mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 03:33:20 +01:00
f59acc15ad
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
114 lines
3.8 KiB
LLVM
114 lines
3.8 KiB
LLVM
; RUN: opt < %s -analyze -scalar-evolution -scalar-evolution-max-iterations=0 | FileCheck %s
|
|
; RUN: opt < %s -passes='print<scalar-evolution>' -disable-output 2>&1 | FileCheck %s
|
|
; PR1101
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
@A = weak global [1000 x i32] zeroinitializer, align 32
|
|
|
|
; CHECK-LABEL: Determining loop execution counts for: @test1
|
|
; CHECK: backedge-taken count is 10000
|
|
|
|
define void @test1(i32 %N) {
|
|
entry:
|
|
br label %bb3
|
|
|
|
bb: ; preds = %bb3
|
|
%tmp = getelementptr [1000 x i32], [1000 x i32]* @A, i32 0, i32 %i.0 ; <i32*> [#uses=1]
|
|
store i32 123, i32* %tmp
|
|
%tmp2 = add i32 %i.0, 1 ; <i32> [#uses=1]
|
|
br label %bb3
|
|
|
|
bb3: ; preds = %bb, %entry
|
|
%i.0 = phi i32 [ 0, %entry ], [ %tmp2, %bb ] ; <i32> [#uses=3]
|
|
%tmp3 = icmp sle i32 %i.0, 9999 ; <i1> [#uses=1]
|
|
br i1 %tmp3, label %bb, label %bb5
|
|
|
|
bb5: ; preds = %bb3
|
|
br label %return
|
|
|
|
return: ; preds = %bb5
|
|
ret void
|
|
}
|
|
|
|
; PR22795
|
|
; CHECK-LABEL: Classifying expressions for: @test2
|
|
; CHECK: %iv = phi i32 [ -1, %entry ], [ %next.1, %for.inc.1 ]
|
|
; CHECK-NEXT: --> {-1,+,2}<%preheader> U: full-set S: full-set Exits: 13
|
|
|
|
define i32 @test2() {
|
|
entry:
|
|
%bins = alloca [16 x i64], align 16
|
|
%0 = bitcast [16 x i64]* %bins to i8*
|
|
call void @llvm.memset.p0i8.i64(i8* align 16 %0, i8 0, i64 128, i1 false)
|
|
br label %preheader
|
|
|
|
preheader: ; preds = %for.inc.1, %entry
|
|
%v11 = phi i64 [ 0, %entry ], [ %next12.1, %for.inc.1 ]
|
|
%iv = phi i32 [ -1, %entry ], [ %next.1, %for.inc.1 ]
|
|
%cmp = icmp sgt i64 %v11, 0
|
|
br i1 %cmp, label %for.body, label %for.inc
|
|
|
|
for.body: ; preds = %preheader
|
|
%zext = zext i32 %iv to i64
|
|
%arrayidx = getelementptr [16 x i64], [16 x i64]* %bins, i64 0, i64 %v11
|
|
%loaded = load i64, i64* %arrayidx, align 8
|
|
%add = add i64 %loaded, 1
|
|
%add2 = add i64 %add, %zext
|
|
store i64 %add2, i64* %arrayidx, align 8
|
|
br label %for.inc
|
|
|
|
for.inc: ; preds = %for.body, %preheader
|
|
%next12 = add nuw nsw i64 %v11, 1
|
|
%next = add nsw i32 %iv, 1
|
|
br i1 true, label %for.body.1, label %for.inc.1
|
|
|
|
end: ; preds = %for.inc.1
|
|
%arrayidx8 = getelementptr [16 x i64], [16 x i64]* %bins, i64 0, i64 2
|
|
%load = load i64, i64* %arrayidx8, align 16
|
|
%shr4 = lshr i64 %load, 32
|
|
%conv = trunc i64 %shr4 to i32
|
|
ret i32 %conv
|
|
|
|
for.body.1: ; preds = %for.inc
|
|
%zext.1 = zext i32 %next to i64
|
|
%arrayidx.1 = getelementptr [16 x i64], [16 x i64]* %bins, i64 0, i64 %next12
|
|
%loaded.1 = load i64, i64* %arrayidx.1, align 8
|
|
%add.1 = add i64 %loaded.1, 1
|
|
%add2.1 = add i64 %add.1, %zext.1
|
|
store i64 %add2.1, i64* %arrayidx.1, align 8
|
|
br label %for.inc.1
|
|
|
|
for.inc.1: ; preds = %for.body.1, %for.inc
|
|
%next12.1 = add nuw nsw i64 %next12, 1
|
|
%next.1 = add nuw nsw i32 %next, 1
|
|
%exitcond.1 = icmp eq i64 %next12.1, 16
|
|
br i1 %exitcond.1, label %end, label %preheader
|
|
}
|
|
|
|
; Function Attrs: nounwind
|
|
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) #0
|
|
|
|
declare void @may_exit() nounwind
|
|
|
|
define void @pr28012(i32 %n) {
|
|
; CHECK-LABEL: Classifying expressions for: @pr28012
|
|
; CHECK: Loop %loop: backedge-taken count is -1431655751
|
|
; CHECK: Loop %loop: max backedge-taken count is -1431655751
|
|
; CHECK: Loop %loop: Predicated backedge-taken count is -1431655751
|
|
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i32 [ 0, %entry ], [ %iv.inc, %loop ]
|
|
%iv.inc = add nsw i32 %iv, 3
|
|
call void @may_exit()
|
|
%becond = icmp ne i32 %iv.inc, 46
|
|
br i1 %becond, label %loop, label %leave
|
|
|
|
leave:
|
|
ret void
|
|
}
|