popov/cpuminer-opt-gpu
1
0
Fork 0
mirror of https://github.com/JayDDee/cpuminer-opt.git synced 2025-09-17 23:44:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated Support for AArch64 (markdown)

JayDDee
2023-10-19 17:27:02 -04:00
parent d482e0e581
commit e941281471
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
Support-for-AArch64.md

@@ -26,7 +26,8 @@ Uncommited changes:
The miner compiles and runs on Raspberry Pi 4B, and compiles for all version of armv8 with our without AES and SHA2. The miner compiles and runs on Raspberry Pi 4B, and compiles for all version of armv8 with our without AES and SHA2.
Things that have been tested to work: Things that have been tested to work:
* sha256dt: unoptimized is working, SHA2 is enabled but untested, 4way currently disabled. * Argon2d is working with NEON.
* Sha256dt: unoptimized is working, SHA2 is enabled but untested, 4way currently disabled.
* x17: working with Blake 2way, Keccak 2way and Cubehash linear vectorization, Shavite AES is enabled and compiles but untested, all other optimizations disabled. * x17: working with Blake 2way, Keccak 2way and Cubehash linear vectorization, Shavite AES is enabled and compiles but untested, all other optimizations disabled.
* m7m: unoptimzed is working, SHA2 is enabled but untested. * m7m: unoptimzed is working, SHA2 is enabled but untested.
* stratum+ssl is working * stratum+ssl is working
@@ -34,7 +35,6 @@ Things that have been tested to work:
* CPU temperature and clock frequency is working. * CPU temperature and clock frequency is working.
Known problems: Known problems:
* Argon2d: problems with widening multiplication
* Simd: Problem with algebraic shift right and widening multiplication, x* reduced performance. * Simd: Problem with algebraic shift right and widening multiplication, x* reduced performance.
* SWIFFTX: Algebraic shift right and widening multiplication, X22i & x25x performance further reduced. * SWIFFTX: Algebraic shift right and widening multiplication, X22i & x25x performance further reduced.
* Yespower, Yescrypt: widening multiplication issue. * Yespower, Yescrypt: widening multiplication issue.
@@ -43,4 +43,4 @@ Goal for next release:
* get as many algos as possible working even if optimizations need to be disabled, * get as many algos as possible working even if optimizations need to be disabled,
* address some of the disabled optimizations, * address some of the disabled optimizations,
* enable SHA2, and AES for Groestl & Echo, but they will be untested. * enable SHA2, and AES for Groestl & Echo, untested.