llvm/test/CodeGen/X86/memcpy.ll
Manuel Jacob f3296cdf51 Partially fix memcpy / memset / memmove lowering in SelectionDAG construction if address space != 0.
Summary:
Previously SelectionDAGBuilder asserted that the pointer operands of
memcpy / memset / memmove intrinsics are in address space < 256.  This assert
implicitly assumed the X86 backend, where all address spaces < 256 are
equivalent to address space 0 from the code generator's point of view.  On some
targets (R600 and NVPTX) several address spaces < 256 have a target-defined
meaning, so this assert made little sense for these targets.

This patch removes this wrong assertion and adds extra checks before lowering
these intrinsics to library calls.  If a pointer operand can't be casted to
address space 0 without changing semantics, a fatal error is reported to the
user.

The new behavior should be valid for all targets that give address spaces != 0
a target-specified meaning (NVPTX, R600, X86).  NVPTX lowers big or
variable-sized memory intrinsics before SelectionDAG construction.  All other
memory intrinsics are inlined (the threshold is set very high for this target).
R600 doesn't support memcpy / memset / memmove library calls (previously the
illegal emission of a call to such library function triggered an error
somewhere in the code generator).  X86 now emits inline loads and stores for
address spaces 256 and 257 up to the same threshold that is used for address
space 0 and reports a fatal error otherwise.

I call this a "partial fix" because there are still cases that can't be
lowered.  A fatal error is reported in these cases.

Reviewers: arsenm, theraven, compnerd, hfinkel

Subscribers: hfinkel, llvm-commits, alex

Differential Revision: http://reviews.llvm.org/D7241

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@255441 91177308-0d34-0410-b5e6-96231b3b80d8
2015-12-12 21:33:31 +00:00

154 lines
4.3 KiB
LLVM

; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=core2 | FileCheck %s -check-prefix=LINUX
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=DARWIN
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
declare void @llvm.memcpy.p256i8.p256i8.i64(i8 addrspace(256)* nocapture, i8 addrspace(256)* nocapture, i64, i32, i1) nounwind
; Variable memcpy's should lower to calls.
define i8* @test1(i8* %a, i8* %b, i64 %n) nounwind {
entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64( i8* %a, i8* %b, i64 %n, i32 1, i1 0 )
ret i8* %a
; LINUX-LABEL: test1:
; LINUX: memcpy
}
; Variable memcpy's should lower to calls.
define i8* @test2(i64* %a, i64* %b, i64 %n) nounwind {
entry:
%tmp14 = bitcast i64* %a to i8*
%tmp25 = bitcast i64* %b to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp14, i8* %tmp25, i64 %n, i32 8, i1 0 )
ret i8* %tmp14
; LINUX-LABEL: test2:
; LINUX: memcpy
}
; Large constant memcpy's should lower to a call when optimizing for size.
; PR6623
; On the other hand, Darwin's definition of -Os is optimizing for size without
; hurting performance so it should just ignore optsize when expanding memcpy.
; rdar://8821501
define void @test3(i8* nocapture %A, i8* nocapture %B) nounwind optsize noredzone {
entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void
; LINUX-LABEL: test3:
; LINUX: memcpy
; DARWIN-LABEL: test3:
; DARWIN-NOT: memcpy
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
}
define void @test3_minsize(i8* nocapture %A, i8* nocapture %B) nounwind minsize noredzone {
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void
; LINUX-LABEL: test3_minsize:
; LINUX: memcpy
; DARWIN-LABEL: test3_minsize:
; DARWIN: memcpy
}
define void @test3_minsize_optsize(i8* nocapture %A, i8* nocapture %B) nounwind optsize minsize noredzone {
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void
; LINUX-LABEL: test3_minsize_optsize:
; LINUX: memcpy
; DARWIN-LABEL: test3_minsize_optsize:
; DARWIN: memcpy
}
; Large constant memcpy's should be inlined when not optimizing for size.
define void @test4(i8* nocapture %A, i8* nocapture %B) nounwind noredzone {
entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void
; LINUX-LABEL: test4:
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
}
@.str = private unnamed_addr constant [30 x i8] c"\00aaaaaaaaaaaaaaaaaaaaaaaaaaaa\00", align 1
define void @test5(i8* nocapture %C) nounwind uwtable ssp {
entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([30 x i8], [30 x i8]* @.str, i64 0, i64 0), i64 16, i32 1, i1 false)
ret void
; DARWIN-LABEL: test5:
; DARWIN: movabsq $7016996765293437281
; DARWIN: movabsq $7016996765293437184
}
; PR14896
@.str2 = private unnamed_addr constant [2 x i8] c"x\00", align 1
define void @test6() nounwind uwtable {
entry:
; DARWIN: test6
; DARWIN: movw $0, 8
; DARWIN: movq $120, 0
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* null, i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str2, i64 0, i64 0), i64 10, i32 1, i1 false)
ret void
}
define void @PR15348(i8* %a, i8* %b) {
; Ensure that alignment of '0' in an @llvm.memcpy intrinsic results in
; unaligned loads and stores.
; LINUX: PR15348
; LINUX: movb
; LINUX: movb
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 17, i32 0, i1 false)
ret void
}
; Memcpys from / to address space 256 should be lowered to appropriate loads /
; stores if small enough.
define void @addrspace256(i8 addrspace(256)* %a, i8 addrspace(256)* %b) nounwind {
tail call void @llvm.memcpy.p256i8.p256i8.i64(i8 addrspace(256)* %a, i8 addrspace(256)* %b, i64 16, i32 8, i1 false)
ret void
; LINUX-LABEL: addrspace256:
; LINUX: movq %gs:
; LINUX: movq %gs:
; LINUX: movq {{.*}}, %gs:
; LINUX: movq {{.*}}, %gs:
}