Rémi Denis-Courmont 15c3a0bd6e lavc/aacpsdsp: RISC-V V hybrid_analysis ... This starts with one-time initialisation of the 26 constant factors like 08edacc248. That is done with the scalar instruction set. While the formula can readily be vectored, the gains would (probably) be more than lost in transfering the results back to FP registers (or suitably reshuffling them into vector registers). Note that the main loop could likely be scheduled sligthly better by expanding the filter macro and interleaving loads with arithmetic. It is not clear yet if that would be relevant for vector processing (as opposed to traditional SIMD). We could also use fewer vectors, but there is not much point in sparing them (they are *all* callee-clobbered).		2022-09-27 13:19:52 +02:00
..
Makefile	lavc/aacpsdsp: RISC-V V add_squares	2022-09-27 13:19:52 +02:00
aacpsdsp_init.c	lavc/aacpsdsp: RISC-V V hybrid_analysis	2022-09-27 13:19:52 +02:00
aacpsdsp_rvv.S	lavc/aacpsdsp: RISC-V V hybrid_analysis	2022-09-27 13:19:52 +02:00
audiodsp_init.c	lavc/audiodsp: RISC-V V scalarproduct_int16	2022-09-27 13:19:52 +02:00
audiodsp_rvf.S	…
audiodsp_rvv.S	lavc/audiodsp: RISC-V V scalarproduct_int16	2022-09-27 13:19:52 +02:00
fmtconvert_init.c	lavc/fmtconvert: RISC-V V int32_to_float_fmul_array8	2022-09-27 13:19:52 +02:00
fmtconvert_rvv.S	lavc/fmtconvert: RISC-V V int32_to_float_fmul_array8	2022-09-27 13:19:52 +02:00
pixblockdsp_init.c	…
pixblockdsp_rvi.S	…
vorbisdsp_init.c	lavc/vorbisdsp: RISC-V V inverse_coupling	2022-09-27 13:19:52 +02:00
vorbisdsp_rvv.S	lavc/vorbisdsp: RISC-V V inverse_coupling	2022-09-27 13:19:52 +02:00