1e68724d24
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
81 lines
3.4 KiB
LLVM
81 lines
3.4 KiB
LLVM
; RUN: opt < %s -scalar-evolution -analyze | FileCheck %s
|
|
|
|
; ScalarEvolution can't compute a trip count because it doesn't know if
|
|
; dividing by the stride will have a remainder. This could theoretically
|
|
; be teaching it how to use a more elaborate trip count computation.
|
|
|
|
; CHECK: Loop %bb3.i: backedge-taken count is ((64 + (-64 smax (-1 + (-1 * %0))) + %0) /u 64)
|
|
; CHECK: Loop %bb3.i: max backedge-taken count is 33554431
|
|
|
|
%struct.FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct.FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] }
|
|
%struct.SHA_INFO = type { [5 x i32], i32, i32, [16 x i32] }
|
|
%struct._IO_marker = type { %struct._IO_marker*, %struct.FILE*, i32 }
|
|
|
|
@_2E_str = external constant [26 x i8]
|
|
@stdin = external global %struct.FILE*
|
|
@_2E_str1 = external constant [3 x i8]
|
|
@_2E_str12 = external constant [30 x i8]
|
|
|
|
declare void @sha_init(%struct.SHA_INFO* nocapture) nounwind
|
|
|
|
declare fastcc void @sha_transform(%struct.SHA_INFO* nocapture) nounwind
|
|
|
|
declare void @sha_print(%struct.SHA_INFO* nocapture) nounwind
|
|
|
|
declare i32 @printf(i8* nocapture, ...) nounwind
|
|
|
|
declare void @sha_final(%struct.SHA_INFO* nocapture) nounwind
|
|
|
|
declare void @sha_update(%struct.SHA_INFO* nocapture, i8* nocapture, i32) nounwind
|
|
|
|
declare i64 @fread(i8* noalias nocapture, i64, i64, %struct.FILE* noalias nocapture) nounwind
|
|
|
|
declare i32 @main(i32, i8** nocapture) nounwind
|
|
|
|
declare noalias %struct.FILE* @fopen(i8* noalias nocapture, i8* noalias nocapture) nounwind
|
|
|
|
declare i32 @fclose(%struct.FILE* nocapture) nounwind
|
|
|
|
declare void @sha_stream(%struct.SHA_INFO* nocapture, %struct.FILE* nocapture) nounwind
|
|
|
|
define void @sha_stream_bb3_2E_i(%struct.SHA_INFO* %sha_info, i8* %data1, i32, i8** %buffer_addr.0.i.out, i32* %count_addr.0.i.out) nounwind {
|
|
newFuncRoot:
|
|
br label %bb3.i
|
|
|
|
sha_update.exit.exitStub: ; preds = %bb3.i
|
|
store i8* %buffer_addr.0.i, i8** %buffer_addr.0.i.out
|
|
store i32 %count_addr.0.i, i32* %count_addr.0.i.out
|
|
ret void
|
|
|
|
bb2.i: ; preds = %bb3.i
|
|
%1 = getelementptr %struct.SHA_INFO, %struct.SHA_INFO* %sha_info, i64 0, i32 3
|
|
%2 = bitcast [16 x i32]* %1 to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %2, i8* %buffer_addr.0.i, i64 64, i1 false)
|
|
%3 = getelementptr %struct.SHA_INFO, %struct.SHA_INFO* %sha_info, i64 0, i32 3, i64 0
|
|
%4 = bitcast i32* %3 to i8*
|
|
br label %codeRepl
|
|
|
|
codeRepl: ; preds = %bb2.i
|
|
call void @sha_stream_bb3_2E_i_bb1_2E_i_2E_i(i8* %4)
|
|
br label %byte_reverse.exit.i
|
|
|
|
byte_reverse.exit.i: ; preds = %codeRepl
|
|
call fastcc void @sha_transform(%struct.SHA_INFO* %sha_info) nounwind
|
|
%5 = getelementptr i8, i8* %buffer_addr.0.i, i64 64
|
|
%6 = add i32 %count_addr.0.i, -64
|
|
br label %bb3.i
|
|
|
|
bb3.i: ; preds = %byte_reverse.exit.i, %newFuncRoot
|
|
%buffer_addr.0.i = phi i8* [ %data1, %newFuncRoot ], [ %5, %byte_reverse.exit.i ]
|
|
%count_addr.0.i = phi i32 [ %0, %newFuncRoot ], [ %6, %byte_reverse.exit.i ]
|
|
%7 = icmp sgt i32 %count_addr.0.i, 63
|
|
br i1 %7, label %bb2.i, label %sha_update.exit.exitStub
|
|
}
|
|
|
|
declare void @sha_stream_bb3_2E_i_bb1_2E_i_2E_i(i8*) nounwind
|
|
|
|
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
|
|
|