2011-05-27 05:47:59 +08:00
; RUN: llc < %s - | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:32:64-v128:32:128-a0:0:32-n32"
target triple = "thumbv7-apple-macosx10.6.7"
2011-06-03 04:07:12 +08:00
;CHECK: vadd.f32 q4, q8, q8
[Thumb] Teach ISel how to lower compares of AND bitmasks efficiently
This is essentially a recommit of r285893, but with a correctness fix. The
problem of the original commit was that this:
bic r5, r7, #31
cbz r5, .LBB2_10
got rewritten into:
lsrs r5, r7, #5
beq .LBB2_10
The result in destination register r5 is not the same and this is incorrect
when r5 is not dead. So this fix includes checking the uses of the AND
destination register. And also, compared to the original commit, some regression
tests didn't need changing anymore because of this extra check.
For completeness, this was the original commit message:
For the common pattern (CMPZ (AND x, #bitmask), #0), we can do some more
efficient instruction selection if the bitmask is one consecutive sequence of
set bits (32 - clz(bm) - ctz(bm) == popcount(bm)).
1) If the bitmask touches the LSB, then we can remove all the upper bits and
set the flags by doing one LSLS.
2) If the bitmask touches the MSB, then we can remove all the lower bits and
set the flags with one LSRS.
3) If the bitmask has popcount == 1 (only one set bit), we can shift that bit
into the sign bit with one LSLS and change the condition query from NE/EQ to
MI/PL (we could also implement this by shifting into the carry bit and
branching on BCC/BCS).
4) Otherwise, we can emit a sequence of LSLS+LSRS to remove the upper and lower
zero bits of the mask.
1-3 require only one 16-bit instruction and can elide the CMP. 4 requires two
16-bit instructions but can elide the CMP and doesn't require materializing a
complex immediate, so is also a win.
Differential Revision: https://reviews.llvm.org/D27761
llvm-svn: 289794
2016-12-15 17:38:59 +08:00
;CHECK-NEXT: LBB0_1
2012-08-14 13:19:07 +08:00
2016-12-02 08:37:57 +08:00
;CHECK: @DEBUG_VALUE: x <- %Q4{{$}}
;CHECK-NEXT: @DEBUG_VALUE: y <- %Q4{{$}}
;CHECK: beq LBB0_1
2011-06-03 04:07:12 +08:00
2011-05-27 05:47:59 +08:00
@.str = external constant [ 13 x i8 ]
declare < 4 x float > @test0001 ( float ) nounwind readnone ssp
2015-11-06 06:03:56 +08:00
define i32 @main ( i32 %argc , i8 * * nocapture %argv , i1 %cond ) nounwind ssp !dbg !10 {
2011-05-27 05:47:59 +08:00
entry:
br label %for.body9
for.body9: ; preds = %for.body9, %entry
%add19 = fadd < 4 x float > undef , < float 0.000000e+00 , float 0.000000e+00 , float 0.000000e+00 , float 1.000000e+00 > , !dbg !39
2015-04-30 00:38:44 +08:00
tail call void @llvm.dbg.value ( metadata < 4 x float > %add19 , i64 0 , metadata !27 , metadata !DIExpression ( ) ) , !dbg !39
2011-05-27 05:47:59 +08:00
%add20 = fadd < 4 x float > undef , < float 0.000000e+00 , float 0.000000e+00 , float 0.000000e+00 , float 1.000000e+00 > , !dbg !39
2015-04-30 00:38:44 +08:00
tail call void @llvm.dbg.value ( metadata < 4 x float > %add20 , i64 0 , metadata !28 , metadata !DIExpression ( ) ) , !dbg !39
2012-08-14 13:19:07 +08:00
br i1 %cond , label %for.end54 , label %for.body9 , !dbg !44
2011-05-27 05:47:59 +08:00
for.end54: ; preds = %for.body9
%tmp115 = extractelement < 4 x float > %add19 , i32 1
%conv6.i75 = fpext float %tmp115 to double , !dbg !45
[opaque pointer type] Add textual IR support for explicit type parameter to the call instruction
See r230786 and r230794 for similar changes to gep and load
respectively.
Call is a bit different because it often doesn't have a single explicit
type - usually the type is deduced from the arguments, and just the
return type is explicit. In those cases there's no need to change the
IR.
When that's not the case, the IR usually contains the pointer type of
the first operand - but since typed pointers are going away, that
representation is insufficient so I'm just stripping the "pointerness"
of the explicit type away.
This does make the IR a bit weird - it /sort of/ reads like the type of
the first operand: "call void () %x(" but %x is actually of type "void
()*" and will eventually be just of type "ptr". But this seems not too
bad and I don't think it would benefit from repeating the type
("void (), void () * %x(" and then eventually "void (), ptr %x(") as has
been done with gep and load.
This also has a side benefit: since the explicit type is no longer a
pointer, there's no ambiguity between an explicit type and a function
that returns a function pointer. Previously this case needed an explicit
type (eg: a function returning a void() function was written as
"call void () () * @x(" rather than "call void () * @x(" because of the
ambiguity between a function returning a pointer to a void() function
and a function returning void).
No ambiguity means even function pointer return types can just be
written alone, without writing the whole function's type.
This leaves /only/ the varargs case where the explicit type is required.
Given the special type syntax in call instructions, the regex-fu used
for migration was a bit more involved in its own unique way (as every
one of these is) so here it is. Use it in conjunction with the apply.sh
script and associated find/xargs commands I've provided in rr230786 to
migrate your out of tree tests. Do let me know if any of this doesn't
cover your cases & we can iterate on a more general script/regexes to
help others with out of tree tests.
About 9 test cases couldn't be automatically migrated - half of those
were functions returning function pointers, where I just had to manually
delete the function argument types now that we didn't need an explicit
function type there. The other half were typedefs of function types used
in calls - just had to manually drop the * from those.
import fileinput
import sys
import re
pat = re.compile(r'((?:=|:|^|\s)call\s(?:[^@]*?))(\s*$|\s*(?:(?:\[\[[a-zA-Z0-9_]+\]\]|[@%](?:(")?[\\\?@a-zA-Z0-9_.]*?(?(3)"|)|{{.*}}))(?:\(|$)|undef|inttoptr|bitcast|null|asm).*$)')
addrspace_end = re.compile(r"addrspace\(\d+\)\s*\*$")
func_end = re.compile("(?:void.*|\)\s*)\*$")
def conv(match, line):
if not match or re.search(addrspace_end, match.group(1)) or not re.search(func_end, match.group(1)):
return line
return line[:match.start()] + match.group(1)[:match.group(1).rfind('*')].rstrip() + match.group(2) + line[match.end():]
for line in sys.stdin:
sys.stdout.write(conv(re.search(pat, line), line))
llvm-svn: 235145
2015-04-17 07:24:18 +08:00
%call.i82 = tail call i32 ( i8 * , . . . ) @printf ( i8 * getelementptr inbounds ( [ 13 x i8 ] , [ 13 x i8 ] * @.str , i32 0 , i32 0 ) , double undef , double %conv6.i75 , double undef , double undef ) nounwind , !dbg !45
2011-05-27 05:47:59 +08:00
%tmp116 = extractelement < 4 x float > %add20 , i32 1
%conv6.i76 = fpext float %tmp116 to double , !dbg !45
[opaque pointer type] Add textual IR support for explicit type parameter to the call instruction
See r230786 and r230794 for similar changes to gep and load
respectively.
Call is a bit different because it often doesn't have a single explicit
type - usually the type is deduced from the arguments, and just the
return type is explicit. In those cases there's no need to change the
IR.
When that's not the case, the IR usually contains the pointer type of
the first operand - but since typed pointers are going away, that
representation is insufficient so I'm just stripping the "pointerness"
of the explicit type away.
This does make the IR a bit weird - it /sort of/ reads like the type of
the first operand: "call void () %x(" but %x is actually of type "void
()*" and will eventually be just of type "ptr". But this seems not too
bad and I don't think it would benefit from repeating the type
("void (), void () * %x(" and then eventually "void (), ptr %x(") as has
been done with gep and load.
This also has a side benefit: since the explicit type is no longer a
pointer, there's no ambiguity between an explicit type and a function
that returns a function pointer. Previously this case needed an explicit
type (eg: a function returning a void() function was written as
"call void () () * @x(" rather than "call void () * @x(" because of the
ambiguity between a function returning a pointer to a void() function
and a function returning void).
No ambiguity means even function pointer return types can just be
written alone, without writing the whole function's type.
This leaves /only/ the varargs case where the explicit type is required.
Given the special type syntax in call instructions, the regex-fu used
for migration was a bit more involved in its own unique way (as every
one of these is) so here it is. Use it in conjunction with the apply.sh
script and associated find/xargs commands I've provided in rr230786 to
migrate your out of tree tests. Do let me know if any of this doesn't
cover your cases & we can iterate on a more general script/regexes to
help others with out of tree tests.
About 9 test cases couldn't be automatically migrated - half of those
were functions returning function pointers, where I just had to manually
delete the function argument types now that we didn't need an explicit
function type there. The other half were typedefs of function types used
in calls - just had to manually drop the * from those.
import fileinput
import sys
import re
pat = re.compile(r'((?:=|:|^|\s)call\s(?:[^@]*?))(\s*$|\s*(?:(?:\[\[[a-zA-Z0-9_]+\]\]|[@%](?:(")?[\\\?@a-zA-Z0-9_.]*?(?(3)"|)|{{.*}}))(?:\(|$)|undef|inttoptr|bitcast|null|asm).*$)')
addrspace_end = re.compile(r"addrspace\(\d+\)\s*\*$")
func_end = re.compile("(?:void.*|\)\s*)\*$")
def conv(match, line):
if not match or re.search(addrspace_end, match.group(1)) or not re.search(func_end, match.group(1)):
return line
return line[:match.start()] + match.group(1)[:match.group(1).rfind('*')].rstrip() + match.group(2) + line[match.end():]
for line in sys.stdin:
sys.stdout.write(conv(re.search(pat, line), line))
llvm-svn: 235145
2015-04-17 07:24:18 +08:00
%call.i83 = tail call i32 ( i8 * , . . . ) @printf ( i8 * getelementptr inbounds ( [ 13 x i8 ] , [ 13 x i8 ] * @.str , i32 0 , i32 0 ) , double undef , double %conv6.i76 , double undef , double undef ) nounwind , !dbg !45
2011-05-27 05:47:59 +08:00
ret i32 0 , !dbg !49
}
declare i32 @printf ( i8 * nocapture , . . . ) nounwind
Move the complex address expression out of DIVariable and into an extra
argument of the llvm.dbg.declare/llvm.dbg.value intrinsics.
Previously, DIVariable was a variable-length field that has an optional
reference to a Metadata array consisting of a variable number of
complex address expressions. In the case of OpPiece expressions this is
wasting a lot of storage in IR, because when an aggregate type is, e.g.,
SROA'd into all of its n individual members, the IR will contain n copies
of the DIVariable, all alike, only differing in the complex address
reference at the end.
By making the complex address into an extra argument of the
dbg.value/dbg.declare intrinsics, all of the pieces can reference the
same variable and the complex address expressions can be uniqued across
the CU, too.
Down the road, this will allow us to move other flags, such as
"indirection" out of the DIVariable, too.
The new intrinsics look like this:
declare void @llvm.dbg.declare(metadata %storage, metadata %var, metadata %expr)
declare void @llvm.dbg.value(metadata %storage, i64 %offset, metadata %var, metadata %expr)
This patch adds a new LLVM-local tag to DIExpressions, so we can detect
and pretty-print DIExpression metadata nodes.
What this patch doesn't do:
This patch does not touch the "Indirect" field in DIVariable; but moving
that into the expression would be a natural next step.
http://reviews.llvm.org/D4919
rdar://problem/17994491
Thanks to dblaikie and dexonsmith for reviewing this patch!
Note: I accidentally committed a bogus older version of this patch previously.
llvm-svn: 218787
2014-10-02 02:55:02 +08:00
declare void @llvm.dbg.value ( metadata , i64 , metadata , metadata ) nounwind readnone
2011-05-27 05:47:59 +08:00
2013-11-23 09:16:29 +08:00
!llvm.module.flags = ! { !56 }
2014-07-26 00:05:18 +08:00
!llvm.dbg.cu = ! { !2 }
2013-11-23 09:16:29 +08:00
2016-04-15 23:57:41 +08:00
!0 = distinct !DISubprogram ( name: "test0001" , line: 3 , isLocal: false , isDefinition: true , virtualIndex: 6 , flags: D I F l a g P r o t o t y p e d , isOptimized: true , unit: !2 , file: !54 , scope: null , type: !3 , variables: !51 )
2015-04-30 00:38:44 +08:00
!1 = !DIFile ( filename: "build2.c" , directory: "/private/tmp" )
2016-04-15 23:57:41 +08:00
!2 = distinct !DICompileUnit ( language: D W _ L A N G _ C 99 , producer: "clang version 3.0 (trunk 129915)" , isOptimized: true , emissionKind: F u l l D e b u g , file: !54 , enums: ! { } , retainedTypes: ! { } , imports: null )
2015-04-30 00:38:44 +08:00
!3 = !DISubroutineType ( types: !4 )
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!4 = ! { !5 }
2015-04-30 00:38:44 +08:00
!5 = !DIDerivedType ( tag: D W _ T A G _ t y p e d e f , name: "v4f32" , line: 14 , file: !54 , scope: !2 , baseType: !6 )
!6 = !DICompositeType ( tag: D W _ T A G _ a r r a y _ type , size: 128 , align: 128 , file: !54 , scope: !2 , baseType: !7 , elements: !8 )
!7 = !DIBasicType ( tag: D W _ T A G _ b a s e _ type , name: "float" , size: 32 , align: 32 , encoding: D W _ A T E _ float )
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!8 = ! { !9 }
2015-04-30 00:38:44 +08:00
!9 = !DISubrange ( count: 4 )
2016-04-15 23:57:41 +08:00
!10 = distinct !DISubprogram ( name: "main" , line: 59 , isLocal: false , isDefinition: true , virtualIndex: 6 , flags: D I F l a g P r o t o t y p e d , isOptimized: true , unit: !2 , file: !54 , scope: null , type: !11 , variables: !52 )
2015-04-30 00:38:44 +08:00
!11 = !DISubroutineType ( types: !12 )
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!12 = ! { !13 }
2015-04-30 00:38:44 +08:00
!13 = !DIBasicType ( tag: D W _ T A G _ b a s e _ type , name: "int" , size: 32 , align: 32 , encoding: D W _ A T E _ s i g n e d )
2016-04-15 23:57:41 +08:00
!14 = distinct !DISubprogram ( name: "printFV" , line: 41 , isLocal: true , isDefinition: true , virtualIndex: 6 , flags: D I F l a g P r o t o t y p e d , isOptimized: true , unit: !2 , file: !55 , scope: null , type: !16 , variables: !53 )
2015-04-30 00:38:44 +08:00
!15 = !DIFile ( filename: "/Volumes/Lalgate/work/llvm/projects/llvm-test/SingleSource/UnitTests/Vector/helpers.h" , directory: "/private/tmp" )
!16 = !DISubroutineType ( types: !17 )
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!17 = ! { null }
2015-08-01 02:58:39 +08:00
!18 = !DILocalVariable ( name: "a" , line: 3 , arg: 1 , scope: !0 , file: !1 , type: !7 )
!19 = !DILocalVariable ( name: "argc" , line: 59 , arg: 1 , scope: !10 , file: !1 , type: !13 )
!20 = !DILocalVariable ( name: "argv" , line: 59 , arg: 2 , scope: !10 , file: !1 , type: !21 )
2015-04-30 00:38:44 +08:00
!21 = !DIDerivedType ( tag: D W _ T A G _ p o i n t e r _ type , size: 32 , align: 32 , scope: !2 , baseType: !22 )
!22 = !DIDerivedType ( tag: D W _ T A G _ p o i n t e r _ type , size: 32 , align: 32 , scope: !2 , baseType: !23 )
!23 = !DIBasicType ( tag: D W _ T A G _ b a s e _ type , name: "char" , size: 8 , align: 8 , encoding: D W _ A T E _ s i g n e d _ c h a r )
2015-08-01 02:58:39 +08:00
!24 = !DILocalVariable ( name: "i" , line: 60 , scope: !25 , file: !1 , type: !13 )
2015-04-30 00:38:44 +08:00
!25 = distinct !DILexicalBlock ( line: 59 , column: 33 , file: !1 , scope: !10 )
2015-08-01 02:58:39 +08:00
!26 = !DILocalVariable ( name: "j" , line: 60 , scope: !25 , file: !1 , type: !13 )
!27 = !DILocalVariable ( name: "x" , line: 61 , scope: !25 , file: !1 , type: !5 )
!28 = !DILocalVariable ( name: "y" , line: 62 , scope: !25 , file: !1 , type: !5 )
!29 = !DILocalVariable ( name: "z" , line: 63 , scope: !25 , file: !1 , type: !5 )
!30 = !DILocalVariable ( name: "F" , line: 41 , arg: 1 , scope: !14 , file: !15 , type: !31 )
2015-04-30 00:38:44 +08:00
!31 = !DIDerivedType ( tag: D W _ T A G _ p o i n t e r _ type , size: 32 , align: 32 , scope: !2 , baseType: !32 )
!32 = !DIDerivedType ( tag: D W _ T A G _ t y p e d e f , name: "FV" , line: 25 , file: !55 , scope: !2 , baseType: !33 )
!33 = !DICompositeType ( tag: D W _ T A G _ u n i o n _ type , line: 22 , size: 128 , align: 128 , file: !55 , scope: !2 , elements: !34 )
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!34 = ! { !35 , !37 }
2015-04-30 00:38:44 +08:00
!35 = !DIDerivedType ( tag: D W _ T A G _ m e m b e r , name: "V" , line: 23 , size: 128 , align: 128 , file: !55 , scope: !15 , baseType: !36 )
!36 = !DIDerivedType ( tag: D W _ T A G _ t y p e d e f , name: "v4sf" , line: 3 , file: !55 , scope: !2 , baseType: !6 )
!37 = !DIDerivedType ( tag: D W _ T A G _ m e m b e r , name: "A" , line: 24 , size: 128 , align: 32 , file: !55 , scope: !15 , baseType: !38 )
!38 = !DICompositeType ( tag: D W _ T A G _ a r r a y _ type , size: 128 , align: 32 , scope: !2 , baseType: !7 , elements: !8 )
!39 = !DILocation ( line: 79 , column: 7 , scope: !40 )
!40 = distinct !DILexicalBlock ( line: 75 , column: 35 , file: !1 , scope: !41 )
!41 = distinct !DILexicalBlock ( line: 75 , column: 5 , file: !1 , scope: !42 )
!42 = distinct !DILexicalBlock ( line: 71 , column: 32 , file: !1 , scope: !43 )
!43 = distinct !DILexicalBlock ( line: 71 , column: 3 , file: !1 , scope: !25 )
!44 = !DILocation ( line: 75 , column: 5 , scope: !42 )
!45 = !DILocation ( line: 42 , column: 2 , scope: !46 , inlinedAt: !48 )
!46 = distinct !DILexicalBlock ( line: 42 , column: 2 , file: !15 , scope: !47 )
!47 = distinct !DILexicalBlock ( line: 41 , column: 28 , file: !15 , scope: !14 )
!48 = !DILocation ( line: 95 , column: 3 , scope: !25 )
!49 = !DILocation ( line: 99 , column: 3 , scope: !25 )
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!51 = ! { !18 }
!52 = ! { !19 , !20 , !24 , !26 , !27 , !28 , !29 }
!53 = ! { !30 }
2015-04-30 00:38:44 +08:00
!54 = !DIFile ( filename: "build2.c" , directory: "/private/tmp" )
!55 = !DIFile ( filename: "/Volumes/Lalgate/work/llvm/projects/llvm-test/SingleSource/UnitTests/Vector/helpers.h" , directory: "/private/tmp" )
2015-03-04 01:24:31 +08:00
!56 = ! { i32 1 , !"Debug Info Version" , i32 3 }
