mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 20:43:44 +02:00
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
126 lines
4.3 KiB
LLVM
126 lines
4.3 KiB
LLVM
; RUN: llc < %s -mtriple=aarch64-eabi -aarch64-neon-syntax=apple -aarch64-enable-stp-suppress=false -verify-machineinstrs -asm-verbose=false | FileCheck %s
|
|
|
|
; CHECK-LABEL: test_strd_sturd:
|
|
; CHECK-NEXT: stp d0, d1, [x0, #-8]
|
|
; CHECK-NEXT: ret
|
|
define void @test_strd_sturd(float* %ptr, <2 x float> %v1, <2 x float> %v2) #0 {
|
|
%tmp1 = bitcast float* %ptr to <2 x float>*
|
|
store <2 x float> %v2, <2 x float>* %tmp1, align 16
|
|
%add.ptr = getelementptr inbounds float, float* %ptr, i64 -2
|
|
%tmp = bitcast float* %add.ptr to <2 x float>*
|
|
store <2 x float> %v1, <2 x float>* %tmp, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_sturd_strd:
|
|
; CHECK-NEXT: stp d0, d1, [x0, #-8]
|
|
; CHECK-NEXT: ret
|
|
define void @test_sturd_strd(float* %ptr, <2 x float> %v1, <2 x float> %v2) #0 {
|
|
%add.ptr = getelementptr inbounds float, float* %ptr, i64 -2
|
|
%tmp = bitcast float* %add.ptr to <2 x float>*
|
|
store <2 x float> %v1, <2 x float>* %tmp, align 16
|
|
%tmp1 = bitcast float* %ptr to <2 x float>*
|
|
store <2 x float> %v2, <2 x float>* %tmp1, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_strq_sturq:
|
|
; CHECK-NEXT: stp q0, q1, [x0, #-16]
|
|
; CHECK-NEXT: ret
|
|
define void @test_strq_sturq(double* %ptr, <2 x double> %v1, <2 x double> %v2) #0 {
|
|
%tmp1 = bitcast double* %ptr to <2 x double>*
|
|
store <2 x double> %v2, <2 x double>* %tmp1, align 16
|
|
%add.ptr = getelementptr inbounds double, double* %ptr, i64 -2
|
|
%tmp = bitcast double* %add.ptr to <2 x double>*
|
|
store <2 x double> %v1, <2 x double>* %tmp, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_sturq_strq:
|
|
; CHECK-NEXT: stp q0, q1, [x0, #-16]
|
|
; CHECK-NEXT: ret
|
|
define void @test_sturq_strq(double* %ptr, <2 x double> %v1, <2 x double> %v2) #0 {
|
|
%add.ptr = getelementptr inbounds double, double* %ptr, i64 -2
|
|
%tmp = bitcast double* %add.ptr to <2 x double>*
|
|
store <2 x double> %v1, <2 x double>* %tmp, align 16
|
|
%tmp1 = bitcast double* %ptr to <2 x double>*
|
|
store <2 x double> %v2, <2 x double>* %tmp1, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_ldrx_ldurx:
|
|
; CHECK-NEXT: ldp [[V0:x[0-9]+]], [[V1:x[0-9]+]], [x0, #-8]
|
|
; CHECK-NEXT: add x0, [[V0]], [[V1]]
|
|
; CHECK-NEXT: ret
|
|
define i64 @test_ldrx_ldurx(i64* %p) #0 {
|
|
%tmp = load i64, i64* %p, align 4
|
|
%add.ptr = getelementptr inbounds i64, i64* %p, i64 -1
|
|
%tmp1 = load i64, i64* %add.ptr, align 4
|
|
%add = add nsw i64 %tmp1, %tmp
|
|
ret i64 %add
|
|
}
|
|
|
|
; CHECK-LABEL: test_ldurx_ldrx:
|
|
; CHECK-NEXT: ldp [[V0:x[0-9]+]], [[V1:x[0-9]+]], [x0, #-8]
|
|
; CHECK-NEXT: add x0, [[V0]], [[V1]]
|
|
; CHECK-NEXT: ret
|
|
define i64 @test_ldurx_ldrx(i64* %p) #0 {
|
|
%add.ptr = getelementptr inbounds i64, i64* %p, i64 -1
|
|
%tmp1 = load i64, i64* %add.ptr, align 4
|
|
%tmp = load i64, i64* %p, align 4
|
|
%add = add nsw i64 %tmp1, %tmp
|
|
ret i64 %add
|
|
}
|
|
|
|
; CHECK-LABEL: test_ldrsw_ldursw:
|
|
; CHECK-NEXT: ldpsw [[V0:x[0-9]+]], [[V1:x[0-9]+]], [x0, #-4]
|
|
; CHECK-NEXT: add x0, [[V0]], [[V1]]
|
|
; CHECK-NEXT: ret
|
|
define i64 @test_ldrsw_ldursw(i32* %p) #0 {
|
|
%tmp = load i32, i32* %p, align 4
|
|
%add.ptr = getelementptr inbounds i32, i32* %p, i64 -1
|
|
%tmp1 = load i32, i32* %add.ptr, align 4
|
|
%sexttmp = sext i32 %tmp to i64
|
|
%sexttmp1 = sext i32 %tmp1 to i64
|
|
%add = add nsw i64 %sexttmp1, %sexttmp
|
|
ret i64 %add
|
|
}
|
|
|
|
; Also make sure we only match valid offsets.
|
|
; CHECK-LABEL: test_ldrq_ldruq_invalidoffset:
|
|
; CHECK-NEXT: ldr q[[V0:[0-9]+]], [x0]
|
|
; CHECK-NEXT: ldur q[[V1:[0-9]+]], [x0, #24]
|
|
; CHECK-NEXT: add.2d v0, v[[V0]], v[[V1]]
|
|
; CHECK-NEXT: ret
|
|
define <2 x i64> @test_ldrq_ldruq_invalidoffset(i64* %p) #0 {
|
|
%a1 = bitcast i64* %p to <2 x i64>*
|
|
%tmp1 = load <2 x i64>, < 2 x i64>* %a1, align 8
|
|
%add.ptr2 = getelementptr inbounds i64, i64* %p, i64 3
|
|
%a2 = bitcast i64* %add.ptr2 to <2 x i64>*
|
|
%tmp2 = load <2 x i64>, <2 x i64>* %a2, align 8
|
|
%add = add nsw <2 x i64> %tmp1, %tmp2
|
|
ret <2 x i64> %add
|
|
}
|
|
|
|
; Pair an unscaled store with a scaled store where the scaled store has a
|
|
; non-zero offset. This should not hit an assert.
|
|
; CHECK-LABEL: test_stur_str_no_assert
|
|
; CHECK: stp xzr, xzr, [sp, #16]
|
|
; CHECK: ret
|
|
define void @test_stur_str_no_assert() #0 {
|
|
entry:
|
|
%a1 = alloca i64, align 4
|
|
%a2 = alloca [12 x i8], align 4
|
|
%0 = bitcast i64* %a1 to i8*
|
|
%C = getelementptr inbounds [12 x i8], [12 x i8]* %a2, i64 0, i64 4
|
|
%1 = bitcast i8* %C to i64*
|
|
store i64 0, i64* %1, align 4
|
|
call void @llvm.memset.p0i8.i64(i8* align 8 %0, i8 0, i64 8, i1 false)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
|
|
|
|
|
|
attributes #0 = { nounwind }
|