6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-12-19 11:23:32 +00:00
Code Issues Projects Releases Wiki Activity

[ARM] Use AEABI aligned function variants

Browse Source 
AEABI defines aligned variants of memcpy etc. that can be faster than
the default version due to not having to do alignment checks. When
emitting target code for these functions make use of these aligned
variants if possible. Also convert memset to memclr if possible.

Differential Revision: http://reviews.llvm.org/D8060


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237127 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
John Brawn
2015-05-12 13:13:38 +00:00
parent 00666a17ff
commit e38f45effc
3 changed files with 223 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

113
test/CodeGen/ARM/memfunc.ll
View File

@@ -18,13 +18,64 @@ entry:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 0, i1 false)
; EABI memset swaps arguments
; CHECK-IOS: mov r1, #1
; CHECK-IOS: memset
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: memset
; CHECK-EABI: mov r2, #1
; CHECK-EABI: __aeabi_memset
call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 0, i1 false)
; EABI uses memclr if value set to 0
; CHECK-IOS: mov r1, #0
; CHECK-IOS: memset
; CHECK-DARWIN: movs r1, #0
; CHECK-DARWIN: memset
; CHECK-EABI: mov r2, #0
; CHECK-EABI: __aeabi_memset
; CHECK-EABI: __aeabi_memclr
call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i32 0, i1 false)
; EABI uses aligned function variants if possible
; CHECK-IOS: memmove
; CHECK-DARWIN: memmove
; CHECK-EABI: __aeabi_memmove4
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 4, i1 false)
; CHECK-IOS: memcpy
; CHECK-DARWIN: memcpy
; CHECK-EABI: __aeabi_memcpy4
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 4, i1 false)
; CHECK-IOS: memset
; CHECK-DARWIN: memset
; CHECK-EABI: __aeabi_memset4
call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 4, i1 false)
; CHECK-IOS: memset
; CHECK-DARWIN: memset
; CHECK-EABI: __aeabi_memclr4
call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i32 4, i1 false)
; CHECK-IOS: memmove
; CHECK-DARWIN: memmove
; CHECK-EABI: __aeabi_memmove8
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false)
; CHECK-IOS: memcpy
; CHECK-DARWIN: memcpy
; CHECK-EABI: __aeabi_memcpy8
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false)
; CHECK-IOS: memset
; CHECK-DARWIN: memset
; CHECK-EABI: __aeabi_memset8
call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 8, i1 false)
; CHECK-IOS: memset
; CHECK-DARWIN: memset
; CHECK-EABI: __aeabi_memclr8
call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i32 8, i1 false)
unreachable
}
@@ -53,17 +104,17 @@ entry:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
; CHECK-IOS: mov r0, sp
; CHECK-IOS: mov r1, #0
; CHECK-IOS: mov r1, #1
; CHECK-IOS: memset
; CHECK-DARINW: add r0, sp, #4
; CHECK-DARWIN: movs r1, #0
; CHECK-DARWIN: add r0, sp, #4
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: memset
; CHECK-EABI: add r0, sp, #4
; CHECK-EABI: mov r2, #0
; CHECK-EABI: mov r2, #1
; CHECK-EABI: __aeabi_memset
%arr2 = alloca [9 x i8], align 1
%2 = bitcast [9 x i8]* %arr2 to i8*
call void @llvm.memset.p0i8.i32(i8* %2, i8 0, i32 %n, i32 0, i1 false)
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
unreachable
}
@@ -90,15 +141,15 @@ entry:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
; CHECK: {{add(.w)? r0, sp, #3}}
; CHECK-IOS: mov r1, #0
; CHECK-IOS: mov r1, #1
; CHECK-IOS: memset
; CHECK-DARWIN: movs r1, #0
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: memset
; CHECK-EABI: mov r2, #0
; CHECK-EABI: mov r2, #1
; CHECK-EABI: __aeabi_memset
%arr2 = alloca [7 x i8], align 1
%2 = bitcast [7 x i8]* %arr2 to i8*
call void @llvm.memset.p0i8.i32(i8* %2, i8 0, i32 %n, i32 0, i1 false)
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
unreachable
}
@@ -125,15 +176,15 @@ entry:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)}}
; CHECK-IOS: mov r1, #0
; CHECK-IOS: mov r1, #1
; CHECK-IOS: memset
; CHECK-DARWIN: movs r1, #0
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: memset
; CHECK-EABI: mov r2, #0
; CHECK-EABI: mov r2, #1
; CHECK-EABI: __aeabi_memset
%arr2 = alloca [9 x i8], align 1
%2 = getelementptr inbounds [9 x i8], [9 x i8]* %arr2, i32 0, i32 4
call void @llvm.memset.p0i8.i32(i8* %2, i8 0, i32 %n, i32 0, i1 false)
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
unreachable
}
@@ -160,15 +211,15 @@ entry:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)}}
; CHECK-IOS: mov r1, #0
; CHECK-IOS: mov r1, #1
; CHECK-IOS: memset
; CHECK-DARWIN: movs r1, #0
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: memset
; CHECK-EABI: mov r2, #0
; CHECK-EABI: mov r2, #1
; CHECK-EABI: __aeabi_memset
%arr2 = alloca [13 x i8], align 1
%2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 1
call void @llvm.memset.p0i8.i32(i8* %2, i8 0, i32 %n, i32 0, i1 false)
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
unreachable
}
@@ -195,15 +246,15 @@ entry:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)}}
; CHECK-IOS: mov r1, #0
; CHECK-IOS: mov r1, #1
; CHECK-IOS: memset
; CHECK-DARWIN: movs r1, #0
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: memset
; CHECK-EABI: mov r2, #0
; CHECK-EABI: mov r2, #1
; CHECK-EABI: __aeabi_memset
%arr2 = alloca [13 x i8], align 1
%2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 %i
call void @llvm.memset.p0i8.i32(i8* %2, i8 0, i32 %n, i32 0, i1 false)
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
unreachable
}
@@ -230,15 +281,15 @@ entry:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)}}
; CHECK-IOS: mov r1, #0
; CHECK-IOS: mov r1, #1
; CHECK-IOS: memset
; CHECK-DARWIN: movs r1, #0
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: memset
; CHECK-EABI: mov r2, #0
; CHECK-EABI: mov r2, #1
; CHECK-EABI: __aeabi_memset
%arr2 = alloca [13 x i8], align 1
%2 = getelementptr [13 x i8], [13 x i8]* %arr2, i32 0, i32 4
call void @llvm.memset.p0i8.i32(i8* %2, i8 0, i32 %n, i32 0, i1 false)
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
unreachable
}
@@ -265,15 +316,15 @@ entry:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)}}
; CHECK-IOS: mov r1, #0
; CHECK-IOS: mov r1, #1
; CHECK-IOS: memset
; CHECK-DARWIN: movs r1, #0
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: memset
; CHECK-EABI: mov r2, #0
; CHECK-EABI: mov r2, #1
; CHECK-EABI: __aeabi_memset
%arr2 = alloca [13 x i8], align 1
%2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 16
call void @llvm.memset.p0i8.i32(i8* %2, i8 0, i32 %n, i32 0, i1 false)
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
unreachable
}