[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/R600/pv.ll b/llvm/test/CodeGen/R600/pv.ll
index 1908f15..26bfa0d 100644
--- a/llvm/test/CodeGen/R600/pv.ll
+++ b/llvm/test/CodeGen/R600/pv.ll
@@ -33,63 +33,63 @@
%25 = extractelement <4 x float> %reg7, i32 1
%26 = extractelement <4 x float> %reg7, i32 2
%27 = extractelement <4 x float> %reg7, i32 3
- %28 = load <4 x float> addrspace(8)* null
+ %28 = load <4 x float>, <4 x float> addrspace(8)* null
%29 = extractelement <4 x float> %28, i32 0
%30 = fmul float %0, %29
- %31 = load <4 x float> addrspace(8)* null
+ %31 = load <4 x float>, <4 x float> addrspace(8)* null
%32 = extractelement <4 x float> %31, i32 1
%33 = fmul float %0, %32
- %34 = load <4 x float> addrspace(8)* null
+ %34 = load <4 x float>, <4 x float> addrspace(8)* null
%35 = extractelement <4 x float> %34, i32 2
%36 = fmul float %0, %35
- %37 = load <4 x float> addrspace(8)* null
+ %37 = load <4 x float>, <4 x float> addrspace(8)* null
%38 = extractelement <4 x float> %37, i32 3
%39 = fmul float %0, %38
- %40 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
+ %40 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
%41 = extractelement <4 x float> %40, i32 0
%42 = fmul float %1, %41
%43 = fadd float %42, %30
- %44 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
+ %44 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
%45 = extractelement <4 x float> %44, i32 1
%46 = fmul float %1, %45
%47 = fadd float %46, %33
- %48 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
+ %48 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
%49 = extractelement <4 x float> %48, i32 2
%50 = fmul float %1, %49
%51 = fadd float %50, %36
- %52 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
+ %52 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 1)
%53 = extractelement <4 x float> %52, i32 3
%54 = fmul float %1, %53
%55 = fadd float %54, %39
- %56 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
+ %56 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
%57 = extractelement <4 x float> %56, i32 0
%58 = fmul float %2, %57
%59 = fadd float %58, %43
- %60 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
+ %60 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
%61 = extractelement <4 x float> %60, i32 1
%62 = fmul float %2, %61
%63 = fadd float %62, %47
- %64 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
+ %64 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
%65 = extractelement <4 x float> %64, i32 2
%66 = fmul float %2, %65
%67 = fadd float %66, %51
- %68 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
+ %68 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 2)
%69 = extractelement <4 x float> %68, i32 3
%70 = fmul float %2, %69
%71 = fadd float %70, %55
- %72 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 3)
+ %72 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 3)
%73 = extractelement <4 x float> %72, i32 0
%74 = fmul float %3, %73
%75 = fadd float %74, %59
- %76 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 3)
+ %76 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 3)
%77 = extractelement <4 x float> %76, i32 1
%78 = fmul float %3, %77
%79 = fadd float %78, %63
- %80 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 3)
+ %80 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 3)
%81 = extractelement <4 x float> %80, i32 2
%82 = fmul float %3, %81
%83 = fadd float %82, %67
- %84 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 3)
+ %84 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 3)
%85 = extractelement <4 x float> %84, i32 3
%86 = fmul float %3, %85
%87 = fadd float %86, %71
@@ -107,15 +107,15 @@
%99 = fmul float %4, %98
%100 = fmul float %5, %98
%101 = fmul float %6, %98
- %102 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 4)
+ %102 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 4)
%103 = extractelement <4 x float> %102, i32 0
%104 = fmul float %103, %8
%105 = fadd float %104, %20
- %106 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 4)
+ %106 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 4)
%107 = extractelement <4 x float> %106, i32 1
%108 = fmul float %107, %9
%109 = fadd float %108, %21
- %110 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 4)
+ %110 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 4)
%111 = extractelement <4 x float> %110, i32 2
%112 = fmul float %111, %10
%113 = fadd float %112, %22
@@ -123,11 +123,11 @@
%115 = call float @llvm.AMDIL.clamp.(float %109, float 0.000000e+00, float 1.000000e+00)
%116 = call float @llvm.AMDIL.clamp.(float %113, float 0.000000e+00, float 1.000000e+00)
%117 = call float @llvm.AMDIL.clamp.(float %15, float 0.000000e+00, float 1.000000e+00)
- %118 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 5)
+ %118 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 5)
%119 = extractelement <4 x float> %118, i32 0
- %120 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 5)
+ %120 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 5)
%121 = extractelement <4 x float> %120, i32 1
- %122 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 5)
+ %122 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 5)
%123 = extractelement <4 x float> %122, i32 2
%124 = insertelement <4 x float> undef, float %99, i32 0
%125 = insertelement <4 x float> %124, float %100, i32 1
@@ -138,11 +138,11 @@
%130 = insertelement <4 x float> %129, float %123, i32 2
%131 = insertelement <4 x float> %130, float 0.000000e+00, i32 3
%132 = call float @llvm.AMDGPU.dp4(<4 x float> %127, <4 x float> %131)
- %133 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 7)
+ %133 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 7)
%134 = extractelement <4 x float> %133, i32 0
- %135 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 7)
+ %135 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 7)
%136 = extractelement <4 x float> %135, i32 1
- %137 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 7)
+ %137 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 7)
%138 = extractelement <4 x float> %137, i32 2
%139 = insertelement <4 x float> undef, float %99, i32 0
%140 = insertelement <4 x float> %139, float %100, i32 1
@@ -153,31 +153,31 @@
%145 = insertelement <4 x float> %144, float %138, i32 2
%146 = insertelement <4 x float> %145, float 0.000000e+00, i32 3
%147 = call float @llvm.AMDGPU.dp4(<4 x float> %142, <4 x float> %146)
- %148 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 8)
+ %148 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 8)
%149 = extractelement <4 x float> %148, i32 0
%150 = fmul float %149, %8
- %151 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 8)
+ %151 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 8)
%152 = extractelement <4 x float> %151, i32 1
%153 = fmul float %152, %9
- %154 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 8)
+ %154 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 8)
%155 = extractelement <4 x float> %154, i32 2
%156 = fmul float %155, %10
- %157 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 9)
+ %157 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 9)
%158 = extractelement <4 x float> %157, i32 0
%159 = fmul float %158, %12
- %160 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 9)
+ %160 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 9)
%161 = extractelement <4 x float> %160, i32 1
%162 = fmul float %161, %13
- %163 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 9)
+ %163 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 9)
%164 = extractelement <4 x float> %163, i32 2
%165 = fmul float %164, %14
- %166 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 10)
+ %166 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 10)
%167 = extractelement <4 x float> %166, i32 0
%168 = fmul float %167, %16
- %169 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 10)
+ %169 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 10)
%170 = extractelement <4 x float> %169, i32 1
%171 = fmul float %170, %17
- %172 = load <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 10)
+ %172 = load <4 x float>, <4 x float> addrspace(8)* getelementptr ([1024 x <4 x float>] addrspace(8)* null, i64 0, i32 10)
%173 = extractelement <4 x float> %172, i32 2
%174 = fmul float %173, %18
%175 = fcmp uge float %132, 0.000000e+00