Chris Lattner a2b5600e61 Improve an integer select optimization in two ways: ... 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120929 91177308-0d34-0410-b5e6-96231b3b80d8		2010-12-05 01:23:24 +00:00
..
Alpha
ARM	ARM/MC/ELF relocation "hello world" for movw/movt.	2010-12-01 02:40:06 +00:00
Blackfin
CBackend
CellSPU	Handle lshr for i128 correctly on SPU also when	2010-11-29 14:44:28 +00:00
CPP
Generic
MBlaze
Mips
MSP430
PowerPC	remove a pointless testcase.	2010-11-15 05:07:03 +00:00
PTX	ptx: add command-line options for gpu target and ptx version	2010-11-30 10:14:14 +00:00
SPARC
SystemZ
Thumb
Thumb2	The Thumb tADDrSPi instruction is not valid when the destination is SP.	2010-12-04 04:40:19 +00:00
X86	Improve an integer select optimization in two ways:	2010-12-05 01:23:24 +00:00
XCore
thumb2-mul.ll