Age | Commit message (Collapse) | Author | |
---|---|---|---|
2012-02-21 | Initial partial conversion to SPU assembly | Siarhei Siamashka | |
Only the first loop is converted. The performance is increased up to ~5.97 khash/sec per SPE core. TODO: try to update it to use better data layout and more unrolling from shakti's variant. | |||
2012-01-01 | Fix strict aliasing problems | Siarhei Siamashka | |
Currently the cast between uint32_t and uint64_t pointers breaks strict aliasing rules and needs -fno-strict-aliasing option as a workaround, otherwise the code gets miscompiled. But -fno-strict-aliasing can seriously inhibit optimization possibilities. For example, performance of 1 thread on Cell PPU (using Altivec instructions): CFLAGS="-O3 -mcpu=cell -fno-strict-aliasing" - 1.79 khash/sec CFLAGS="-O3 -mcpu=cell -fstrict-aliasing" - 2.60 khash/sec | |||
2011-12-29 | Added Cell/BE optimizations | Siarhei Siamashka | |
Linux on PS3 gets a huge boost in litecoin mining performance. Cell/BE support should be detected and enabled automatically by autotools. The miner threads are first allocated to the available SPU cores (typically 6). The remaining threads are allocated on PPU. There will be 8 threads total on PS3: 6 SPU threads and 2 PPU threads. Each SPU core provides ~5.4 khash/s if compiled with spu-elf-gcc 4.6 The performance may vary for different gcc versions, older ones are typically slower. | |||
2011-12-29 | Use gcc vector extensions for SIMD scrypt key derivation function | Siarhei Siamashka | |
The code can be compiled for different architectures from the same source starting with gcc 4.7. But SSE2/Altivec/SPU targets have compatibility wrappers, which also allow the use of older versions of gcc. Two hashes are processed at the same time, so twice bigger scratch buffer is needed (~256K vs. ~128K). Speedup on Cell PPU (32-bit), single thread, 3.2GHz: ~0.58 khash/s -> ~1.79 khash/sec | |||
2011-12-29 | SHA256 code moved to a separate header file | Siarhei Siamashka | |
2011-10-01 | Rip out sha256 algos | Art Forz | |
2011-09-20 | add scrypt function | Art Forz | |
2011-06-08 | Fix libcurl include path | Christian Ludwig | |
Fix the include path for libcurl, if it was installed in a location where gcc does not look by default. The variable is declared in the LIBCURL_CHECK_CONFIG m4 macro. | |||
2011-04-11 | Proper platform detection. | fleger | |
Use target instead of host. Fix compilation for non win32 and non x86_64 platforms. | |||
2011-03-14 | Fix Windows build, that broke with yasm integration | Jeff Garzik | |
2011-03-14 | Move all RPC I/O to separate thread. | Jeff Garzik | |
2011-03-14 | Makefile.am: neaten minerd sources list | Jeff Garzik | |
2011-03-06 | X86_64 SSE2 support for Linux | Mark Crichton | |
2011-02-13 | Add support for JSON-format configuration file | Jeff Garzik | |
2010-11-28 | Add Crypto++ sha256 implementation (C only, ASM elided for now) | Jeff Garzik | |
2010-11-27 | Move sha256_generic into its own .o build output. Const-ify midstate param. | Jeff Garzik | |
2010-11-27 | Add experimental (read: probably broken) VIA padlock support. | Jeff Garzik | |
2010-11-26 | Add tcatm's 4way SSE2 sha256 implementation. | Jeff Garzik | |
2010-11-26 | Build on Windows using mingw32. | Jeff Garzik | |
2010-11-26 | Build jansson 1.3 in-tree, if not present on system. | Jeff Garzik | |
2010-11-26 | Makefile.am: add compat.h, to correct 'make distcheck' failures | Jeff Garzik | |
2010-11-26 | Link with pthreads lib, if present. Remove GNU-specific asprintf usage. | Jeff Garzik | |
2010-11-25 | Move utility routines to util.c. | Jeff Garzik | |
2010-11-25 | Allocate work struct once, on stack, rather than alloc+free for each getwork. | Jeff Garzik | |
2010-11-25 | Remove unused OpenSSL dependency. | Jeff Garzik | |
Also, turn a few strings into #define'd constants. | |||
2010-11-24 | Do not build sha256_generic module separate from cpu-miner.c. Version 0.1.1.v0.1.1 | Jeff Garzik | |
2010-11-24 | Convert over to autotools. Release version 0.1.v0.1 | Jeff Garzik | |