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
159 lines
4.0 KiB
LLVM
159 lines
4.0 KiB
LLVM
; Test memset in cases where the set value is variable.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
|
|
|
|
declare void @llvm.memset.p0i8.i32(i8 *nocapture, i8, i32, i1) nounwind
|
|
declare void @llvm.memset.p0i8.i64(i8 *nocapture, i8, i64, i1) nounwind
|
|
|
|
; No bytes, i32 version.
|
|
define void @f1(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK-NOT: %r2
|
|
; CHECK-NOT: %r3
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i32(i8* %dest, i8 %val, i32 0, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; No bytes, i64 version.
|
|
define void @f2(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK-NOT: %r2
|
|
; CHECK-NOT: %r3
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i64(i8* %dest, i8 %val, i64 0, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 1 byte, i32 version.
|
|
define void @f3(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i32(i8* %dest, i8 %val, i32 1, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 1 byte, i64 version.
|
|
define void @f4(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i64(i8* %dest, i8 %val, i64 1, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 2 bytes, i32 version.
|
|
define void @f5(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f5:
|
|
; CHECK-DAG: stc %r3, 0(%r2)
|
|
; CHECK-DAG: stc %r3, 1(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i32(i8* %dest, i8 %val, i32 2, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 2 bytes, i64 version.
|
|
define void @f6(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f6:
|
|
; CHECK-DAG: stc %r3, 0(%r2)
|
|
; CHECK-DAG: stc %r3, 1(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i64(i8* %dest, i8 %val, i64 2, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 3 bytes, i32 version.
|
|
define void @f7(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f7:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: mvc 1(2,%r2), 0(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i32(i8* %dest, i8 %val, i32 3, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 3 bytes, i64 version.
|
|
define void @f8(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f8:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: mvc 1(2,%r2), 0(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i64(i8* %dest, i8 %val, i64 3, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 257 bytes, i32 version.
|
|
define void @f9(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f9:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: mvc 1(256,%r2), 0(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i32(i8* %dest, i8 %val, i32 257, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 257 bytes, i64 version.
|
|
define void @f10(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f10:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: mvc 1(256,%r2), 0(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i64(i8* %dest, i8 %val, i64 257, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 258 bytes, i32 version. We need two MVCs.
|
|
define void @f11(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f11:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: mvc 1(256,%r2), 0(%r2)
|
|
; CHECK: mvc 257(1,%r2), 256(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i32(i8* %dest, i8 %val, i32 258, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; 258 bytes, i64 version.
|
|
define void @f12(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f12:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: mvc 1(256,%r2), 0(%r2)
|
|
; CHECK: mvc 257(1,%r2), 256(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i64(i8* %dest, i8 %val, i64 258, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; Test the largest case for which straight-line code is used.
|
|
define void @f13(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f13:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: mvc 1(256,%r2), 0(%r2)
|
|
; CHECK: mvc 257(256,%r2), 256(%r2)
|
|
; CHECK: mvc 513(256,%r2), 512(%r2)
|
|
; CHECK: mvc 769(256,%r2), 768(%r2)
|
|
; CHECK: mvc 1025(256,%r2), 1024(%r2)
|
|
; CHECK: mvc 1281(256,%r2), 1280(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i64(i8* %dest, i8 %val, i64 1537, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; Test the next size up, which uses a loop. We leave the other corner
|
|
; cases to memcpy-01.ll.
|
|
define void @f14(i8* %dest, i8 %val) {
|
|
; CHECK-LABEL: f14:
|
|
; CHECK: stc %r3, 0(%r2)
|
|
; CHECK: lghi [[COUNT:%r[0-5]]], 6
|
|
; CHECK: [[LABEL:\.L[^:]*]]:
|
|
; CHECK: pfd 2, 769(%r2)
|
|
; CHECK: mvc 1(256,%r2), 0(%r2)
|
|
; CHECK: la %r2, 256(%r2)
|
|
; CHECK: brctg [[COUNT]], [[LABEL]]
|
|
; CHECK: mvc 1(1,%r2), 0(%r2)
|
|
; CHECK: br %r14
|
|
call void @llvm.memset.p0i8.i64(i8* %dest, i8 %val, i64 1538, i1 false)
|
|
ret void
|
|
}
|