2014-04-19 05:22:04 +08:00
|
|
|
; REQUIRES: asserts
|
2017-05-26 05:26:32 +08:00
|
|
|
; RUN: llc < %s -mtriple=arm64-linux-gnu -mcpu=cortex-a53 -pre-RA-sched=source -enable-misched -verify-misched -debug-only=machine-scheduler -disable-machine-dce -o - 2>&1 > /dev/null | FileCheck %s
|
|
|
|
|
; RUN: llc < %s -mtriple=arm64-linux-gnu -mcpu=cortex-a53 -pre-RA-sched=source -enable-misched -verify-misched -debug-only=machine-scheduler -disable-machine-dce -o - -misched-limit=2 2>&1 > /dev/null | FileCheck %s
|
2014-04-19 05:22:04 +08:00
|
|
|
;
|
|
|
|
|
; The Cortex-A53 machine model will cause the MADD instruction to be scheduled
|
|
|
|
|
; much higher than the ADD instructions in order to hide latency. When not
|
|
|
|
|
; specifying a subtarget, the MADD will remain near the end of the block.
|
|
|
|
|
;
|
|
|
|
|
; CHECK: ********** MI Scheduling **********
|
|
|
|
|
; CHECK: main
|
2017-12-05 01:18:51 +08:00
|
|
|
; CHECK: *** Final schedule for %bb.2 ***
|
2014-04-19 05:22:04 +08:00
|
|
|
; CHECK: MADDWrrr
|
|
|
|
|
; CHECK: ADDWri
|
|
|
|
|
; CHECK: ********** INTERVALS **********
|
|
|
|
|
@main.x = private unnamed_addr constant [8 x i32] [i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1], align 4
|
|
|
|
|
@main.y = private unnamed_addr constant [8 x i32] [i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2], align 4
|
|
|
|
|
|
|
|
|
|
; Function Attrs: nounwind
|
|
|
|
|
define i32 @main() #0 {
|
|
|
|
|
entry:
|
|
|
|
|
%retval = alloca i32, align 4
|
|
|
|
|
%x = alloca [8 x i32], align 4
|
|
|
|
|
%y = alloca [8 x i32], align 4
|
|
|
|
|
%i = alloca i32, align 4
|
|
|
|
|
%xx = alloca i32, align 4
|
|
|
|
|
%yy = alloca i32, align 4
|
|
|
|
|
store i32 0, i32* %retval
|
|
|
|
|
%0 = bitcast [8 x i32]* %x to i8*
|
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)
Summary:
This is a resurrection of work first proposed and discussed in Aug 2015:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.
This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.
In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
require that the alignments for source & dest be equal.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)
Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.
s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g
The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use
getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reviewers: pete, hfinkel, lhames, reames, bollu
Reviewed By: reames
Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits
Differential Revision: https://reviews.llvm.org/D41675
llvm-svn: 322965
2018-01-20 01:13:12 +08:00
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 bitcast ([8 x i32]* @main.x to i8*), i64 32, i1 false)
|
2014-04-19 05:22:04 +08:00
|
|
|
%1 = bitcast [8 x i32]* %y to i8*
|
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)
Summary:
This is a resurrection of work first proposed and discussed in Aug 2015:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.
This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.
In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
require that the alignments for source & dest be equal.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)
Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.
s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g
The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use
getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reviewers: pete, hfinkel, lhames, reames, bollu
Reviewed By: reames
Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits
Differential Revision: https://reviews.llvm.org/D41675
llvm-svn: 322965
2018-01-20 01:13:12 +08:00
|
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %1, i8* align 4 bitcast ([8 x i32]* @main.y to i8*), i64 32, i1 false)
|
2014-04-19 05:22:04 +08:00
|
|
|
store i32 0, i32* %xx, align 4
|
|
|
|
|
store i32 0, i32* %yy, align 4
|
|
|
|
|
store i32 0, i32* %i, align 4
|
|
|
|
|
br label %for.cond
|
|
|
|
|
|
|
|
|
|
for.cond: ; preds = %for.inc, %entry
|
2015-02-28 05:17:42 +08:00
|
|
|
%2 = load i32, i32* %i, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%cmp = icmp slt i32 %2, 8
|
|
|
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
|
|
|
|
|
|
for.body: ; preds = %for.cond
|
2015-02-28 05:17:42 +08:00
|
|
|
%3 = load i32, i32* %i, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%idxprom = sext i32 %3 to i64
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx = getelementptr inbounds [8 x i32], [8 x i32]* %x, i32 0, i64 %idxprom
|
2015-02-28 05:17:42 +08:00
|
|
|
%4 = load i32, i32* %arrayidx, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%add = add nsw i32 %4, 1
|
|
|
|
|
store i32 %add, i32* %xx, align 4
|
2015-02-28 05:17:42 +08:00
|
|
|
%5 = load i32, i32* %xx, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%add1 = add nsw i32 %5, 12
|
|
|
|
|
store i32 %add1, i32* %xx, align 4
|
2015-02-28 05:17:42 +08:00
|
|
|
%6 = load i32, i32* %xx, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%add2 = add nsw i32 %6, 23
|
|
|
|
|
store i32 %add2, i32* %xx, align 4
|
2015-02-28 05:17:42 +08:00
|
|
|
%7 = load i32, i32* %xx, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%add3 = add nsw i32 %7, 34
|
|
|
|
|
store i32 %add3, i32* %xx, align 4
|
2015-02-28 05:17:42 +08:00
|
|
|
%8 = load i32, i32* %i, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%idxprom4 = sext i32 %8 to i64
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%arrayidx5 = getelementptr inbounds [8 x i32], [8 x i32]* %y, i32 0, i64 %idxprom4
|
2015-02-28 05:17:42 +08:00
|
|
|
%9 = load i32, i32* %arrayidx5, align 4
|
|
|
|
|
%10 = load i32, i32* %yy, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%mul = mul nsw i32 %10, %9
|
|
|
|
|
store i32 %mul, i32* %yy, align 4
|
|
|
|
|
br label %for.inc
|
|
|
|
|
|
|
|
|
|
for.inc: ; preds = %for.body
|
2015-02-28 05:17:42 +08:00
|
|
|
%11 = load i32, i32* %i, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%inc = add nsw i32 %11, 1
|
|
|
|
|
store i32 %inc, i32* %i, align 4
|
|
|
|
|
br label %for.cond
|
|
|
|
|
|
|
|
|
|
for.end: ; preds = %for.cond
|
2015-02-28 05:17:42 +08:00
|
|
|
%12 = load i32, i32* %xx, align 4
|
|
|
|
|
%13 = load i32, i32* %yy, align 4
|
2014-04-19 05:22:04 +08:00
|
|
|
%add6 = add nsw i32 %12, %13
|
|
|
|
|
ret i32 %add6
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
; The Cortex-A53 machine model will cause the FDIVvvv_42 to be raised to
|
|
|
|
|
; hide latency. Whereas normally there would only be a single FADDvvv_4s
|
|
|
|
|
; after it, this test checks to make sure there are more than one.
|
|
|
|
|
;
|
|
|
|
|
; CHECK: ********** MI Scheduling **********
|
2017-12-05 01:18:51 +08:00
|
|
|
; CHECK: neon4xfloat:%bb.0
|
|
|
|
|
; CHECK: *** Final schedule for %bb.0 ***
|
2014-04-19 05:22:04 +08:00
|
|
|
; CHECK: FDIVv4f32
|
|
|
|
|
; CHECK: FADDv4f32
|
|
|
|
|
; CHECK: FADDv4f32
|
|
|
|
|
; CHECK: ********** INTERVALS **********
|
|
|
|
|
define <4 x float> @neon4xfloat(<4 x float> %A, <4 x float> %B) {
|
|
|
|
|
%tmp1 = fadd <4 x float> %A, %B;
|
|
|
|
|
%tmp2 = fadd <4 x float> %A, %tmp1;
|
|
|
|
|
%tmp3 = fadd <4 x float> %A, %tmp2;
|
|
|
|
|
%tmp4 = fadd <4 x float> %A, %tmp3;
|
|
|
|
|
%tmp5 = fadd <4 x float> %A, %tmp4;
|
|
|
|
|
%tmp6 = fadd <4 x float> %A, %tmp5;
|
|
|
|
|
%tmp7 = fadd <4 x float> %A, %tmp6;
|
|
|
|
|
%tmp8 = fadd <4 x float> %A, %tmp7;
|
|
|
|
|
%tmp9 = fdiv <4 x float> %A, %B;
|
|
|
|
|
%tmp10 = fadd <4 x float> %tmp8, %tmp9;
|
|
|
|
|
|
|
|
|
|
ret <4 x float> %tmp10
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; Function Attrs: nounwind
|
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)
Summary:
This is a resurrection of work first proposed and discussed in Aug 2015:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.
This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.
In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
require that the alignments for source & dest be equal.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)
Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.
s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g
The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use
getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reviewers: pete, hfinkel, lhames, reames, bollu
Reviewed By: reames
Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits
Differential Revision: https://reviews.llvm.org/D41675
llvm-svn: 322965
2018-01-20 01:13:12 +08:00
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) #1
|
2014-04-19 05:22:04 +08:00
|
|
|
|
2021-05-25 01:43:40 +08:00
|
|
|
attributes #0 = { nounwind "less-precise-fpmad"="false" "frame-pointer"="all" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|
2014-04-19 05:22:04 +08:00
|
|
|
attributes #1 = { nounwind }
|
2014-05-20 06:59:51 +08:00
|
|
|
|
|
|
|
|
|
2014-05-22 00:19:51 +08:00
|
|
|
; Regression Test for PR19761
|
|
|
|
|
; [ARM64] Cortex-a53 schedule mode can't handle NEON post-increment load
|
2014-05-20 06:59:51 +08:00
|
|
|
;
|
|
|
|
|
; Nothing explicit to check other than llc not crashing.
|
|
|
|
|
define { <16 x i8>, <16 x i8> } @test_v16i8_post_imm_ld2(i8* %A, i8** %ptr) {
|
2014-05-24 20:50:23 +08:00
|
|
|
%ld2 = tail call { <16 x i8>, <16 x i8> } @llvm.aarch64.neon.ld2.v16i8.p0i8(i8* %A)
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%tmp = getelementptr i8, i8* %A, i32 32
|
2014-05-20 06:59:51 +08:00
|
|
|
store i8* %tmp, i8** %ptr
|
|
|
|
|
ret { <16 x i8>, <16 x i8> } %ld2
|
|
|
|
|
}
|
|
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
declare { <16 x i8>, <16 x i8> } @llvm.aarch64.neon.ld2.v16i8.p0i8(i8*)
|
2014-06-27 12:57:05 +08:00
|
|
|
|
|
|
|
|
; Regression Test for PR20057.
|
|
|
|
|
;
|
|
|
|
|
; Cortex-A53 machine model stalls on A53UnitFPMDS contention. Instructions that
|
|
|
|
|
; are otherwise ready are jammed in the pending queue.
|
|
|
|
|
; CHECK: ********** MI Scheduling **********
|
|
|
|
|
; CHECK: testResourceConflict
|
2017-12-05 01:18:51 +08:00
|
|
|
; CHECK: *** Final schedule for %bb.0 ***
|
2014-06-27 12:57:05 +08:00
|
|
|
; CHECK: BRK
|
|
|
|
|
; CHECK: ********** INTERVALS **********
|
|
|
|
|
define void @testResourceConflict(float* %ptr) {
|
|
|
|
|
entry:
|
|
|
|
|
%add1 = fadd float undef, undef
|
|
|
|
|
%mul2 = fmul float undef, undef
|
|
|
|
|
%add3 = fadd float %mul2, undef
|
|
|
|
|
%mul4 = fmul float undef, %add3
|
|
|
|
|
%add5 = fadd float %mul4, undef
|
|
|
|
|
%sub6 = fsub float 0.000000e+00, undef
|
|
|
|
|
%sub7 = fsub float %add5, undef
|
|
|
|
|
%div8 = fdiv float 1.000000e+00, undef
|
|
|
|
|
%mul9 = fmul float %div8, %sub7
|
|
|
|
|
%mul14 = fmul float %sub6, %div8
|
|
|
|
|
%mul10 = fsub float -0.000000e+00, %mul14
|
|
|
|
|
%mul15 = fmul float undef, %div8
|
|
|
|
|
%mul11 = fsub float -0.000000e+00, %mul15
|
|
|
|
|
%mul12 = fmul float 0.000000e+00, %div8
|
|
|
|
|
%mul13 = fmul float %add1, %mul9
|
|
|
|
|
%mul21 = fmul float %add5, %mul11
|
|
|
|
|
%add22 = fadd float %mul13, %mul21
|
|
|
|
|
store float %add22, float* %ptr, align 4
|
|
|
|
|
%mul28 = fmul float %add1, %mul10
|
|
|
|
|
%mul33 = fmul float %add5, %mul12
|
|
|
|
|
%add34 = fadd float %mul33, %mul28
|
|
|
|
|
store float %add34, float* %ptr, align 4
|
|
|
|
|
%mul240 = fmul float undef, %mul9
|
|
|
|
|
%add246 = fadd float %mul240, undef
|
|
|
|
|
store float %add246, float* %ptr, align 4
|
|
|
|
|
%mul52 = fmul float undef, %mul10
|
|
|
|
|
%mul57 = fmul float undef, %mul12
|
|
|
|
|
%add58 = fadd float %mul57, %mul52
|
|
|
|
|
store float %add58, float* %ptr, align 4
|
|
|
|
|
%mul27 = fmul float 0.000000e+00, %mul9
|
|
|
|
|
%mul81 = fmul float undef, %mul10
|
|
|
|
|
%add82 = fadd float %mul27, %mul81
|
|
|
|
|
store float %add82, float* %ptr, align 4
|
|
|
|
|
call void @llvm.trap()
|
|
|
|
|
unreachable
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare void @llvm.trap()
|
2014-07-03 00:46:08 +08:00
|
|
|
|
|
|
|
|
; Regression test for PR20057: "permanent hazard"'
|
|
|
|
|
; Resource contention on LDST.
|
|
|
|
|
; CHECK: ********** MI Scheduling **********
|
|
|
|
|
; CHECK: testLdStConflict
|
2017-12-05 01:18:51 +08:00
|
|
|
; CHECK: *** Final schedule for %bb.1 ***
|
2014-07-03 00:46:08 +08:00
|
|
|
; CHECK: LD4Fourv2d
|
|
|
|
|
; CHECK: STRQui
|
|
|
|
|
; CHECK: ********** INTERVALS **********
|
[AArch64] Split 0 vector stores into scalar store pairs.
Summary:
Replace a splat of zeros to a vector store by scalar stores of WZR/XZR.
The load store optimizer pass will merge them to store pair stores.
This should be better than a movi to create the vector zero followed by
a vector store if the zero constant is not re-used, since one
instructions and one register live range will be removed.
For example, the final generated code should be:
stp xzr, xzr, [x0]
instead of:
movi v0.2d, #0
str q0, [x0]
Reviewers: t.p.northover, mcrosier, MatzeB, jmolloy
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D26561
llvm-svn: 286875
2016-11-15 03:39:04 +08:00
|
|
|
define void @testLdStConflict(<2 x i64> %v) {
|
2014-07-03 00:46:08 +08:00
|
|
|
entry:
|
|
|
|
|
br label %loop
|
|
|
|
|
|
|
|
|
|
loop:
|
|
|
|
|
%0 = call { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld4.v2i64.p0i8(i8* null)
|
|
|
|
|
%ptr = bitcast i8* undef to <2 x i64>*
|
[AArch64] Split 0 vector stores into scalar store pairs.
Summary:
Replace a splat of zeros to a vector store by scalar stores of WZR/XZR.
The load store optimizer pass will merge them to store pair stores.
This should be better than a movi to create the vector zero followed by
a vector store if the zero constant is not re-used, since one
instructions and one register live range will be removed.
For example, the final generated code should be:
stp xzr, xzr, [x0]
instead of:
movi v0.2d, #0
str q0, [x0]
Reviewers: t.p.northover, mcrosier, MatzeB, jmolloy
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D26561
llvm-svn: 286875
2016-11-15 03:39:04 +08:00
|
|
|
store <2 x i64> %v, <2 x i64>* %ptr, align 4
|
2014-07-03 00:46:08 +08:00
|
|
|
%ptr1 = bitcast i8* undef to <2 x i64>*
|
[AArch64] Split 0 vector stores into scalar store pairs.
Summary:
Replace a splat of zeros to a vector store by scalar stores of WZR/XZR.
The load store optimizer pass will merge them to store pair stores.
This should be better than a movi to create the vector zero followed by
a vector store if the zero constant is not re-used, since one
instructions and one register live range will be removed.
For example, the final generated code should be:
stp xzr, xzr, [x0]
instead of:
movi v0.2d, #0
str q0, [x0]
Reviewers: t.p.northover, mcrosier, MatzeB, jmolloy
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D26561
llvm-svn: 286875
2016-11-15 03:39:04 +08:00
|
|
|
store <2 x i64> %v, <2 x i64>* %ptr1, align 4
|
2014-07-03 00:46:08 +08:00
|
|
|
%ptr2 = bitcast i8* undef to <2 x i64>*
|
[AArch64] Split 0 vector stores into scalar store pairs.
Summary:
Replace a splat of zeros to a vector store by scalar stores of WZR/XZR.
The load store optimizer pass will merge them to store pair stores.
This should be better than a movi to create the vector zero followed by
a vector store if the zero constant is not re-used, since one
instructions and one register live range will be removed.
For example, the final generated code should be:
stp xzr, xzr, [x0]
instead of:
movi v0.2d, #0
str q0, [x0]
Reviewers: t.p.northover, mcrosier, MatzeB, jmolloy
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D26561
llvm-svn: 286875
2016-11-15 03:39:04 +08:00
|
|
|
store <2 x i64> %v, <2 x i64>* %ptr2, align 4
|
2014-07-03 00:46:08 +08:00
|
|
|
%ptr3 = bitcast i8* undef to <2 x i64>*
|
[AArch64] Split 0 vector stores into scalar store pairs.
Summary:
Replace a splat of zeros to a vector store by scalar stores of WZR/XZR.
The load store optimizer pass will merge them to store pair stores.
This should be better than a movi to create the vector zero followed by
a vector store if the zero constant is not re-used, since one
instructions and one register live range will be removed.
For example, the final generated code should be:
stp xzr, xzr, [x0]
instead of:
movi v0.2d, #0
str q0, [x0]
Reviewers: t.p.northover, mcrosier, MatzeB, jmolloy
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D26561
llvm-svn: 286875
2016-11-15 03:39:04 +08:00
|
|
|
store <2 x i64> %v, <2 x i64>* %ptr3, align 4
|
2014-07-03 00:46:08 +08:00
|
|
|
%ptr4 = bitcast i8* undef to <2 x i64>*
|
[AArch64] Split 0 vector stores into scalar store pairs.
Summary:
Replace a splat of zeros to a vector store by scalar stores of WZR/XZR.
The load store optimizer pass will merge them to store pair stores.
This should be better than a movi to create the vector zero followed by
a vector store if the zero constant is not re-used, since one
instructions and one register live range will be removed.
For example, the final generated code should be:
stp xzr, xzr, [x0]
instead of:
movi v0.2d, #0
str q0, [x0]
Reviewers: t.p.northover, mcrosier, MatzeB, jmolloy
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D26561
llvm-svn: 286875
2016-11-15 03:39:04 +08:00
|
|
|
store <2 x i64> %v, <2 x i64>* %ptr4, align 4
|
2014-07-03 00:46:08 +08:00
|
|
|
br label %loop
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
declare { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld4.v2i64.p0i8(i8*)
|