13241 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
Kovid Goyal	ef8e8313ab	For some reason, memcpy is faster than assignment	2024-02-25 09:57:28 +05:30
Kovid Goyal	17cb65e981	Adjust amount of data in the benchmarks for more consistent timing	2024-02-25 09:57:28 +05:30
Kovid Goyal	f2153f060d	add unicode benchmark	2024-02-25 09:57:28 +05:30
Kovid Goyal	48c0b30671	Install simde on CI	2024-02-25 09:57:28 +05:30
Kovid Goyal	e8f67281cf	Warmup font rendering before running benchmark	2024-02-25 09:57:28 +05:30
Kovid Goyal	49a54b086f	Use simde so SIMD speedups work on ARM as well	2024-02-25 09:57:28 +05:30
Kovid Goyal	4790959938	Use -fno-plt ... We dont need the PLT and it frees up some registers	2024-02-25 09:57:28 +05:30
Kovid Goyal	33249c872f	Use a better default march for binary builds ... x86-64-v2 implies SSE4.2 which should be available everywhere by now. We will see if we get errors with it. https://developers.redhat.com/blog/2021/01/05/building-red-hat-enterprise-linux-9-for-the-x86-64-v2-microarchitecture-level#architectural_considerations_for_rhel_9	2024-02-25 09:57:28 +05:30
Kovid Goyal	71bf099041	Speed up drawing of printable ascii chars	2024-02-25 09:57:28 +05:30
Kovid Goyal	307acb3f64	Add API to Screen to draw a set of printable ascii chars fast	2024-02-25 09:57:28 +05:30
Kovid Goyal	e5675e9537	Simplify API	2024-02-25 09:57:28 +05:30
Kovid Goyal	9cf425006f	...	2024-02-25 09:57:28 +05:30
Kovid Goyal	c052831291	Dont double parse CSI digits	2024-02-25 09:57:28 +05:30
Kovid Goyal	fe2cd543ba	Switch to same algorithm for 128bit SIMD as used for 256 bit SIMD ... Avoids needing to write to the haystack and also less chance of a bug in the never tested simd since all CPUs I have access to have AVX2	2024-02-25 09:57:28 +05:30
Kovid Goyal	1925d5ea65	Prepare for plain sse4 fallback	2024-02-25 09:57:27 +05:30
Kovid Goyal	aacdffd539	DRYer	2024-02-25 09:57:27 +05:30
Kovid Goyal	a0e1eb4985	AVX2 implementation for find either of two	2024-02-25 09:57:27 +05:30
Kovid Goyal	e4c48a5f17	Add AVX2 implementation of find byte not in range ... Also fix alignment bug and ensure the simd finders dont return a pointer beyond the end	2024-02-25 09:57:27 +05:30
Kovid Goyal	021dd168e5	...	2024-02-25 09:57:27 +05:30
Kovid Goyal	b032313c45	Only use SIMD if CPU supports it at runtime	2024-02-25 09:57:27 +05:30
Kovid Goyal	19a41b4d9a	Use sse4.2 instruction for normal mode printable ascii detection	2024-02-25 09:57:27 +05:30
Kovid Goyal	25e7a2882d	Work on using SIMD for normal mode dispatch	2024-02-25 09:57:27 +05:30
Kovid Goyal	a75fb6509e	...	2024-02-25 09:57:27 +05:30
Kovid Goyal	23c42cb555	...	2024-02-25 09:57:27 +05:30
Kovid Goyal	1f8feea454	Parse new data that is writtne while parsing is in progress in the parse loop ... Avoids unnecessary memmove()	2024-02-25 09:57:27 +05:30
Kovid Goyal	f0afdc51af	...	2024-02-25 09:57:27 +05:30
Kovid Goyal	ac6afcb0a8	Release the parser IO lock while parsing	2024-02-25 09:57:27 +05:30
Kovid Goyal	ad7f671a7b	Add a long escape code benchmark	2024-02-25 09:57:27 +05:30
Kovid Goyal	4f67b8b433	Need -msse4.2 on non-native builds	2024-02-25 09:57:27 +05:30
Kovid Goyal	e3d6aa2c60	Use simd in a few loops	2024-02-25 09:57:27 +05:30
Kovid Goyal	89d416806b	...	2024-02-25 09:57:26 +05:30
Kovid Goyal	859b0cc585	Include -march=native for debug builds	2024-02-25 09:57:26 +05:30
Kovid Goyal	8b4209cb97	Also use fast find for pending mode	2024-02-25 09:57:26 +05:30
Kovid Goyal	8dca5a6b9a	...	2024-02-25 09:57:26 +05:30
Kovid Goyal	200e5bf6e3	Examine 8 bytes at once for terminator char	2024-02-25 09:57:26 +05:30
Kovid Goyal	f4819175b0	Start work on vectorizing searches	2024-02-25 09:57:26 +05:30
Kovid Goyal	5921ca1139	Add images benchmark	2024-02-25 09:57:26 +05:30
Kovid Goyal	dbc4b98742	Ignore input_delay when the input buffer is close to full	2024-02-25 09:57:26 +05:30
Kovid Goyal	822c9cb1d6	...	2024-02-25 09:57:26 +05:30
Kovid Goyal	529de9c91d	Allow specifying benchmarks to run on the command line	2024-02-25 09:57:26 +05:30
Kovid Goyal	7914523a16	Add a CSI + ascii test	2024-02-25 09:57:26 +05:30
Kovid Goyal	d39c71f927	Round the time to two digit precision	2024-02-25 09:57:26 +05:30
Kovid Goyal	934f2ede0b	Start work on simple benchmark tool	2024-02-25 09:57:26 +05:30
Kovid Goyal	8dbea2a046	...	2024-02-25 09:57:26 +05:30
Kovid Goyal	38c8100a76	...	2024-02-25 09:57:26 +05:30
Kovid Goyal	a560d86d0f	Use aligned loads for the byte loader	2024-02-25 09:57:26 +05:30
Kovid Goyal	47a493c090	Increase chunk size for graphics protocol since the VT parser now supports it	2024-02-25 09:57:25 +05:30
Kovid Goyal	35da87994b	Fix input_delay not working	2024-02-25 09:57:25 +05:30
Kovid Goyal	f49f2a1b82	Fix buf full -> not full reporting	2024-02-25 09:57:25 +05:30
Kovid Goyal	91c3492455	Allow logging code to log arbitrary length messages	2024-02-25 09:57:25 +05:30