mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-05 17:30:02 +00:00
acc068e873
X86ISelLowering C++ code. Because this is lowered via an xor wrapped around a bsr, we want the dagcombine which runs after isel lowering to have a chance to clean things up. In particular, it is very common to see code which looks like: (sizeof(x)*8 - 1) ^ __builtin_clz(x) Which is trying to compute the most significant bit of 'x'. That's actually the value computed directly by the 'bsr' instruction, but if we match it too late, we'll get completely redundant xor instructions. The more naive code for the above (subtracting rather than using an xor) still isn't handled correctly due to the dagcombine getting confused. Also, while here fix an issue spotted by inspection: we should have been expanding the zero-undef variants to the normal variants when there is an 'lzcnt' instruction. Do so, and test for this. We don't want to generate unnecessary 'bsr' instructions. These two changes fix some regressions in encoding and decoding benchmarks. However, there is still a *lot* to be improve on in this type of code. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147244 91177308-0d34-0410-b5e6-96231b3b80d8
63 lines
1.3 KiB
LLVM
63 lines
1.3 KiB
LLVM
; RUN: llc < %s -march=x86-64 -mattr=+lzcnt | FileCheck %s
|
|
|
|
declare i8 @llvm.ctlz.i8(i8, i1) nounwind readnone
|
|
declare i16 @llvm.ctlz.i16(i16, i1) nounwind readnone
|
|
declare i32 @llvm.ctlz.i32(i32, i1) nounwind readnone
|
|
declare i64 @llvm.ctlz.i64(i64, i1) nounwind readnone
|
|
|
|
define i8 @t1(i8 %x) nounwind {
|
|
%tmp = tail call i8 @llvm.ctlz.i8( i8 %x, i1 false )
|
|
ret i8 %tmp
|
|
; CHECK: t1:
|
|
; CHECK: lzcntw
|
|
}
|
|
|
|
define i16 @t2(i16 %x) nounwind {
|
|
%tmp = tail call i16 @llvm.ctlz.i16( i16 %x, i1 false )
|
|
ret i16 %tmp
|
|
; CHECK: t2:
|
|
; CHECK: lzcntw
|
|
}
|
|
|
|
define i32 @t3(i32 %x) nounwind {
|
|
%tmp = tail call i32 @llvm.ctlz.i32( i32 %x, i1 false )
|
|
ret i32 %tmp
|
|
; CHECK: t3:
|
|
; CHECK: lzcntl
|
|
}
|
|
|
|
define i64 @t4(i64 %x) nounwind {
|
|
%tmp = tail call i64 @llvm.ctlz.i64( i64 %x, i1 false )
|
|
ret i64 %tmp
|
|
; CHECK: t4:
|
|
; CHECK: lzcntq
|
|
}
|
|
|
|
define i8 @t5(i8 %x) nounwind {
|
|
%tmp = tail call i8 @llvm.ctlz.i8( i8 %x, i1 true )
|
|
ret i8 %tmp
|
|
; CHECK: t5:
|
|
; CHECK: lzcntw
|
|
}
|
|
|
|
define i16 @t6(i16 %x) nounwind {
|
|
%tmp = tail call i16 @llvm.ctlz.i16( i16 %x, i1 true )
|
|
ret i16 %tmp
|
|
; CHECK: t6:
|
|
; CHECK: lzcntw
|
|
}
|
|
|
|
define i32 @t7(i32 %x) nounwind {
|
|
%tmp = tail call i32 @llvm.ctlz.i32( i32 %x, i1 true )
|
|
ret i32 %tmp
|
|
; CHECK: t7:
|
|
; CHECK: lzcntl
|
|
}
|
|
|
|
define i64 @t8(i64 %x) nounwind {
|
|
%tmp = tail call i64 @llvm.ctlz.i64( i64 %x, i1 true )
|
|
ret i64 %tmp
|
|
; CHECK: t8:
|
|
; CHECK: lzcntq
|
|
}
|