standard daxpy needs implementing and writing up (brief internet-blog style)
step by step writeup, TODO move the page to cookbook. https://git.libre-soc.org/?p=libreriscv.git;a=commitdiff;h=d4bd4fb2f
Luke just wanted to confirm, is the budget breakdown for this task correct? Currently the TOML field shows the full 2000 EUR assigned to Red.
(In reply to Andrey Miroshnikov from comment #2) > Luke just wanted to confirm, is the budget breakdown for this task correct? > Currently the TOML field shows the full 2000 EUR assigned to Red. unless i need it in an emergency, yes. i have to check my personal bank account to see where it stands.
(In reply to Luke Kenneth Casson Leighton from comment #3) > i have to check my personal bank account to see where > it stands. down to GBP 3,000 this will have to be split 50-50
a quick re-read to ensure that before approving the RED RFP that it looks good for NLnet to review and accept, i added this additional paragraph which helps explain and justify the huge number (30+ !) of LD/ST Post-Increment Update instructions that Libre-SOC is proposing. their value is enormous, they get added to every high-end ISA but Power lacks them as they take up a HELL of a lot of Opcode space, and Power ISA is under significant opcode pressure. hm just spotted a spelling error... fixed. https://git.libre-soc.org/?p=libreriscv.git;a=commitdiff;h=c56745a2ad3 of the next batch. +If `sv.lfdup` was not available, `sv.lfdu` could be used to the same +effect, but RA would have to be *pre-subtracted by one element*, outside +of the loop. Due to the compactness of this highly hardware-parallelizable +algorithm, that one additinal instruction would increase the implementation +code size by 5 percent! This helps explain why Post-Increment Update +Load/Store instructions are so important.