tevador
2a04dfdd4f
Fixed x87 math precision (i386 build)
5 years ago
tevador
afaeff6066
Fixed incorrect sqrt results on 32bit targets using x87 math
...
Cleaner implementation of FSWAP
5 years ago
tevador
1aa7865619
Abstracted away from x86 intrinsics
5 years ago
tevador
3dd21ea93d
Prepare for JIT compiler support for other platforms
5 years ago
tevador
a560cec3e7
Clarifications/corrections in the specification/comments
...
Removed some unused code
5 years ago
tevador
3f7139d3aa
Fixed a possibility of buffer overflow in Superscalar generator
5 years ago
tevador
a78429202b
Query for LargePageMinimum on Windows
5 years ago
tevador
c1314dc2a2
Use values from configuration.h in assembly code
5 years ago
tevador
4934bbf69d
Updated documentation
5 years ago
tevador
40a08bb0c8
Fixed incorrect latency of mul_r in SuperscalarHash
5 years ago
tevador
a22e3b3cb0
30% faster JIT compiler
5 years ago
tevador
b1f1e1d6ad
Fixed IMUL_RCP if divisor is a power of 2
5 years ago
tevador
b62b1f8717
Added scratchpad entropy test
5 years ago
tevador
cb3d57376f
Fixed API examples
5 years ago
tevador
9e5eac8645
Fixed a chance of CBRANCH looping
...
Fixed CBRANCH jump probability being lower than expected
5 years ago
tevador
01db567e9d
Fixed an inconsistency in IADD_RS in SuperscalarHash
5 years ago
tevador
c87dcc8ae5
Cache seed renamed to key
5 years ago
tevador
1a4bde36be
Fixed a missing header dependency
5 years ago
tevador
ca96270509
Group E exponent changed from a static value (-240) to dynamic
5 years ago
tevador
be21ba767c
Doubled the frequency of CBRANCH, halved the jumping probability
5 years ago
tevador
3cf6a30076
Fixed biased condition register selection
5 years ago
tevador
5543fb5f2f
Removed unused code
5 years ago
tevador
ffebc37381
COND_R instruction reworked as CBRANCH
...
instruction mod field bits reallocated
5 years ago
tevador
ebddaf671c
Alignment of x86 code for SuperscalarHash made optional
5 years ago
tevador
cf72ed79c7
Function typedefs without pointer
5 years ago
tevador
7f6bdd9a52
Code cleanup & refactoring
5 years ago
tevador
22a3aa8d79
randomx_cache and randomx_dataset changed to standard-layout structs
5 years ago
tevador
fd7186f873
Changed IADD_RS to use mod.mem
5 years ago
tevador
ff88a57a98
Fixed reading from the red zone
5 years ago
tevador
e758c1e2b2
Fixed non-x86 compilation
5 years ago
tevador
270a4f97fe
Dataset size increased to 2080 MiB
...
Implemented dataset base offset
Tweaked SuperscalarHash constants to prevent register collisions
5 years ago
tevador
f66da3911e
Fixed some compilation issues
...
Code cleanup
5 years ago
tevador
018c1a5222
Big endian bug fixes
5 years ago
tevador
1c3666aa98
Fixed benchmark code
5 years ago
tevador
b4dca14f0c
Added a function to access the dataset memory buffer
...
Number of dataset items changed from a macro to a getter function.
5 years ago
tevador
59d82bbb01
Fixed doc
5 years ago
tevador
4c66b2305a
Formatting & refactoring
5 years ago
tevador
87b8253374
API documentation
...
'dataset block' -> 'dataset item'
customizable benchmark seed
5 years ago
tevador
bc78b628ea
Flags ordered by their impact on performance
...
Additional error handling
5 years ago
tevador
d30eef75af
Fixed non-x86 compilation
5 years ago
tevador
a8c7137873
Linux makefile
...
Exception handling
5 years ago
tevador
41b51a4858
Cleaned up legacy code
5 years ago
tevador
360c8ed913
Fixed superscalar test projects
5 years ago
tevador
0d21ae85fc
Remove capital letters from filenames #3
5 years ago
tevador
f9ea7cc1df
Remove capital letters from filenames #2
5 years ago
tevador
41557ce010
randomx project changed to a static library
...
separate benchmark project
API usage examples
5 years ago
tevador
d7eefce583
Removed capital letters from filenames
5 years ago
tevador
d7276d5786
Reduced the number of virtual calls per hash
5 years ago
tevador
296e77eebc
C API - first working version
5 years ago
tevador
67046a9f38
Full-width mantissa for group E registers and FDIV_M
5 years ago
tevador
d43c7db416
Updated reference result
5 years ago
tevador
682000b1a9
Unique scratchpad addresses - interpreter
...
Additional writes to L3
5 years ago
tevador
33a2fd021d
Unique scratchpad addresses
5 years ago
tevador
2c87a058ec
Support for multithreaded dataset initialization
5 years ago
tevador
9c383dc2ba
Added superscalar-stats
...
Fixed makefile
5 years ago
tevador
53d272c6a9
Merge branch 'feature/light-code-gen' into dev
5 years ago
tevador
8c37d4aac3
More refactoring
5 years ago
tevador
9404516dd8
Refactoring
5 years ago
tevador
d49302561f
Refactoring + comments
5 years ago
tevador
24a22c6b54
Code generator refactoring
5 years ago
tevador
37ff37cd11
msvc solution
5 years ago
tevador
2e68c89740
Separate executeSuperscalar function
...
Tweaked superscalar hash constants
5 years ago
tevador
2132e5fef5
SuperscalarHash interpreter
...
Linux assembly code
5 years ago
tevador
b4c02051fa
Reworked SuperscalarHash instruction set
...
ASM and C code generator for SuperscalarHash
Support for Superscalar hash in the light mode
5 years ago
tevador
6e3136b37f
Fixed cache alignment
...
Performance tuning
5 years ago
tevador
77dbe14658
SuperscalarHash JIT compiler
...
(unfinished)
5 years ago
tevador
690707ef49
Reworked addition instructions
...
Some bug fixes
5 years ago
tevador
2aaec84931
Bug fixes, trace output
5 years ago
tevador
428b845a3d
Fixed an infinite loop bug
5 years ago
tevador
23a357db37
Removed optimizable instruction sequences
5 years ago
tevador
2b9209346e
Operand allocation
5 years ago
tevador
acef5ea0d7
Port mapping
5 years ago
tevador
2fd0a125b5
Front-end simulation
5 years ago
tevador
1c9ad90a96
Removed unused AES key expansion code
5 years ago
tevador
ad7b473388
Updated readme
5 years ago
tevador
59bbb572c2
WIP
5 years ago
tevador
2bb42637fd
Epoch increased to 2048 blocks
5 years ago
tevador
107270d93d
Reduced Dataset size to 2 GiB with 8 memory accesses per block
...
Disabled Dataset growth
5 years ago
tevador
233af9f14f
Minor fixes for non-x86 platforms
5 years ago
tevador
4c1ae951de
Merge branch 'feature/branches' into dev
...
Conflicts:
src/JitCompilerX86.cpp
src/JitCompilerX86.hpp
src/main.cpp
5 years ago
tevador
28ed776fbe
Light JIT compiler - Linux
5 years ago
tevador
73a11f5c01
CompiledLightVirtualMachine
5 years ago
tevador
00368cae02
Fixed stats compilation
5 years ago
tevador
007f8599b9
Implemented branches in the interpreter
...
Fixed x86 immediate encoding
5 years ago
tevador
1617d8e34e
Fixed squareHash reference
5 years ago
tevador
1945aae9f8
align -> balign
5 years ago
tevador
174754cb2b
Added branches - ASM and JIT only
5 years ago
tevador
6b344b81fd
initBlock asm version (disabled)
5 years ago
tevador
91063aac91
Reference result
5 years ago
tevador
344f365c42
Updated constants according to the specs
5 years ago
tevador
edde7672e0
initBlock: cycle columns, asm implementation
5 years ago
tevador
a1dc094c19
added epoch lag configuration
5 years ago
tevador
958d2bdc15
Fixed non-portable deserialization
5 years ago
tevador
2edf05cedc
Implemented Dataset size increase per epoch
5 years ago
tevador
e65d9da66c
Configurable parameters separated into configuration.h
5 years ago
tevador
096a7c0d7b
Implemented virtual memory free
...
Removed legacy AES code
5 years ago
tevador
6e8c83fdb6
Fixed softAes compilation on PowerPC
5 years ago
tevador
7c012b4fee
Fixed non-portable nonce serialization
...
updated program.inc
5 years ago
tevador
d9bc6cfeda
Updated JIT compiler and assembly generator for new int -> float conversion
5 years ago
tevador
790b382eda
Reworked conversion int -> float for register group E
5 years ago
tevador
f3b114af88
Replaced division instructions with IMUL_RCP
5 years ago
tevador
9d5f621d5c
Removed divideByConstantCodegen
5 years ago
tevador
d9fcb34138
Fixed big endian load/store
5 years ago
tevador
88cf9d0728
Fixed 32-bit Windows build
5 years ago
tevador
219efce06c
New command line options
5 years ago
tevador
f930d5d4dc
Fixed a bug in FSWAP_R
5 years ago
tevador
c5309fae9e
Fixed portable intrinsics compilation
5 years ago
tevador
bf34d27ecd
Portable SSE2 intrinsics
5 years ago
tevador
954365634e
Fixed alignment of VirtualMachine
5 years ago
tevador
dce8c74fa8
Fixed software AES in getResult
5 years ago
tevador
9a23bdb40d
Fixed linux version of SquareHash
5 years ago
tevador
bfd557dac5
Added reference result
...
Fixed undefined initial rounding mode
5 years ago
tevador
923420f0a3
Fixed mining and verification mode not giving the same results
...
Trace support in Assembly generator
5 years ago
tevador
a145caa185
Fixed JIT compiler not producing the same code as genAsm and genNative
5 years ago
tevador
f0d52fcf4d
Fixed dependent constants
5 years ago
tevador
ff0c5a58b3
More compact bytecode
5 years ago
tevador
447e8a1d4f
Simplified division in interpreted mode
...
Fixed incorrect condition code in JitCompilerX86
Refactoring
5 years ago
tevador
1df975e583
Restored software AES support
5 years ago
tevador
f76e8c2e20
Reworked "FNEG" instruction to make ASIC optimizations more difficult
5 years ago
tevador
376c868ca0
Fixed wrong REX prefix in FDIV_M code
5 years ago
tevador
5a89c9b28e
Use allocExecutableMemory
5 years ago
tevador
0b1761a846
Refactoring: mining/verification mode
5 years ago
tevador
69764966c0
Position independent loads fixed #21
5 years ago
tevador
b8ce504be6
Added comments to hashAes1Rx4 and fillAes1Rx4
...
Fixed gcc compilation
Added performance numbers
5 years ago
tevador
2798d78717
Render imm32 as signed in RandomX code
5 years ago
tevador
32d827d0a6
Interpreter with bytecode
...
Fixed some undefined behavior with signed types
Fixed different results on big endian systems
Removed unused code files
Restored FNEG_R instructions
Updated documentation
5 years ago
tevador
a586751f6b
Removed FPNEG instruction
...
Optimized instruction frequencies
Increased the range for A registers from [1,65536) to [1, 4294967296)
5 years ago
tevador
ac4462ad42
Renamed floating point instructions
...
Fixed negative source operand for FMUL_M and FDIV_M
5 years ago
tevador
b417fd08ea
16 -> 8 chained programs
...
constant address loads are always from L3
5 years ago
tevador
1ee94bef2a
Added ISWAP instruction
...
Scratchpad -> 2 MiB
New scratchpad initialization
New dataset initialization
5 years ago
tevador
20eb549725
Merged load/store of integer and FP registers
5 years ago
tevador
8f2abd6c05
NOP instruction
...
register load/store from L3
5 years ago
tevador
005c67f64c
Added explicit STORE instructions
...
JIT compiler
5 years ago
tevador
d2cb086221
ASM code generator for "small" programs that fit into the uOP cache
5 years ago
tevador
bd0dba88a8
4 scratchpad segments
5 years ago
tevador
16db607025
Scratchpad size increased to 1 MiB
...
New AES-based scratchpad hashing function
5 years ago
tevador
93c324709b
Related to previous changes
5 years ago
tevador
89bc68d093
Memory-bound dataset initialization
5 years ago
tevador
4fb168e249
Large page support for cache
...
Bug fixes
5 years ago
tevador
8b1102ee05
Interpreter + async mode
5 years ago
tevador
a7ffe8c19a
Mix dataset cacheline with registers r0-r7
5 years ago
tevador
48d85643de
Dataset intialization algorithm (AES)
5 years ago
tevador
67e741ff22
Reduced x86 code size by 512 bytes (and ecx -> and eax)
5 years ago
tevador
1426fcbab5
Print average program code size
...
Fixed assembly for MUL_64 and IMUL_32
Division weight 4 -> 8
5 years ago
tevador
2756bcdcfe
Added magic division to JIT compiler
...
New B operand selection rules
5 years ago
tevador
451dfc5730
Optimized division by constants
5 years ago
tevador
c02ee4291d
FPROUND - variable flag offset
5 years ago
tevador
e487092f07
Simplified CALL and RET
5 years ago
tevador
557241cd95
JUMP instruction
5 years ago
tevador
d1a808643d
Random accesses - JIT compiler
5 years ago
tevador
b71e0eec65
Optimizations to reduce code size under 32K
5 years ago
tevador
b6d654291f
90 address transformations
5 years ago
tevador
2f6a599ff6
Inlined calls for memory read
5 years ago
tevador
6519fed4d1
Combined prefetch + read into a single step
5 years ago
tevador
4189e4ebc6
Original number of VM instructions
5 years ago
tevador
619bee5418
Random dataset accesses - asm only
...
Initial support for large pages
5 years ago
tevador
3caecc7646
Vector FPU instructions
...
JitCompilerX86 - static code written in asm
Updated ALU/FPU tests
Updated instruction weights
5 years ago
tevador
a09bee8d60
js -> jz to enable macro-op fusion on Intel CPUs (~1% speed-up)
5 years ago
tevador
76b6b05cf2
Unconditional RET
5 years ago
tevador
39c569ae44
Fixed a potential crash in JitCompilerX86
5 years ago
tevador
5bc26348f1
Updated readme with performance data
...
Added --help option
6 years ago
tevador
03913d0e81
Run a single thread synchronously
6 years ago
tevador
c05947db09
Bug fixes
6 years ago
tevador
ca59925495
JitCompilerX86: use mmap to allocate an executable buffer
...
compile as c++11
6 years ago
tevador
740c40b218
8 branch conditions for CALL/RET
6 years ago
tevador
55afe9646f
Debuggable assembly generator
6 years ago
tevador
fce6e75689
Fixed copyright notice
6 years ago
tevador
ffa67295c4
Instruction statistics
6 years ago
tevador
1db7dd6e8b
Renamed immediate constants
6 years ago
tevador
b9d2d853aa
Support for multiple threads
6 years ago
tevador
cb12feaf91
t1ha2 hash for scratchpad digest
6 years ago
tevador
ed0bc906d6
JIT compiler for x86
6 years ago
tevador
ddc29cb4d3
Optimized x86 initialization
6 years ago
tevador
4f276541d2
Modified x86 register allocation
6 years ago
tevador
6332831ec1
Implemented cache shift
...
Fixed assembly code generator
Fixed an error in the interpreter
Updated specification: sign-extended immediates
6 years ago
tevador
d6ca408ce2
Merge branch 'master' of git@github.com:tevador/RandomX.git
6 years ago
tevador
cb0721056a
Assembly code generator for Windows 64-bit
6 years ago
Edward Vielmetti
8ef8224270
update ifdef for _rotr on aarch64
...
Enables compilation on aarch64 (Packet c1.large.arm)
6 years ago
tevador
c9102ee88c
RandomX portable interpreter
6 years ago