tomgall/meego/libjpeg-turbo.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
2010-11-10	ARM NEON optimizations for quantization code in 'forward_DCT'HEAD master	Siarhei Siamashka
	Integer divisions replaced with floating point multiplications. Code is still bitexact (calculations produce the same results for all the possible range of input values). This optimized function is now almost 3x faster than original C variant and improves encoding performance somewhat.
2010-11-10	ARM assembly optimizations for 'encode_one_block'	Siarhei Siamashka
	Almost 2x faster than original C variant.
2010-11-10	ARM NEON optimized version of 'rgb_ycc_convert'	Siarhei Siamashka
	Is approximately 10x faster than original C variant.
2010-11-10	ARM NEON optimized version of 'ycc_rgb_convert'	Siarhei Siamashka
	Is approximately 6x faster than original C variant.
2010-11-10	A minor ARM NEON optimization for 'convsamp'	Siarhei Siamashka

2010-11-10	ARM NEON optimized version of 'jpeg_fdct_ifast'	Siarhei Siamashka
	Is approximately 4x faster than original C variant.
2010-11-10	ARM NEON optimized version of 'jpeg_idct_ifast'	Siarhei Siamashka
	Is approximately 4x faster than original C variant.
2010-11-10	ARM NEON optimized version of 'jpeg_idct_4x4'	Siarhei Siamashka
	Is approximately 4x faster than original C variant.
2010-11-10	Added support for ARM optimizations to configure.ac	Siarhei Siamashka
	ARM NEON optimizations need the use of 16-bit data types and benefit from 16-byte alignemnt, so we want to have macro WITH_SIMD defined in the code. Also automated tests are updated to work correctly on ARM. And the required stubs for ARM optimizations added (just copied from 'jsimd_none.c').
2010-11-10	Initial import of upstream libjpeg-turbo (svn revision 290)	Siarhei Siamashka