Kyle Butt 08655997eb CodeGen: BlockPlacement: Reduce TriangleChainCount to 2 ...

This produces a 1% speedup on an important internal Google benchmark
(protocol buffers), with no other regressions in google or in the llvm
test-suite. Only 5 targets in the entire llvm test-suite are affected,
and on those 5 targets the size increase is 0.027%

llvm-svn: 297925

2017-03-16 01:32:29 +00:00

..

add.ll

[DAG] optimize negation of bool

2016-10-19 16:58:59 +00:00

addrspacecast.ll

[mips] Reserve address spaces 1-255 for software use.

2015-09-08 09:07:03 +00:00

and.ll

[mips] interAptiv based generic schedule model

2016-09-01 14:53:53 +00:00

ashr.ll

CodeGen: BlockPlacement: Reduce TriangleChainCount to 2

2017-03-16 01:32:29 +00:00

atomicrmx.ll

[mips] Define patterns for the atomic_{load,store}_{8,16,32,64} nodes.

2015-11-06 12:07:20 +00:00

call.ll

[mips] Recommit: "N64 static relocation model support"

2017-01-27 11:36:52 +00:00

extractelement.ll

DAG: Avoid OOB when legalizing vector indexing

2017-01-10 22:02:30 +00:00

indirectbr.ll

[mips] Correct label prefixes for N32 and N64.

2016-07-19 10:49:03 +00:00

lh_lhu.ll

[mips] Don't derive the default ABI from the CPU in the backend.

2016-06-23 12:42:53 +00:00

load-atomic.ll

[mips] Use --check-prefixes where appropriate. NFC.

2016-06-24 12:23:17 +00:00

lshr.ll

CodeGen: BlockPlacement: Reduce TriangleChainCount to 2

2017-03-16 01:32:29 +00:00

mul.ll

[DAG] optimize negation of bool

2016-10-19 16:58:59 +00:00

not.ll

[mips] interAptiv based generic schedule model

2016-09-01 14:53:53 +00:00

or.ll

[mips] interAptiv based generic schedule model

2016-09-01 14:53:53 +00:00

ret.ll

[mips] Optimize materialization of i64 constants

2016-07-25 09:57:28 +00:00

sdiv.ll

[DAG] optimize negation of bool

2016-10-19 16:58:59 +00:00

select-dbl.ll

[mips] Correct label prefixes for N32 and N64.

2016-07-19 10:49:03 +00:00

select-flt.ll

[mips] interAptiv based generic schedule model

2016-09-01 14:53:53 +00:00

select-int.ll

[mips] interAptiv based generic schedule model

2016-09-01 14:53:53 +00:00

shl.ll

CodeGen: BlockPlacement: Reduce TriangleChainCount to 2

2017-03-16 01:32:29 +00:00

sqrt.ll

[mips][microMIPS] Fix an issue with selecting sqrt instruction in LLVM backend

2015-10-06 15:17:25 +00:00

srem.ll

[DAG] optimize negation of bool

2016-10-19 16:58:59 +00:00

store-atomic.ll

[mips] Use --check-prefixes where appropriate. NFC.

2016-06-24 12:23:17 +00:00

sub.ll

[DAG] optimize negation of bool

2016-10-19 16:58:59 +00:00

udiv.ll

[mips] Preparatory work for a generic scheduler

2016-08-24 13:00:47 +00:00

urem.ll

[DAG] optimize negation of bool

2016-10-19 16:58:59 +00:00

xor.ll

[mips] interAptiv based generic schedule model

2016-09-01 14:53:53 +00:00