mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-07-25 20:10:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make numerous improvements

Browse source 
- Python static hello world now 1.8mb
- Python static fully loaded now 10mb
- Python HTTPS client now uses MbedTLS
- Python REPL now completes import stmts
- Increase stack size for Python for now
- Begin synthesizing posixpath and ntpath
- Restore Python \N{UNICODE NAME} support
- Restore Python NFKD symbol normalization
- Add optimized code path for Intel SHA-NI
- Get more Python unit tests passing faster
- Get Python help() pagination working on NT
- Python hashlib now supports MbedTLS PBKDF2
- Make memcpy/memmove/memcmp/bcmp/etc. faster
- Add Mersenne Twister and Vigna to LIBC_RAND
- Provide privileged __printf() for error code
- Fix zipos opendir() so that it reports ENOTDIR
- Add basic chmod() implementation for Windows NT
- Add Cosmo's best functions to Python cosmo module
- Pin function trace indent depth to that of caller
- Show memory diagram on invalid access in MODE=dbg
- Differentiate stack overflow on crash in MODE=dbg
- Add stb_truetype and tools for analyzing font files
- Upgrade to UNICODE 13 and reduce its binary footprint
- COMPILE.COM now logs resource usage of build commands
- Start implementing basic poll() support on bare metal
- Set getauxval(AT_EXECFN) to GetModuleFileName() on NT
- Add descriptions to strerror() in non-TINY build modes
- Add COUNTBRANCH() macro to help with micro-optimizations
- Make error / backtrace / asan / memory code more unbreakable
- Add fast perfect C implementation of μ-Law and a-Law audio codecs
- Make strtol() functions consistent with other libc implementations
- Improve Linenoise implementation (see also github.com/jart/bestline)
- COMPILE.COM now suppresses stdout/stderr of successful build commands
This commit is contained in:
Justine Tunney 2021-09-27 22:58:51 -07:00
parent fa7b4f5bd1
commit 39bf41f4eb
806 changed files with 77494 additions and 63859 deletions
Download patch file Download diff file Expand all files Collapse all files

79
libc/nexgen32e/sha256.S
View file

@ -50,7 +50,7 @@
#include "libc/macros.internal.h"
.ident "\n\
AVX2 SHA-256 (BSD-2 License)\n\
AVX2 SHA2 (BSD-2 License)\n\
Copyright 2013 Intel Corporation\n"
.include "libc/disclaimer.inc"
@ -598,19 +598,19 @@ sha256_transform_rorx:
.align 16
.Loop1:
vpaddd K256+0*32(SRND), X0, XFER
vpaddd kSha256x2+0*32(SRND), X0, XFER
vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 0*32
vpaddd K256+1*32(SRND), X0, XFER
vpaddd kSha256x2+1*32(SRND), X0, XFER
vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 1*32
vpaddd K256+2*32(SRND), X0, XFER
vpaddd kSha256x2+2*32(SRND), X0, XFER
vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 2*32
vpaddd K256+3*32(SRND), X0, XFER
vpaddd kSha256x2+3*32(SRND), X0, XFER
vmovdqa XFER, 3*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 3*32
@ -620,11 +620,11 @@ sha256_transform_rorx:
.Loop2:
## Do last 16 rounds with no scheduling
vpaddd K256+0*32(SRND), X0, XFER
vpaddd kSha256x2+0*32(SRND), X0, XFER
vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
DO_4ROUNDS _XFER + 0*32
vpaddd K256+1*32(SRND), X1, XFER
vpaddd kSha256x2+1*32(SRND), X1, XFER
vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
DO_4ROUNDS _XFER + 1*32
add $2*32, SRND
@ -712,7 +712,6 @@ sha256_transform_rorx:
.Ldone_hash:
mov _RSP(%rsp), %rsp
popq %r15
popq %r14
popq %r13
@ -722,52 +721,38 @@ sha256_transform_rorx:
ret
.endfn sha256_transform_rorx,globl
.section .rodata.cst512.K256, "aM", @progbits, 512
.align 64
K256:
.long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
.long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
.long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
.long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
.long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
.long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
.long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
.long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
.long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
.long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
.long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
.long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
.long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
.long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
.long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
.long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
.long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
.long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
.long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
.long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
.long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
.long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
.long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
.long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
.long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
.long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
.long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
.long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
.long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
.long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
.long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
.long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
.rodata.cst32
PSHUFFLE_BYTE_FLIP_MASK:
.octa 0x0c0d0e0f08090a0b0405060700010203,0x0c0d0e0f08090a0b0405060700010203
.octa 0x0c0d0e0f08090a0b0405060700010203
.octa 0x0c0d0e0f08090a0b0405060700010203
# shuffle xBxA -> 00BA
.rodata.cst32
_SHUF_00BA:
.octa 0xFFFFFFFFFFFFFFFF0b0a090803020100,0xFFFFFFFFFFFFFFFF0b0a090803020100
.octa 0xFFFFFFFFFFFFFFFF0b0a090803020100
.octa 0xFFFFFFFFFFFFFFFF0b0a090803020100
# shuffle xDxC -> DC00
.rodata.cst32
_SHUF_DC00:
.octa 0x0b0a090803020100FFFFFFFFFFFFFFFF,0x0b0a090803020100FFFFFFFFFFFFFFFF
.octa 0x0b0a090803020100FFFFFFFFFFFFFFFF
.octa 0x0b0a090803020100FFFFFFFFFFFFFFFF
.bss
.align 64
kSha256x2:
.zero 512
.endobj kSha256x2,globl
.previous
.init.start 201,_init_kSha256x2
push $64
pop %rcx
ezlea kSha256,dx
ezlea kSha256x2,ax
0: movaps -16(%rdx,%rcx,4),%xmm0
movaps %xmm0,-16(%rax,%rcx,8)
movaps %xmm0,-32(%rax,%rcx,8)
sub $4,%ecx
jnz 0b
.init.end 201,_init_kSha256x2