llvm-project/llvm/test/CodeGen/X86/tail-dup-merge-loop-headers.ll

191 lines
8.1 KiB
LLVM
Raw Normal View History

; RUN: llc -O2 -o - %s | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; Function Attrs: nounwind uwtable
; CHECK-LABEL: tail_dup_merge_loops
; CHECK: # %entry
; CHECK-NOT: # %{{[a-zA-Z_]+}}
; CHECK: # %inner_loop_exit
; CHECK-NOT: # %{{[a-zA-Z_]+}}
; CHECK: # %inner_loop_latch
; CHECK-NOT: # %{{[a-zA-Z_]+}}
Generalize MergeBlockIntoPredecessor. Replace uses of MergeBasicBlockIntoOnlyPred. Summary: Two utils methods have essentially the same functionality. This is an attempt to merge them into one. 1. lib/Transforms/Utils/Local.cpp : MergeBasicBlockIntoOnlyPred 2. lib/Transforms/Utils/BasicBlockUtils.cpp : MergeBlockIntoPredecessor Prior to the patch: 1. MergeBasicBlockIntoOnlyPred Updates either DomTree or DeferredDominance Moves all instructions from Pred to BB, deletes Pred Asserts BB has single predecessor If address was taken, replace the block address with constant 1 (?) 2. MergeBlockIntoPredecessor Updates DomTree, LoopInfo and MemoryDependenceResults Moves all instruction from BB to Pred, deletes BB Returns if doesn't have a single predecessor Returns if BB's address was taken After the patch: Method 2. MergeBlockIntoPredecessor is attempting to become the new default: Updates DomTree or DeferredDominance, and LoopInfo and MemoryDependenceResults Moves all instruction from BB to Pred, deletes BB Returns if doesn't have a single predecessor Returns if BB's address was taken Uses of MergeBasicBlockIntoOnlyPred that need to be replaced: 1. lib/Transforms/Scalar/LoopSimplifyCFG.cpp Updated in this patch. No challenges. 2. lib/CodeGen/CodeGenPrepare.cpp Updated in this patch. i. eliminateFallThrough is straightforward, but I added using a temporary array to avoid the iterator invalidation. ii. eliminateMostlyEmptyBlock(s) methods also now use a temporary array for blocks Some interesting aspects: - Since Pred is not deleted (BB is), the entry block does not need updating. - The entry block was being updated with the deleted block in eliminateMostlyEmptyBlock. Added assert to make obvious that BB=SinglePred. - isMergingEmptyBlockProfitable assumes BB is the one to be deleted. - eliminateMostlyEmptyBlock(BB) does not delete BB on one path, it deletes its unique predecessor instead. - adding some test owner as subscribers for the interesting tests modified: test/CodeGen/X86/avx-cmp.ll test/CodeGen/AMDGPU/nested-loop-conditions.ll test/CodeGen/AMDGPU/si-annotate-cf.ll test/CodeGen/X86/hoist-spill.ll test/CodeGen/X86/2006-11-17-IllegalMove.ll 3. lib/Transforms/Scalar/JumpThreading.cpp Not covered in this patch. It is the only use case using the DeferredDominance. I would defer to Brian Rzycki to make this replacement. Reviewers: chandlerc, spatel, davide, brzycki, bkramer, javed.absar Subscribers: qcolombet, sanjoy, nemanjai, nhaehnle, jlebar, tpr, kbarton, RKSimon, wmi, arsenm, llvm-commits Differential Revision: https://reviews.llvm.org/D48202 llvm-svn: 335183
2018-06-21 06:01:04 +08:00
; CHECK: # %inner_loop_top
; CHECK-NOT: # %{{[a-zA-Z_]+}}
; CHECK: # %exit
define void @tail_dup_merge_loops(i32 %a, i8* %b, i8* %c) local_unnamed_addr #0 {
entry:
%notlhs674.i = icmp eq i32 %a, 0
br label %outer_loop_top
outer_loop_top: ; preds = %inner_loop_exit, %entry
%dst.0.ph.i = phi i8* [ %b, %entry ], [ %scevgep679.i, %inner_loop_exit ]
br i1 %notlhs674.i, label %exit, label %inner_loop_preheader
inner_loop_preheader: ; preds = %outer_loop_top
br label %inner_loop_top
inner_loop_top: ; preds = %inner_loop_latch, %inner_loop_preheader
%dst.0.i = phi i8* [ %inc, %inner_loop_latch ], [ %dst.0.ph.i, %inner_loop_preheader ]
%var = load i8, i8* %dst.0.i
%tobool1.i = icmp slt i8 %var, 0
br label %inner_loop_test
inner_loop_test: ; preds = %inner_loop_top
br i1 %tobool1.i, label %inner_loop_exit, label %inner_loop_latch
inner_loop_exit: ; preds = %inner_loop_test
%scevgep.i = getelementptr i8, i8* %dst.0.i, i64 1
%scevgep679.i = getelementptr i8, i8* %scevgep.i, i64 0
br label %outer_loop_top
inner_loop_latch: ; preds = %inner_loop_test
%cmp75.i = icmp ult i8* %dst.0.i, %c
%inc = getelementptr i8, i8* %dst.0.i, i64 2
br label %inner_loop_top
exit: ; preds = %outer_loop_top
ret void
}
@.str.6 = external unnamed_addr constant [23 x i8], align 1
; There is an erroneus check in LoopBase::addBasicBlockToLoop(), where it
; assumes that the header block for a loop is unique.
; For most of compilation this assumption is true, but during layout we allow
; this assumption to be violated. The following code will trigger the bug:
; The loops in question is eventually headed by the block shared_loop_header
;
; During layout The block labeled outer_loop_header gets tail-duplicated into
; outer_loop_latch, and into shared_preheader, and then removed. This leaves
; shared_loop_header as the header of both loops. The end result
; is that there are 2 valid loops, and that they share a header. If we re-ran
; the loop analysis, it would classify this as a single loop.
; So far this is fine as far as layout is concerned.
; After layout we tail merge blocks merge_other and merge_predecessor_split.
; We do this even though they share only a single instruction, because
; merge_predecessor_split falls through to their shared successor:
; outer_loop_latch.
; The rest of the blocks in the function are noise unfortunately. Bugpoint
; couldn't shrink the test any further.
; CHECK-LABEL: loop_shared_header
; CHECK: # %entry
; CHECK: # %shared_preheader
; CHECK: # %shared_loop_header
; CHECK: # %inner_loop_body
; CHECK: # %outer_loop_latch
; CHECK: # %merge_predecessor_split
; CHECK: # %outer_loop_latch
; CHECK: # %cleanup
define i32 @loop_shared_header(i8* %exe, i32 %exesz, i32 %headsize, i32 %min, i32 %wwprva, i32 %e_lfanew, i8* readonly %wwp, i32 %wwpsz, i16 zeroext %sects) local_unnamed_addr #0 {
entry:
%0 = load i32, i32* undef, align 4
%mul = shl nsw i32 %0, 2
br i1 undef, label %if.end19, label %cleanup
if.end19: ; preds = %entry
%conv = zext i32 %mul to i64
%call = tail call i8* @cli_calloc(i64 %conv, i64 1)
%1 = icmp eq i32 %exesz, 0
%notrhs = icmp eq i32 %0, 0
%or.cond117.not = or i1 %1, %notrhs
%or.cond202 = or i1 %or.cond117.not, undef
%cmp35 = icmp ult i8* undef, %exe
%or.cond203 = or i1 %or.cond202, %cmp35
br i1 %or.cond203, label %cleanup, label %if.end50
if.end50: ; preds = %if.end19
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
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull %call, i8* undef, i64 %conv, i1 false)
%cmp1.i.i = icmp ugt i32 %mul, 3
br i1 %cmp1.i.i, label %shared_preheader, label %wunpsect.exit.thread.loopexit391
shared_preheader: ; preds = %if.end50
br label %outer_loop_header
outer_loop_header: ; preds = %outer_loop_latch, %shared_preheader
%bits.1.i = phi i8 [ 32, %shared_preheader ], [ %bits.43.i, %outer_loop_latch ]
%dst.0.ph.i = phi i8* [ undef, %shared_preheader ], [ %scevgep679.i, %outer_loop_latch ]
%2 = icmp eq i32 undef, 0
br i1 %2, label %while.cond.us1412.i, label %shared_loop_header
while.cond.us1412.i: ; preds = %outer_loop_header
%.pre.i = add i8 %bits.1.i, -1
%tobool2.us1420.i = icmp eq i8 %.pre.i, 0
%or.cond.us1421.i = or i1 undef, %tobool2.us1420.i
br i1 %or.cond.us1421.i, label %if.end41.us1436.i, label %cleanup
if.end41.us1436.i: ; preds = %while.cond.us1412.i
unreachable
shared_loop_header: ; preds = %dup_early2, %dup_early1
%dst.0.i = phi i8* [ undef, %inner_loop_body ], [ %dst.0.ph.i, %outer_loop_header ], [ undef, %dead_block ]
%cmp3.i1172.i = icmp ult i8* undef, %call
br i1 %cmp3.i1172.i, label %wunpsect.exit.thread.loopexit389, label %inner_loop_body
inner_loop_body: ; preds = %shared_loop_header
%3 = icmp slt i32 undef, 0
br i1 %3, label %if.end96.i, label %shared_loop_header
dead_block: ; preds = %inner_loop_body
%cmp75.i = icmp ult i8* %dst.0.i, undef
br label %shared_loop_header
if.end96.i: ; preds = %inner_loop_body
%cmp97.i = icmp ugt i32 undef, 2
br i1 %cmp97.i, label %if.then99.i, label %if.end287.i
if.then99.i: ; preds = %if.end96.i
tail call void (i8*, ...) @cli_dbgmsg(i8* getelementptr inbounds ([23 x i8], [23 x i8]* @.str.6, i64 0, i64 0), i32 undef)
br label %cleanup
if.end287.i: ; preds = %if.end96.i
%cmp291.i = icmp ne i32 undef, 1
%conv294.i = select i1 %cmp291.i, i16 4, i16 3
br i1 undef, label %if.end308.i, label %outer_loop_latch
if.end308.i: ; preds = %if.end287.i
br i1 undef, label %if.end335.i, label %merge_predecessor_split
merge_predecessor_split: ; preds = %if.end308.i
%4 = bitcast i8* undef to i32*
br label %outer_loop_latch
if.end335.i: ; preds = %if.end308.i
br i1 undef, label %outer_loop_latch, label %merge_other
merge_other: ; preds = %if.end335.i
br label %outer_loop_latch
outer_loop_latch: ; preds = %merge_other, %if.end335.i, %merge_predecessor_split, %if.end287.i
%bits.43.i = phi i8 [ undef, %if.end287.i ], [ undef, %merge_other ], [ 32, %merge_predecessor_split ], [ 0, %if.end335.i ]
%backsize.0.i = phi i16 [ %conv294.i, %if.end287.i ], [ 0, %merge_other ], [ 0, %merge_predecessor_split ], [ 0, %if.end335.i ]
%5 = add i16 %backsize.0.i, -1
%6 = zext i16 %5 to i64
%scevgep.i = getelementptr i8, i8* %dst.0.ph.i, i64 1
%scevgep679.i = getelementptr i8, i8* %scevgep.i, i64 %6
br label %outer_loop_header
wunpsect.exit.thread.loopexit389: ; preds = %shared_loop_header
unreachable
wunpsect.exit.thread.loopexit391: ; preds = %if.end50
unreachable
cleanup: ; preds = %if.then99.i, %while.cond.us1412.i, %if.end19, %entry
%retval.0 = phi i32 [ 0, %if.then99.i ], [ 1, %entry ], [ 1, %if.end19 ], [ 1, %while.cond.us1412.i ]
ret i32 %retval.0
}
; Function Attrs: nounwind
declare void @cli_dbgmsg(i8*, ...) local_unnamed_addr #0
; Function Attrs: nounwind
declare i8* @cli_calloc(i64, i64) local_unnamed_addr #0
; Function Attrs: argmemonly 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 writeonly, i8* nocapture readonly, i64, i1) #1
attributes #0 = { nounwind }
attributes #1 = { argmemonly nounwind }