llvm-mirror

mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 01:03:52 +00:00

Go to file

Chris Lattner 138a3fc9ab Completely eliminate the per-machine-instruction regsUsed set.

This substantially shrinks the size of each machine instruction, which should
make allocation faster and the cache footprint of the machine code lighter.

Here are some timings for code generation of the larger benchmarks we have.
This are timings of code generation phases of the X86 JIT, when compiled in
debug mode:

		Before	After	Diff
164.gzip:
  InstSel	0.0878	0.0722	-21.6%
  RegAlloc	0.2031	0.1757	-15.6%
  TOTAL		0.5585	0.4999	-11.7%
Ptrdist-bc:
  InstSel	0.0878	0.0722	-21.6%
  RegAlloc	0.2070	0.1933	- 7.1%
  TOTAL		0.6972	0.6464	- 7.9%
197.parser:
  InstSel	0.2148	0.2148	- 0.0%
  RegAlloc	0.4941	0.4277	-15.5%
  TOTAL		1.3749	1.2851	- 7.0%
175.vpr:
  InstSel	0.2519	0.2109	-19.4%
  RegAlloc	0.5976	0.5663	- 5.5%
  TOTAL		1.6933	1.6347	- 3.5%
254.gap:
  InstSel	1.1328	0.9921	-14.2%
  RegAlloc	2.6933	2.4804	- 8.6%
  TOTAL		7.7871	7.2499	- 7.4%

llvm-svn: 7622

2003-08-05 22:39:13 +00:00

autoconf

Removed the -only-static option as it is no longer required (and didn't work

2003-07-31 20:59:32 +00:00

docs

Fix a bug

2003-08-01 22:26:27 +00:00

include

Completely eliminate the per-machine-instruction regsUsed set.

2003-08-05 22:39:13 +00:00

lib

Use a new local data structure instead of the MachineInstr::regsUsed set