entry
 for.body:                                         ; preds = %for.body.preheader, %for.body
   %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
   %arrayidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv, !dbg !35
-  %0 = load i32* %arrayidx, align 4, !dbg !35, !tbaa !18
+  %0 = load i32, i32* %arrayidx, align 4, !dbg !35, !tbaa !18
   %idxprom1 = sext i32 %0 to i64, !dbg !35
   %arrayidx2 = getelementptr inbounds i32, i32* %A, i64 %idxprom1, !dbg !35
-  %1 = load i32* %arrayidx2, align 4, !dbg !35, !tbaa !18
+  %1 = load i32, i32* %arrayidx2, align 4, !dbg !35, !tbaa !18
   %arrayidx4 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv, !dbg !35
   store i32 %1, i32* %arrayidx4, align 4, !dbg !35, !tbaa !18
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !32
diff --git a/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll
index cf64283b248..10e27c10cc0 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll
@@ -27,10 +27,10 @@ for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %add8 = phi i32 [ 0, %entry ], [ %add, %for.body ], !dbg !19
   %arrayidx = getelementptr inbounds [16 x i8], [16 x i8]* %cb, i64 0, i64 %indvars.iv, !dbg !19
-  %0 = load i8* %arrayidx, align 1, !dbg !19, !tbaa !21
+  %0 = load i8, i8* %arrayidx, align 1, !dbg !19, !tbaa !21
   %conv = sext i8 %0 to i32, !dbg !19
   %arrayidx2 = getelementptr inbounds [16 x i8], [16 x i8]* %cc, i64 0, i64 %indvars.iv, !dbg !19
-  %1 = load i8* %arrayidx2, align 1, !dbg !19, !tbaa !21
+  %1 = load i8, i8* %arrayidx2, align 1, !dbg !19, !tbaa !21
   %conv3 = sext i8 %1 to i32, !dbg !19
   %sub = sub i32 %conv, %conv3, !dbg !19
   %add = add nsw i32 %sub, %add8, !dbg !19
-- 
cgit v1.2.3