Tim Northover 37abe8df4a Use VLD1 in NEON extenting-load patterns instead of VLDR. ...

On some cores it's a bad idea for performance to mix VFP and NEON instructions
and since these patterns are NEON anyway, the NEON load should be used.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155630 91177308-0d34-0410-b5e6-96231b3b80d8

2012-04-26 08:46:29 +00:00

..

ARM

Use VLD1 in NEON extenting-load patterns instead of VLDR.

2012-04-26 08:46:29 +00:00

CellSPU

Flip the new block-placement pass to be on by default.

2012-04-16 13:49:17 +00:00

CPP

Continue cleanup of LIT, getting rid of the remaining artifacts from dejagnu

2012-03-25 09:02:19 +00:00

Generic

Move to X86 directory because this fails on non-X86 platforms.

2012-04-16 16:38:48 +00:00

Hexagon

Revert r155365, r155366, and r155367. All three of these have regression

2012-04-23 18:25:57 +00:00

MBlaze

Continue cleanup of LIT, getting rid of the remaining artifacts from dejagnu

2012-03-25 09:02:19 +00:00

Mips

Do not use $gp as a dedicated global register if the target ABI is not O32.

2012-04-25 01:24:52 +00:00

MSP430

Continue cleanup of LIT, getting rid of the remaining artifacts from dejagnu

2012-03-25 09:02:19 +00:00

PowerPC

Remove dead SD nodes after the combining pass. Fixes PR12201.

2012-04-16 03:33:22 +00:00

PTX

Continue cleanup of LIT, getting rid of the remaining artifacts from dejagnu

2012-03-25 09:02:19 +00:00

SPARC

Continue cleanup of LIT, getting rid of the remaining artifacts from dejagnu

2012-03-25 09:02:19 +00:00

Thumb

Continue cleanup of LIT, getting rid of the remaining artifacts from dejagnu

2012-03-25 09:02:19 +00:00

Thumb2

If triple is armv7 / thumbv7 and a CPU is specified, do not automatically assume

2012-04-26 01:13:36 +00:00

X86

Try to fix llvm-arm-linux builder with -mcpu.

2012-04-25 21:22:33 +00:00

XCore

Flip the new block-placement pass to be on by default.

2012-04-16 13:49:17 +00:00