sleeping_kangaroo12 0.0.1 → 0.0.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/LICENSE.md +27 -0
- data/README.md +48 -53
- data/ext/Rakefile +12 -37
- data/ext/binding/sleeping_kangaroo12.c +1 -16
- data/ext/{xkcp → k12}/Makefile +0 -0
- data/ext/k12/Makefile.build +118 -0
- data/ext/k12/README.markdown +86 -0
- data/ext/k12/lib/ARMv8Asha3/KeccakP-1600-ARMv8Asha3.S +623 -0
- data/ext/k12/lib/ARMv8Asha3/KeccakP-1600-SnP.h +65 -0
- data/ext/k12/lib/ARMv8Asha3/KeccakP-1600-opt64.c +227 -0
- data/ext/{xkcp/lib/low/KeccakP-1600/compact → k12/lib/Inplace32BI}/KeccakP-1600-SnP.h +4 -9
- data/ext/{xkcp/lib/low/KeccakP-1600/plain-32bits-inplace → k12/lib/Inplace32BI}/KeccakP-1600-inplace32BI.c +65 -160
- data/ext/k12/lib/KangarooTwelve.c +332 -0
- data/ext/{xkcp/lib/high/KangarooTwelve → k12/lib}/KangarooTwelve.h +53 -16
- data/ext/{xkcp/lib/low/KeccakP-1600/AVX2 → k12/lib/Optimized64}/KeccakP-1600-AVX2.s +122 -558
- data/ext/k12/lib/Optimized64/KeccakP-1600-AVX512-plainC.c +241 -0
- data/ext/k12/lib/Optimized64/KeccakP-1600-AVX512.s +551 -0
- data/ext/k12/lib/Optimized64/KeccakP-1600-SnP.h +74 -0
- data/ext/{xkcp/lib/low/KeccakP-1600/common/KeccakP-1600-64.macros → k12/lib/Optimized64/KeccakP-1600-opt64.c} +447 -169
- data/ext/k12/lib/Optimized64/KeccakP-1600-runtimeDispatch.c +406 -0
- data/ext/k12/lib/Optimized64/KeccakP-1600-timesN-AVX2.c +419 -0
- data/ext/k12/lib/Optimized64/KeccakP-1600-timesN-AVX512.c +458 -0
- data/ext/k12/lib/Optimized64/KeccakP-1600-timesN-SSSE3.c +438 -0
- data/ext/{xkcp/lib/low/KeccakP-1600/plain-64bits → k12/lib/Plain64}/KeccakP-1600-SnP.h +14 -20
- data/ext/{xkcp/lib/low/KeccakP-1600/ref-64bits/KeccakP-1600-reference.h → k12/lib/Plain64/KeccakP-1600-plain64.c} +9 -8
- data/ext/{xkcp/lib/common → k12/lib}/align.h +3 -2
- data/ext/{xkcp/lib/common → k12/lib}/brg_endian.h +0 -0
- data/ext/{xkcp → k12}/support/Build/ExpandProducts.xsl +0 -0
- data/ext/{xkcp → k12}/support/Build/ToGlobalMakefile.xsl +0 -0
- data/ext/{xkcp → k12}/support/Build/ToOneTarget.xsl +0 -0
- data/ext/{xkcp → k12}/support/Build/ToTargetConfigFile.xsl +0 -0
- data/ext/{xkcp → k12}/support/Build/ToTargetMakefile.xsl +10 -16
- data/ext/{xkcp → k12}/support/Build/ToVCXProj.xsl +0 -0
- data/lib/sleeping_kangaroo12/binding.rb +2 -1
- data/lib/sleeping_kangaroo12/build/loader.rb +1 -0
- data/lib/sleeping_kangaroo12/build/platform.rb +1 -0
- data/lib/sleeping_kangaroo12/digest.rb +38 -4
- data/lib/sleeping_kangaroo12/version.rb +1 -1
- metadata +48 -288
- data/ext/config/xkcp.build +0 -17
- data/ext/xkcp/LICENSE +0 -1
- data/ext/xkcp/Makefile.build +0 -200
- data/ext/xkcp/README.markdown +0 -296
- data/ext/xkcp/lib/HighLevel.build +0 -143
- data/ext/xkcp/lib/LowLevel.build +0 -757
- data/ext/xkcp/lib/high/KangarooTwelve/KangarooTwelve.c +0 -301
- data/ext/xkcp/lib/high/Keccak/FIPS202/KeccakHash.c +0 -81
- data/ext/xkcp/lib/high/Keccak/FIPS202/KeccakHash.h +0 -125
- data/ext/xkcp/lib/high/Keccak/FIPS202/SimpleFIPS202.c +0 -48
- data/ext/xkcp/lib/high/Keccak/FIPS202/SimpleFIPS202.h +0 -79
- data/ext/xkcp/lib/high/Keccak/KeccakDuplex.c +0 -81
- data/ext/xkcp/lib/high/Keccak/KeccakDuplex.h +0 -73
- data/ext/xkcp/lib/high/Keccak/KeccakDuplex.inc +0 -195
- data/ext/xkcp/lib/high/Keccak/KeccakSponge.c +0 -111
- data/ext/xkcp/lib/high/Keccak/KeccakSponge.h +0 -76
- data/ext/xkcp/lib/high/Keccak/KeccakSponge.inc +0 -314
- data/ext/xkcp/lib/high/Keccak/PRG/KeccakPRG.c +0 -61
- data/ext/xkcp/lib/high/Keccak/PRG/KeccakPRG.h +0 -67
- data/ext/xkcp/lib/high/Keccak/PRG/KeccakPRG.inc +0 -128
- data/ext/xkcp/lib/high/Keccak/SP800-185/SP800-185.c +0 -93
- data/ext/xkcp/lib/high/Keccak/SP800-185/SP800-185.h +0 -599
- data/ext/xkcp/lib/high/Keccak/SP800-185/SP800-185.inc +0 -573
- data/ext/xkcp/lib/high/Ketje/Ketjev2.c +0 -87
- data/ext/xkcp/lib/high/Ketje/Ketjev2.h +0 -88
- data/ext/xkcp/lib/high/Ketje/Ketjev2.inc +0 -274
- data/ext/xkcp/lib/high/Keyak/Keyakv2.c +0 -132
- data/ext/xkcp/lib/high/Keyak/Keyakv2.h +0 -217
- data/ext/xkcp/lib/high/Keyak/Keyakv2.inc +0 -81
- data/ext/xkcp/lib/high/Keyak/Motorist.inc +0 -953
- data/ext/xkcp/lib/high/Kravatte/Kravatte.c +0 -533
- data/ext/xkcp/lib/high/Kravatte/Kravatte.h +0 -115
- data/ext/xkcp/lib/high/Kravatte/KravatteModes.c +0 -557
- data/ext/xkcp/lib/high/Kravatte/KravatteModes.h +0 -247
- data/ext/xkcp/lib/high/Xoodyak/Cyclist.h +0 -66
- data/ext/xkcp/lib/high/Xoodyak/Cyclist.inc +0 -336
- data/ext/xkcp/lib/high/Xoodyak/Xoodyak-parameters.h +0 -26
- data/ext/xkcp/lib/high/Xoodyak/Xoodyak.c +0 -55
- data/ext/xkcp/lib/high/Xoodyak/Xoodyak.h +0 -35
- data/ext/xkcp/lib/high/Xoofff/Xoofff.c +0 -634
- data/ext/xkcp/lib/high/Xoofff/Xoofff.h +0 -147
- data/ext/xkcp/lib/high/Xoofff/XoofffModes.c +0 -483
- data/ext/xkcp/lib/high/Xoofff/XoofffModes.h +0 -241
- data/ext/xkcp/lib/high/common/Phases.h +0 -25
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-SnP.h +0 -41
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-inplace-32bi-armv6m-le-armcc.s +0 -1666
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-inplace-32bi-armv6m-le-gcc.s +0 -1655
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-inplace-32bi-armv7a-le-armcc.s +0 -1268
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-inplace-32bi-armv7a-le-gcc.s +0 -1264
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-inplace-32bi-armv7m-le-armcc.s +0 -1178
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-inplace-32bi-armv7m-le-gcc.s +0 -1175
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-u1-32bi-armv6m-le-armcc.s +0 -1338
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-u1-32bi-armv6m-le-gcc.s +0 -1336
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-u2-32bi-armv6m-le-armcc.s +0 -1343
- data/ext/xkcp/lib/low/KeccakP-1600/ARM/KeccakP-1600-u2-32bi-armv6m-le-gcc.s +0 -1339
- data/ext/xkcp/lib/low/KeccakP-1600/ARMv7A-NEON/KeccakP-1600-SnP.h +0 -42
- data/ext/xkcp/lib/low/KeccakP-1600/ARMv7A-NEON/KeccakP-1600-armv7a-le-neon-armcc.s +0 -823
- data/ext/xkcp/lib/low/KeccakP-1600/ARMv7A-NEON/KeccakP-1600-armv7a-le-neon-gcc.s +0 -831
- data/ext/xkcp/lib/low/KeccakP-1600/ARMv8A/KeccakP-1600-SnP.h +0 -31
- data/ext/xkcp/lib/low/KeccakP-1600/ARMv8A/KeccakP-1600-armv8a-neon.s +0 -540
- data/ext/xkcp/lib/low/KeccakP-1600/AVR8/KeccakP-1600-SnP.h +0 -42
- data/ext/xkcp/lib/low/KeccakP-1600/AVR8/KeccakP-1600-avr8-compact.s +0 -733
- data/ext/xkcp/lib/low/KeccakP-1600/AVR8/KeccakP-1600-avr8-fast.s +0 -1121
- data/ext/xkcp/lib/low/KeccakP-1600/AVX2/KeccakP-1600-SnP.h +0 -52
- data/ext/xkcp/lib/low/KeccakP-1600/AVX512/C/KeccakP-1600-AVX512.c +0 -623
- data/ext/xkcp/lib/low/KeccakP-1600/AVX512/C/KeccakP-1600-SnP.h +0 -47
- data/ext/xkcp/lib/low/KeccakP-1600/AVX512/C/u12/KeccakP-1600-AVX512-config.h +0 -6
- data/ext/xkcp/lib/low/KeccakP-1600/AVX512/C/u6/KeccakP-1600-AVX512-config.h +0 -6
- data/ext/xkcp/lib/low/KeccakP-1600/AVX512/C/ua/KeccakP-1600-AVX512-config.h +0 -6
- data/ext/xkcp/lib/low/KeccakP-1600/AVX512/KeccakP-1600-AVX512.s +0 -1031
- data/ext/xkcp/lib/low/KeccakP-1600/AVX512/KeccakP-1600-SnP.h +0 -53
- data/ext/xkcp/lib/low/KeccakP-1600/XOP/KeccakP-1600-SnP.h +0 -44
- data/ext/xkcp/lib/low/KeccakP-1600/XOP/KeccakP-1600-XOP.c +0 -476
- data/ext/xkcp/lib/low/KeccakP-1600/XOP/u6/KeccakP-1600-XOP-config.h +0 -6
- data/ext/xkcp/lib/low/KeccakP-1600/XOP/ua/KeccakP-1600-XOP-config.h +0 -6
- data/ext/xkcp/lib/low/KeccakP-1600/common/KeccakP-1600-unrolling.macros +0 -305
- data/ext/xkcp/lib/low/KeccakP-1600/compact/KeccakP-1600-compact64.c +0 -420
- data/ext/xkcp/lib/low/KeccakP-1600/plain-32bits-inplace/KeccakP-1600-SnP.h +0 -43
- data/ext/xkcp/lib/low/KeccakP-1600/plain-64bits/KeccakP-1600-opt64.c +0 -565
- data/ext/xkcp/lib/low/KeccakP-1600/plain-64bits/lcu6/KeccakP-1600-opt64-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600/plain-64bits/lcua/KeccakP-1600-opt64-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600/plain-64bits/lcua-shld/KeccakP-1600-opt64-config.h +0 -8
- data/ext/xkcp/lib/low/KeccakP-1600/plain-64bits/u6/KeccakP-1600-opt64-config.h +0 -6
- data/ext/xkcp/lib/low/KeccakP-1600/plain-64bits/ua/KeccakP-1600-opt64-config.h +0 -6
- data/ext/xkcp/lib/low/KeccakP-1600/ref-32bits/KeccakP-1600-SnP.h +0 -44
- data/ext/xkcp/lib/low/KeccakP-1600/ref-32bits/KeccakP-1600-reference.h +0 -23
- data/ext/xkcp/lib/low/KeccakP-1600/ref-32bits/KeccakP-1600-reference32BI.c +0 -625
- data/ext/xkcp/lib/low/KeccakP-1600/ref-64bits/KeccakP-1600-SnP.h +0 -44
- data/ext/xkcp/lib/low/KeccakP-1600/ref-64bits/KeccakP-1600-reference.c +0 -440
- data/ext/xkcp/lib/low/KeccakP-1600/x86-64/KeccakP-1600-SnP.h +0 -42
- data/ext/xkcp/lib/low/KeccakP-1600/x86-64/KeccakP-1600-x86-64-gas.s +0 -1196
- data/ext/xkcp/lib/low/KeccakP-1600/x86-64/KeccakP-1600-x86-64-gas_Apple.s +0 -1124
- data/ext/xkcp/lib/low/KeccakP-1600/x86-64/KeccakP-1600-x86-64-shld-gas.s +0 -1196
- data/ext/xkcp/lib/low/KeccakP-1600-times2/ARMv7A-NEON/KeccakP-1600-inplace-pl2-armv7a-neon-le-armcc.s +0 -1392
- data/ext/xkcp/lib/low/KeccakP-1600-times2/ARMv7A-NEON/KeccakP-1600-inplace-pl2-armv7a-neon-le-gcc.s +0 -1394
- data/ext/xkcp/lib/low/KeccakP-1600-times2/ARMv7A-NEON/KeccakP-1600-times2-SnP.h +0 -42
- data/ext/xkcp/lib/low/KeccakP-1600-times2/AVX512/AVX512u12/SIMD512-2-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times2/AVX512/AVX512u4/SIMD512-2-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times2/AVX512/AVX512ufull/SIMD512-2-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times2/AVX512/KeccakP-1600-times2-SIMD512.c +0 -850
- data/ext/xkcp/lib/low/KeccakP-1600-times2/AVX512/KeccakP-1600-times2-SnP.h +0 -51
- data/ext/xkcp/lib/low/KeccakP-1600-times2/SIMD128/KeccakP-1600-times2-SIMD128.c +0 -957
- data/ext/xkcp/lib/low/KeccakP-1600-times2/SIMD128/KeccakP-1600-times2-SnP.h +0 -49
- data/ext/xkcp/lib/low/KeccakP-1600-times2/SIMD128/SSSE3-u2/SIMD128-config.h +0 -8
- data/ext/xkcp/lib/low/KeccakP-1600-times2/SIMD128/SSSE3-ua/SIMD128-config.h +0 -8
- data/ext/xkcp/lib/low/KeccakP-1600-times2/SIMD128/XOP-u2/SIMD128-config.h +0 -9
- data/ext/xkcp/lib/low/KeccakP-1600-times2/SIMD128/XOP-ua/SIMD128-config.h +0 -9
- data/ext/xkcp/lib/low/KeccakP-1600-times2/fallback-on1/KeccakP-1600-times2-SnP.h +0 -45
- data/ext/xkcp/lib/low/KeccakP-1600-times2/fallback-on1/KeccakP-1600-times2-on1.c +0 -37
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX2/KeccakP-1600-times4-SIMD256.c +0 -1321
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX2/KeccakP-1600-times4-SnP.h +0 -55
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX2/u12/SIMD256-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX2/u6/SIMD256-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX2/ua/SIMD256-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX512/AVX512u12/SIMD512-4-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX512/AVX512u4/SIMD512-4-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX512/AVX512ufull/SIMD512-4-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX512/KeccakP-1600-times4-SIMD512.c +0 -881
- data/ext/xkcp/lib/low/KeccakP-1600-times4/AVX512/KeccakP-1600-times4-SnP.h +0 -51
- data/ext/xkcp/lib/low/KeccakP-1600-times4/fallback-on1/KeccakP-1600-times4-SnP.h +0 -45
- data/ext/xkcp/lib/low/KeccakP-1600-times4/fallback-on1/KeccakP-1600-times4-on1.c +0 -37
- data/ext/xkcp/lib/low/KeccakP-1600-times4/fallback-on2/KeccakP-1600-times4-SnP.h +0 -45
- data/ext/xkcp/lib/low/KeccakP-1600-times4/fallback-on2/KeccakP-1600-times4-on2.c +0 -38
- data/ext/xkcp/lib/low/KeccakP-1600-times8/AVX512/KeccakP-1600-times8-SIMD512.c +0 -1615
- data/ext/xkcp/lib/low/KeccakP-1600-times8/AVX512/KeccakP-1600-times8-SnP.h +0 -57
- data/ext/xkcp/lib/low/KeccakP-1600-times8/AVX512/u12/SIMD512-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times8/AVX512/u4/SIMD512-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times8/AVX512/ua/SIMD512-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-1600-times8/fallback-on1/KeccakP-1600-times8-SnP.h +0 -45
- data/ext/xkcp/lib/low/KeccakP-1600-times8/fallback-on1/KeccakP-1600-times8-on1.c +0 -37
- data/ext/xkcp/lib/low/KeccakP-1600-times8/fallback-on2/KeccakP-1600-times8-SnP.h +0 -45
- data/ext/xkcp/lib/low/KeccakP-1600-times8/fallback-on2/KeccakP-1600-times8-on2.c +0 -38
- data/ext/xkcp/lib/low/KeccakP-1600-times8/fallback-on4/KeccakP-1600-times8-SnP.h +0 -45
- data/ext/xkcp/lib/low/KeccakP-1600-times8/fallback-on4/KeccakP-1600-times8-on4.c +0 -38
- data/ext/xkcp/lib/low/KeccakP-200/ARM/KeccakP-200-SnP.h +0 -41
- data/ext/xkcp/lib/low/KeccakP-200/ARM/KeccakP-200-armv6m-le-armcc.s +0 -442
- data/ext/xkcp/lib/low/KeccakP-200/ARM/KeccakP-200-armv6m-le-gcc.s +0 -446
- data/ext/xkcp/lib/low/KeccakP-200/ARM/KeccakP-200-armv7m-le-armcc.s +0 -419
- data/ext/xkcp/lib/low/KeccakP-200/ARM/KeccakP-200-armv7m-le-gcc.s +0 -427
- data/ext/xkcp/lib/low/KeccakP-200/AVR8/KeccakP-200-SnP.h +0 -41
- data/ext/xkcp/lib/low/KeccakP-200/AVR8/KeccakP-200-avr8-fast.s +0 -647
- data/ext/xkcp/lib/low/KeccakP-200/compact/KeccakP-200-SnP.h +0 -39
- data/ext/xkcp/lib/low/KeccakP-200/compact/KeccakP-200-compact.c +0 -190
- data/ext/xkcp/lib/low/KeccakP-200/ref/KeccakP-200-SnP.h +0 -43
- data/ext/xkcp/lib/low/KeccakP-200/ref/KeccakP-200-reference.c +0 -412
- data/ext/xkcp/lib/low/KeccakP-200/ref/KeccakP-200-reference.h +0 -23
- data/ext/xkcp/lib/low/KeccakP-400/ARM/KeccakP-400-SnP.h +0 -41
- data/ext/xkcp/lib/low/KeccakP-400/ARM/KeccakP-400-armv6m-le-armcc.s +0 -454
- data/ext/xkcp/lib/low/KeccakP-400/ARM/KeccakP-400-armv6m-le-gcc.s +0 -458
- data/ext/xkcp/lib/low/KeccakP-400/ARM/KeccakP-400-armv7m-le-armcc.s +0 -455
- data/ext/xkcp/lib/low/KeccakP-400/ARM/KeccakP-400-armv7m-le-gcc.s +0 -458
- data/ext/xkcp/lib/low/KeccakP-400/AVR8/KeccakP-400-SnP.h +0 -41
- data/ext/xkcp/lib/low/KeccakP-400/AVR8/KeccakP-400-avr8-fast.s +0 -728
- data/ext/xkcp/lib/low/KeccakP-400/ref/KeccakP-400-SnP.h +0 -43
- data/ext/xkcp/lib/low/KeccakP-400/ref/KeccakP-400-reference.c +0 -414
- data/ext/xkcp/lib/low/KeccakP-400/ref/KeccakP-400-reference.h +0 -23
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-SnP.h +0 -42
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-u1-armv6m-le-armcc.s +0 -527
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-u1-armv6m-le-gcc.s +0 -533
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-u2-armv6m-le-armcc.s +0 -528
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-u2-armv6m-le-gcc.s +0 -534
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-u2-armv7a-le-armcc.s +0 -521
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-u2-armv7a-le-gcc.s +0 -527
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-u2-armv7m-le-armcc.s +0 -517
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-u2-armv7m-le-gcc.s +0 -523
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-uf-armv7m-le-armcc.s +0 -550
- data/ext/xkcp/lib/low/KeccakP-800/ARM/KeccakP-800-uf-armv7m-le-gcc.s +0 -556
- data/ext/xkcp/lib/low/KeccakP-800/ARMv8A/KeccakP-800-SnP.h +0 -32
- data/ext/xkcp/lib/low/KeccakP-800/ARMv8A/KeccakP-800-armv8a-neon.s +0 -432
- data/ext/xkcp/lib/low/KeccakP-800/AVR8/KeccakP-800-SnP.h +0 -42
- data/ext/xkcp/lib/low/KeccakP-800/AVR8/KeccakP-800-avr8-fast.s +0 -929
- data/ext/xkcp/lib/low/KeccakP-800/compact/KeccakP-800-SnP.h +0 -40
- data/ext/xkcp/lib/low/KeccakP-800/compact/KeccakP-800-compact.c +0 -244
- data/ext/xkcp/lib/low/KeccakP-800/plain/KeccakP-800-SnP.h +0 -46
- data/ext/xkcp/lib/low/KeccakP-800/plain/KeccakP-800-opt32-bis.macros +0 -184
- data/ext/xkcp/lib/low/KeccakP-800/plain/KeccakP-800-opt32.c +0 -454
- data/ext/xkcp/lib/low/KeccakP-800/plain/KeccakP-800-opt32.macros +0 -459
- data/ext/xkcp/lib/low/KeccakP-800/plain/KeccakP-800-unrolling-bis.macros +0 -83
- data/ext/xkcp/lib/low/KeccakP-800/plain/KeccakP-800-unrolling.macros +0 -88
- data/ext/xkcp/lib/low/KeccakP-800/plain/lcu2/KeccakP-800-opt32-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-800/plain/lcua/KeccakP-800-opt32-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-800/plain/u2/KeccakP-800-opt32-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-800/plain/ua/KeccakP-800-opt32-config.h +0 -7
- data/ext/xkcp/lib/low/KeccakP-800/ref/KeccakP-800-SnP.h +0 -44
- data/ext/xkcp/lib/low/KeccakP-800/ref/KeccakP-800-reference.c +0 -437
- data/ext/xkcp/lib/low/KeccakP-800/ref/KeccakP-800-reference.h +0 -23
- data/ext/xkcp/lib/low/Ketje/OptimizedAsmARM/Ket.h +0 -57
- data/ext/xkcp/lib/low/Ketje/OptimizedAsmARM/KetjeJr-armv7m-le-armcc.s +0 -475
- data/ext/xkcp/lib/low/Ketje/OptimizedAsmARM/KetjeJr-armv7m-le-gcc.s +0 -480
- data/ext/xkcp/lib/low/Ketje/OptimizedAsmARM/KetjeSr-armv7m-le-armcc.s +0 -590
- data/ext/xkcp/lib/low/Ketje/OptimizedAsmARM/KetjeSr-armv7m-le-gcc.s +0 -590
- data/ext/xkcp/lib/low/Ketje/OptimizedLE/Ket.c +0 -126
- data/ext/xkcp/lib/low/Ketje/OptimizedLE/Ket.h +0 -68
- data/ext/xkcp/lib/low/Ketje/OptimizedLE/Ket.inc +0 -174
- data/ext/xkcp/lib/low/Ketje/SnP-compliant/Ket.c +0 -80
- data/ext/xkcp/lib/low/Ketje/SnP-compliant/Ket.h +0 -68
- data/ext/xkcp/lib/low/Ketje/SnP-compliant/Ket.inc +0 -142
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodoo-SnP.h +0 -55
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodoo-u1-armv6m-le-armcc.s +0 -1086
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodoo-u1-armv6m-le-gcc.s +0 -1092
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodoo-uf-armv6-le-armcc.s +0 -721
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodoo-uf-armv6-le-gcc.s +0 -726
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodoo-uf-armv7m-le-armcc.s +0 -723
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodoo-uf-armv7m-le-gcc.s +0 -729
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodyak-u1-armv6m-le-armcc.s +0 -1164
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodyak-u1-armv6m-le-gcc.s +0 -1165
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodyak-uf-armv6-le-armcc.s +0 -562
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodyak-uf-armv6-le-gcc.s +0 -563
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodyak-uf-armv7m-le-armcc.s +0 -563
- data/ext/xkcp/lib/low/Xoodoo/ARM/Xoodyak-uf-armv7m-le-gcc.s +0 -565
- data/ext/xkcp/lib/low/Xoodoo/ARMv7A-NEON/Xoodoo-SnP.h +0 -55
- data/ext/xkcp/lib/low/Xoodoo/ARMv7A-NEON/Xoodoo-uf-armv7a-neon-le-armcc.s +0 -476
- data/ext/xkcp/lib/low/Xoodoo/ARMv7A-NEON/Xoodoo-uf-armv7a-neon-le-gcc.s +0 -485
- data/ext/xkcp/lib/low/Xoodoo/ARMv7A-NEON/Xoodyak-uf-armv7a-neon-le-armcc.s +0 -362
- data/ext/xkcp/lib/low/Xoodoo/ARMv7A-NEON/Xoodyak-uf-armv7a-neon-le-gcc.s +0 -367
- data/ext/xkcp/lib/low/Xoodoo/AVR8/Xoodoo-SnP.h +0 -43
- data/ext/xkcp/lib/low/Xoodoo/AVR8/Xoodoo-avr8-u1.s +0 -1341
- data/ext/xkcp/lib/low/Xoodoo/AVX512/Xoodoo-SIMD512.c +0 -581
- data/ext/xkcp/lib/low/Xoodoo/AVX512/Xoodoo-SnP.h +0 -58
- data/ext/xkcp/lib/low/Xoodoo/AVX512/Xoodyak-full-block-SIMD512.c +0 -332
- data/ext/xkcp/lib/low/Xoodoo/SSE2/Xoodoo-SIMD128.c +0 -329
- data/ext/xkcp/lib/low/Xoodoo/SSE2/Xoodoo-SnP.h +0 -53
- data/ext/xkcp/lib/low/Xoodoo/SSE2/Xoodyak-full-block-SIMD128.c +0 -355
- data/ext/xkcp/lib/low/Xoodoo/Xoodoo.h +0 -79
- data/ext/xkcp/lib/low/Xoodoo/plain/Xoodoo-SnP.h +0 -56
- data/ext/xkcp/lib/low/Xoodoo/plain/Xoodoo-optimized.c +0 -399
- data/ext/xkcp/lib/low/Xoodoo/plain/Xoodyak-full-blocks.c +0 -127
- data/ext/xkcp/lib/low/Xoodoo/ref/Xoodoo-SnP.h +0 -43
- data/ext/xkcp/lib/low/Xoodoo/ref/Xoodoo-reference.c +0 -253
- data/ext/xkcp/lib/low/Xoodoo-times16/AVX512/Xoodoo-times16-SIMD512.c +0 -1044
- data/ext/xkcp/lib/low/Xoodoo-times16/AVX512/Xoodoo-times16-SnP.h +0 -49
- data/ext/xkcp/lib/low/Xoodoo-times16/fallback-on1/Xoodoo-times16-SnP.h +0 -45
- data/ext/xkcp/lib/low/Xoodoo-times16/fallback-on1/Xoodoo-times16-on1.c +0 -37
- data/ext/xkcp/lib/low/Xoodoo-times4/ARMv7A-NEON/Xoodoo-times4-ARMv7A.s +0 -1587
- data/ext/xkcp/lib/low/Xoodoo-times4/ARMv7A-NEON/Xoodoo-times4-SnP.h +0 -48
- data/ext/xkcp/lib/low/Xoodoo-times4/AVX512/Xoodoo-times4-SIMD512.c +0 -1202
- data/ext/xkcp/lib/low/Xoodoo-times4/AVX512/Xoodoo-times4-SnP.h +0 -48
- data/ext/xkcp/lib/low/Xoodoo-times4/SSSE3/Xoodoo-times4-SIMD128.c +0 -484
- data/ext/xkcp/lib/low/Xoodoo-times4/SSSE3/Xoodoo-times4-SnP.h +0 -44
- data/ext/xkcp/lib/low/Xoodoo-times4/fallback-on1/Xoodoo-times4-SnP.h +0 -45
- data/ext/xkcp/lib/low/Xoodoo-times4/fallback-on1/Xoodoo-times4-on1.c +0 -37
- data/ext/xkcp/lib/low/Xoodoo-times8/AVX2/Xoodoo-times8-SIMD256.c +0 -939
- data/ext/xkcp/lib/low/Xoodoo-times8/AVX2/Xoodoo-times8-SnP.h +0 -49
- data/ext/xkcp/lib/low/Xoodoo-times8/AVX512/Xoodoo-times8-SIMD512.c +0 -1216
- data/ext/xkcp/lib/low/Xoodoo-times8/AVX512/Xoodoo-times8-SnP.h +0 -48
- data/ext/xkcp/lib/low/Xoodoo-times8/fallback-on1/Xoodoo-times8-SnP.h +0 -45
- data/ext/xkcp/lib/low/Xoodoo-times8/fallback-on1/Xoodoo-times8-on1.c +0 -37
- data/ext/xkcp/lib/low/common/PlSnP-Fallback.inc +0 -290
- data/ext/xkcp/lib/low/common/SnP-Relaned.h +0 -141
- data/ext/xkcp/support/Kernel-PMU/Kernel-pmu.md +0 -133
- data/ext/xkcp/support/Kernel-PMU/Makefile +0 -8
- data/ext/xkcp/support/Kernel-PMU/enable_arm_pmu.c +0 -129
- data/ext/xkcp/support/Kernel-PMU/load-module +0 -1
- data/ext/xkcp/util/KeccakSum/KeccakSum.c +0 -394
- data/ext/xkcp/util/KeccakSum/base64.c +0 -86
- data/ext/xkcp/util/KeccakSum/base64.h +0 -12
@@ -1,1086 +0,0 @@
|
|
1
|
-
;
|
2
|
-
; The eXtended Keccak Code Package (XKCP)
|
3
|
-
; https://github.com/XKCP/XKCP
|
4
|
-
;
|
5
|
-
; The Xoodoo permutation, designed by Joan Daemen, Seth Hoffert, Gilles Van Assche and Ronny Van Keer.
|
6
|
-
;
|
7
|
-
; Implementation by Ronny Van Keer, hereby denoted as "the implementer".
|
8
|
-
;
|
9
|
-
; For more information, feedback or questions, please refer to the Keccak Team website:
|
10
|
-
; https://keccak.team/
|
11
|
-
;
|
12
|
-
; To the extent possible under law, the implementer has waived all copyright
|
13
|
-
; and related or neighboring rights to the source code in this file.
|
14
|
-
; http://creativecommons.org/publicdomain/zero/1.0/
|
15
|
-
;
|
16
|
-
|
17
|
-
; WARNING: These functions work only on little endian CPU with ARMv6m architecture (Cortex-M0, ...).
|
18
|
-
|
19
|
-
PRESERVE8
|
20
|
-
THUMB
|
21
|
-
AREA |.text|, CODE, READONLY
|
22
|
-
|
23
|
-
; ----------------------------------------------------------------------------
|
24
|
-
;
|
25
|
-
; void Xoodoo_Initialize(void *state)
|
26
|
-
;
|
27
|
-
align 4
|
28
|
-
EXPORT Xoodoo_Initialize
|
29
|
-
Xoodoo_Initialize PROC
|
30
|
-
movs r1, #0
|
31
|
-
movs r2, #0
|
32
|
-
movs r3, #0
|
33
|
-
stmia r0!, { r1 - r3 }
|
34
|
-
stmia r0!, { r1 - r3 }
|
35
|
-
stmia r0!, { r1 - r3 }
|
36
|
-
stmia r0!, { r1 - r3 }
|
37
|
-
bx lr
|
38
|
-
align 4
|
39
|
-
ENDP
|
40
|
-
|
41
|
-
; ----------------------------------------------------------------------------
|
42
|
-
;
|
43
|
-
; void Xoodoo_AddBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
44
|
-
;
|
45
|
-
EXPORT Xoodoo_AddBytes
|
46
|
-
Xoodoo_AddBytes PROC
|
47
|
-
push {r4,lr}
|
48
|
-
adds r0, r0, r2 ; state += offset
|
49
|
-
subs r3, r3, #4 ; if length >= 4
|
50
|
-
bcc Xoodoo_AddBytes_Bytes
|
51
|
-
movs r2, r0 ; and data pointer and offset both 32-bit aligned
|
52
|
-
orrs r2, r2, r1
|
53
|
-
lsls r2, #30
|
54
|
-
bne Xoodoo_AddBytes_Bytes
|
55
|
-
Xoodoo_AddBytes_LanesLoop ; then, perform on words
|
56
|
-
ldr r2, [r0]
|
57
|
-
ldmia r1!, {r4}
|
58
|
-
eors r2, r2, r4
|
59
|
-
stmia r0!, {r2}
|
60
|
-
subs r3, r3, #4
|
61
|
-
bcs Xoodoo_AddBytes_LanesLoop
|
62
|
-
Xoodoo_AddBytes_Bytes
|
63
|
-
adds r3, r3, #4
|
64
|
-
beq Xoodoo_AddBytes_Exit
|
65
|
-
subs r3, r3, #1
|
66
|
-
Xoodoo_AddBytes_BytesLoop
|
67
|
-
ldrb r2, [r0, r3]
|
68
|
-
ldrb r4, [r1, r3]
|
69
|
-
eors r2, r2, r4
|
70
|
-
strb r2, [r0, r3]
|
71
|
-
subs r3, r3, #1
|
72
|
-
bcs Xoodoo_AddBytes_BytesLoop
|
73
|
-
Xoodoo_AddBytes_Exit
|
74
|
-
pop {r4,pc}
|
75
|
-
align 4
|
76
|
-
ENDP
|
77
|
-
|
78
|
-
; ----------------------------------------------------------------------------
|
79
|
-
;
|
80
|
-
; void Xoodoo_OverwriteBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
81
|
-
;
|
82
|
-
EXPORT Xoodoo_OverwriteBytes
|
83
|
-
Xoodoo_OverwriteBytes PROC
|
84
|
-
adds r0, r0, r2 ; state += offset
|
85
|
-
subs r3, r3, #4 ; if length >= 4
|
86
|
-
bcc Xoodoo_OverwriteBytes_Bytes
|
87
|
-
movs r2, r0 ; and data pointer and offset both 32-bit aligned
|
88
|
-
orrs r2, r2, r1
|
89
|
-
lsls r2, #30
|
90
|
-
bne Xoodoo_OverwriteBytes_Bytes
|
91
|
-
Xoodoo_OverwriteBytes_LanesLoop ; then, perform on words
|
92
|
-
ldmia r1!, {r2}
|
93
|
-
stmia r0!, {r2}
|
94
|
-
subs r3, r3, #4
|
95
|
-
bcs Xoodoo_OverwriteBytes_LanesLoop
|
96
|
-
Xoodoo_OverwriteBytes_Bytes
|
97
|
-
adds r3, r3, #4
|
98
|
-
beq Xoodoo_OverwriteBytes_Exit
|
99
|
-
subs r3, r3, #1
|
100
|
-
Xoodoo_OverwriteBytes_BytesLoop
|
101
|
-
ldrb r2, [r1, r3]
|
102
|
-
strb r2, [r0, r3]
|
103
|
-
subs r3, r3, #1
|
104
|
-
bcs Xoodoo_OverwriteBytes_BytesLoop
|
105
|
-
Xoodoo_OverwriteBytes_Exit
|
106
|
-
bx lr
|
107
|
-
align 4
|
108
|
-
ENDP
|
109
|
-
|
110
|
-
; ----------------------------------------------------------------------------
|
111
|
-
;
|
112
|
-
; void Xoodoo_OverwriteWithZeroes(void *state, unsigned int byteCount)
|
113
|
-
;
|
114
|
-
EXPORT Xoodoo_OverwriteWithZeroes
|
115
|
-
Xoodoo_OverwriteWithZeroes PROC
|
116
|
-
movs r3, #0
|
117
|
-
lsrs r2, r1, #2
|
118
|
-
beq Xoodoo_OverwriteWithZeroes_Bytes
|
119
|
-
Xoodoo_OverwriteWithZeroes_LoopLanes
|
120
|
-
stm r0!, { r3 }
|
121
|
-
subs r2, r2, #1
|
122
|
-
bne Xoodoo_OverwriteWithZeroes_LoopLanes
|
123
|
-
Xoodoo_OverwriteWithZeroes_Bytes
|
124
|
-
lsls r1, r1, #32-2
|
125
|
-
beq Xoodoo_OverwriteWithZeroes_Exit
|
126
|
-
lsrs r1, r1, #32-2
|
127
|
-
Xoodoo_OverwriteWithZeroes_LoopBytes
|
128
|
-
subs r1, r1, #1
|
129
|
-
strb r3, [r0, r1]
|
130
|
-
bne Xoodoo_OverwriteWithZeroes_LoopBytes
|
131
|
-
Xoodoo_OverwriteWithZeroes_Exit
|
132
|
-
bx lr
|
133
|
-
align 4
|
134
|
-
ENDP
|
135
|
-
|
136
|
-
; ----------------------------------------------------------------------------
|
137
|
-
;
|
138
|
-
; void Xoodoo_ExtractBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
139
|
-
;
|
140
|
-
EXPORT Xoodoo_ExtractBytes
|
141
|
-
Xoodoo_ExtractBytes PROC
|
142
|
-
adds r0, r0, r2 ; state += offset
|
143
|
-
subs r3, r3, #4 ; if length >= 4
|
144
|
-
bcc Xoodoo_ExtractBytes_Bytes
|
145
|
-
movs r2, r0 ; and data pointer and offset both 32-bit aligned
|
146
|
-
orrs r2, r2, r1
|
147
|
-
lsls r2, #30
|
148
|
-
bne Xoodoo_ExtractBytes_Bytes
|
149
|
-
Xoodoo_ExtractBytes_LanesLoop ; then, perform on words
|
150
|
-
ldmia r0!, {r2}
|
151
|
-
stmia r1!, {r2}
|
152
|
-
subs r3, r3, #4
|
153
|
-
bcs Xoodoo_ExtractBytes_LanesLoop
|
154
|
-
Xoodoo_ExtractBytes_Bytes
|
155
|
-
adds r3, r3, #4
|
156
|
-
beq Xoodoo_ExtractBytes_Exit
|
157
|
-
subs r3, r3, #1
|
158
|
-
Xoodoo_ExtractBytes_BytesLoop
|
159
|
-
ldrb r2, [r0, r3]
|
160
|
-
strb r2, [r1, r3]
|
161
|
-
subs r3, r3, #1
|
162
|
-
bcs Xoodoo_ExtractBytes_BytesLoop
|
163
|
-
Xoodoo_ExtractBytes_Exit
|
164
|
-
bx lr
|
165
|
-
align 4
|
166
|
-
ENDP
|
167
|
-
|
168
|
-
; ----------------------------------------------------------------------------
|
169
|
-
;
|
170
|
-
; void Xoodoo_ExtractAndAddBytes(void *state, const unsigned char *input, unsigned char *output, unsigned int offset, unsigned int length)
|
171
|
-
;
|
172
|
-
EXPORT Xoodoo_ExtractAndAddBytes
|
173
|
-
Xoodoo_ExtractAndAddBytes PROC
|
174
|
-
push {r4,r5}
|
175
|
-
adds r0, r0, r3 ; state += offset (offset register no longer needed, reuse for length)
|
176
|
-
ldr r3, [sp, #8] ; get length argument from stack
|
177
|
-
subs r3, r3, #4 ; if length >= 4
|
178
|
-
bcc Xoodoo_ExtractAndAddBytes_Bytes
|
179
|
-
movs r5, r0 ; and input/output/state pointer all 32-bit aligned
|
180
|
-
orrs r5, r5, r1
|
181
|
-
orrs r5, r5, r2
|
182
|
-
lsls r5, #30
|
183
|
-
bne Xoodoo_ExtractAndAddBytes_Bytes
|
184
|
-
Xoodoo_ExtractAndAddBytes_LanesLoop ; then, perform on words
|
185
|
-
ldmia r0!, {r5}
|
186
|
-
ldmia r1!, {r4}
|
187
|
-
eors r5, r5, r4
|
188
|
-
stmia r2!, {r5}
|
189
|
-
subs r3, r3, #4
|
190
|
-
bcs Xoodoo_ExtractAndAddBytes_LanesLoop
|
191
|
-
Xoodoo_ExtractAndAddBytes_Bytes
|
192
|
-
adds r3, r3, #4
|
193
|
-
beq Xoodoo_ExtractAndAddBytes_Exit
|
194
|
-
subs r3, r3, #1
|
195
|
-
Xoodoo_ExtractAndAddBytes_BytesLoop
|
196
|
-
ldrb r5, [r0, r3]
|
197
|
-
ldrb r4, [r1, r3]
|
198
|
-
eors r5, r5, r4
|
199
|
-
strb r5, [r2, r3]
|
200
|
-
subs r3, r3, #1
|
201
|
-
bcs Xoodoo_ExtractAndAddBytes_BytesLoop
|
202
|
-
Xoodoo_ExtractAndAddBytes_Exit
|
203
|
-
pop {r4,r5}
|
204
|
-
bx lr
|
205
|
-
align 4
|
206
|
-
ENDP
|
207
|
-
|
208
|
-
; ----------------------------------------------------------------------------
|
209
|
-
|
210
|
-
; offsets in RAM state
|
211
|
-
_oA00 equ 0*4
|
212
|
-
_oA01 equ 1*4
|
213
|
-
_oA02 equ 2*4
|
214
|
-
_oA03 equ 3*4
|
215
|
-
_oA10 equ 4*4
|
216
|
-
_oA11 equ 5*4
|
217
|
-
_oA12 equ 6*4
|
218
|
-
_oA13 equ 7*4
|
219
|
-
_oA20 equ 8*4
|
220
|
-
_oA21 equ 9*4
|
221
|
-
_oA22 equ 10*4
|
222
|
-
_oA23 equ 11*4
|
223
|
-
|
224
|
-
; possible locations of state lanes
|
225
|
-
locRegL equ 1
|
226
|
-
locRegH equ 2
|
227
|
-
locMem equ 3
|
228
|
-
|
229
|
-
; ----------------------------------------------------------------------------
|
230
|
-
|
231
|
-
_r0 equ 5
|
232
|
-
_r1 equ 14
|
233
|
-
_r2 equ 1
|
234
|
-
|
235
|
-
_w1 equ 11
|
236
|
-
|
237
|
-
_e0 equ 2
|
238
|
-
_e1 equ 8
|
239
|
-
|
240
|
-
; ----------------------------------------------------------------------------
|
241
|
-
|
242
|
-
MACRO
|
243
|
-
mXor3 $ro, $a0, $a1, $a2, $loc, $tt
|
244
|
-
mov $ro, $a1
|
245
|
-
eors $ro, $ro, $a2
|
246
|
-
if $loc == locRegL
|
247
|
-
eors $ro, $ro, $a0
|
248
|
-
else
|
249
|
-
if $loc == locRegH
|
250
|
-
mov $tt, $a0
|
251
|
-
else
|
252
|
-
ldr $tt, [sp, #$a0]
|
253
|
-
endif
|
254
|
-
eors $ro, $ro, $tt
|
255
|
-
endif
|
256
|
-
MEND
|
257
|
-
|
258
|
-
MACRO
|
259
|
-
mXor $ro, $ri, $tt, $loc
|
260
|
-
if $loc == locRegL
|
261
|
-
eors $ro, $ro, $ri
|
262
|
-
else
|
263
|
-
if $loc == locRegH
|
264
|
-
mov $tt, $ro
|
265
|
-
eors $tt, $tt, $ri
|
266
|
-
mov $ro, $tt
|
267
|
-
else
|
268
|
-
ldr $tt, [sp, #$ro]
|
269
|
-
eors $tt, $tt, $ri
|
270
|
-
str $tt, [sp, #$ro]
|
271
|
-
endif
|
272
|
-
endif
|
273
|
-
MEND
|
274
|
-
|
275
|
-
MACRO
|
276
|
-
mChi3 $a0,$a1,$a2,$r0,$r1,$a0s,$loc
|
277
|
-
mov $r1, $a2
|
278
|
-
mov $r0, $a1
|
279
|
-
bics $r1, $r1, $r0
|
280
|
-
eors $a0, $a0, $r1
|
281
|
-
if $loc != locRegL
|
282
|
-
if $loc == locRegH
|
283
|
-
mov $a0s, $a0
|
284
|
-
else
|
285
|
-
str $a0, [sp, #$a0s]
|
286
|
-
endif
|
287
|
-
endif
|
288
|
-
|
289
|
-
mov $r0, $a0
|
290
|
-
bics $r0, $r0, $a2
|
291
|
-
mov $r1, $a1
|
292
|
-
eors $r1, $r1, $r0
|
293
|
-
mov $a1, $r1
|
294
|
-
|
295
|
-
bics $r1, $r1, $a0
|
296
|
-
eors $a2, $a2, $r1
|
297
|
-
MEND
|
298
|
-
|
299
|
-
MACRO
|
300
|
-
mRound $offsetRC, $offsetA03
|
301
|
-
|
302
|
-
; Theta: Column Parity Mixer
|
303
|
-
mXor3 r0, $offsetA03, lr, r7, locMem, r2
|
304
|
-
mov r1, r0
|
305
|
-
movs r2, #32-(_r1-_r0)
|
306
|
-
rors r1, r1, r2
|
307
|
-
eors r1, r1, r0
|
308
|
-
movs r2, #32-_r0
|
309
|
-
rors r1, r1, r2
|
310
|
-
mXor3 r0, r3, r10, r4, locRegL, r2
|
311
|
-
mXor r3, r1, r2, locRegL
|
312
|
-
mXor r10, r1, r2, locRegH
|
313
|
-
mXor r4, r1, r2, locRegL
|
314
|
-
|
315
|
-
mov r1, r0
|
316
|
-
movs r2, #32-(_r1-_r0)
|
317
|
-
rors r1, r1, r2
|
318
|
-
eors r1, r1, r0
|
319
|
-
movs r2, #32-_r0
|
320
|
-
rors r1, r1, r2
|
321
|
-
mXor3 r0, r8, r11, r5, locRegH, r2
|
322
|
-
mXor r8, r1, r2, locRegH
|
323
|
-
mXor r11, r1, r2, locRegH
|
324
|
-
mXor r5, r1, r2, locRegL
|
325
|
-
|
326
|
-
mov r1, r0
|
327
|
-
movs r2, #32-(_r1-_r0)
|
328
|
-
rors r1, r1, r2
|
329
|
-
eors r1, r1, r0
|
330
|
-
movs r2, #32-_r0
|
331
|
-
rors r1, r1, r2
|
332
|
-
mXor3 r0, r9, r12, r6, locRegH, r2
|
333
|
-
mXor r9, r1, r2, locRegH
|
334
|
-
mXor r12, r1, r2, locRegH
|
335
|
-
mXor r6, r1, r2, locRegL
|
336
|
-
|
337
|
-
mov r1, r0
|
338
|
-
movs r2, #32-(_r1-_r0)
|
339
|
-
rors r1, r1, r2
|
340
|
-
eors r1, r1, r0
|
341
|
-
movs r2, #32-_r0
|
342
|
-
rors r1, r1, r2
|
343
|
-
mXor $offsetA03, r1, r2, locMem
|
344
|
-
mXor lr, r1, r2, locRegH
|
345
|
-
mXor r7, r1, r2, locRegL
|
346
|
-
|
347
|
-
; Rho-west: Plane shift
|
348
|
-
movs r0, #32-_w1
|
349
|
-
rors r4, r4, r0
|
350
|
-
rors r5, r5, r0
|
351
|
-
rors r6, r6, r0
|
352
|
-
rors r7, r7, r0
|
353
|
-
mov r0, lr
|
354
|
-
mov lr, r12
|
355
|
-
mov r12, r11
|
356
|
-
mov r11, r10
|
357
|
-
mov r10, r0
|
358
|
-
|
359
|
-
; Iota: round constant
|
360
|
-
ldr r0, [sp, #$offsetRC]
|
361
|
-
ldmia r0!, {r1}
|
362
|
-
str r0, [sp, #$offsetRC]
|
363
|
-
eors r3, r3, r1
|
364
|
-
|
365
|
-
; Chi: non linear step, on colums
|
366
|
-
mChi3 r3, r10, r4, r0, r1, r3, locRegL
|
367
|
-
mov r2, r8
|
368
|
-
mChi3 r2, r11, r5, r0, r1, r8, locRegH
|
369
|
-
mov r2, r9
|
370
|
-
mChi3 r2, r12, r6, r0, r1, r9, locRegH
|
371
|
-
ldr r2, [sp, #$offsetA03]
|
372
|
-
mChi3 r2, lr, r7, r0, r1, $offsetA03, locMem
|
373
|
-
|
374
|
-
; Rho-east: Plane shift
|
375
|
-
movs r0, #32-1
|
376
|
-
mov r1, r10
|
377
|
-
rors r1, r1, r0
|
378
|
-
mov r10, r1
|
379
|
-
mov r1, r11
|
380
|
-
rors r1, r1, r0
|
381
|
-
mov r11, r1
|
382
|
-
mov r1, r12
|
383
|
-
rors r1, r1, r0
|
384
|
-
mov r12, r1
|
385
|
-
mov r1, lr
|
386
|
-
rors r1, r1, r0
|
387
|
-
mov lr, r1
|
388
|
-
|
389
|
-
movs r0, #32-_e1
|
390
|
-
rors r4, r4, r0
|
391
|
-
rors r5, r5, r0
|
392
|
-
rors r6, r6, r0
|
393
|
-
rors r7, r7, r0
|
394
|
-
|
395
|
-
mov r0, r4
|
396
|
-
mov r4, r6
|
397
|
-
mov r6, r0
|
398
|
-
mov r0, r5
|
399
|
-
mov r5, r7
|
400
|
-
mov r7, r0
|
401
|
-
|
402
|
-
MEND
|
403
|
-
|
404
|
-
; ----------------------------------------------------------------------------
|
405
|
-
;
|
406
|
-
; void Xoodoo_Permute_Nrounds(void *state, unsigned int nrounds)
|
407
|
-
;
|
408
|
-
|
409
|
-
; offsets on stack
|
410
|
-
Xoodoo_Permute_Nrounds_offsetA03 equ 0
|
411
|
-
Xoodoo_Permute_Nrounds_offsetRC equ 4
|
412
|
-
Xoodoo_Permute_Nrounds_SAS equ 8
|
413
|
-
Xoodoo_Permute_Nrounds_offsetState equ Xoodoo_Permute_Nrounds_SAS
|
414
|
-
|
415
|
-
EXPORT Xoodoo_Permute_Nrounds
|
416
|
-
Xoodoo_Permute_Nrounds PROC
|
417
|
-
push {r4-r6,lr}
|
418
|
-
mov r2, r8
|
419
|
-
mov r3, r9
|
420
|
-
mov r4, r10
|
421
|
-
mov r5, r11
|
422
|
-
push {r0,r2-r5,r7}
|
423
|
-
|
424
|
-
sub sp, #Xoodoo_Permute_Nrounds_SAS
|
425
|
-
adr r2, Xoodoo_Permute_RoundConstants12
|
426
|
-
lsls r1, r1, #2
|
427
|
-
subs r2, r2, r1
|
428
|
-
str r2, [sp, #Xoodoo_Permute_Nrounds_offsetRC]
|
429
|
-
|
430
|
-
ldm r0!, {r3,r5,r6,r7}
|
431
|
-
mov r8, r5
|
432
|
-
mov r9, r6
|
433
|
-
str r7, [sp, #Xoodoo_Permute_Nrounds_offsetA03]
|
434
|
-
ldm r0!, {r4,r5,r6,r7}
|
435
|
-
mov r10, r4
|
436
|
-
mov r11, r5
|
437
|
-
mov r12, r6
|
438
|
-
mov lr, r7
|
439
|
-
ldm r0!, {r4,r5,r6,r7}
|
440
|
-
Xoodoo_Permute_Nrouds_Loop
|
441
|
-
mRound Xoodoo_Permute_Nrounds_offsetRC, Xoodoo_Permute_Nrounds_offsetA03
|
442
|
-
ldr r0, [sp, #Xoodoo_Permute_Nrounds_offsetRC]
|
443
|
-
ldr r0, [r0]
|
444
|
-
cmp r0, #0
|
445
|
-
beq Xoodoo_Permute_Nrouds_Done
|
446
|
-
b Xoodoo_Permute_Nrouds_Loop
|
447
|
-
Xoodoo_Permute_Nrouds_Done
|
448
|
-
ldr r0, [sp, #Xoodoo_Permute_Nrounds_offsetState]
|
449
|
-
|
450
|
-
stm r0!, {r3}
|
451
|
-
mov r1, r8
|
452
|
-
mov r2, r9
|
453
|
-
ldr r3, [sp, #Xoodoo_Permute_Nrounds_offsetA03]
|
454
|
-
stm r0!, {r1,r2,r3}
|
455
|
-
|
456
|
-
mov r1, r10
|
457
|
-
mov r2, r11
|
458
|
-
mov r3, r12
|
459
|
-
stm r0!, {r1,r2,r3}
|
460
|
-
|
461
|
-
mov r1, lr
|
462
|
-
stm r0!, {r1,r4,r5,r6,r7}
|
463
|
-
|
464
|
-
add sp, #Xoodoo_Permute_Nrounds_SAS
|
465
|
-
pop {r0-r4,r7}
|
466
|
-
mov r8, r1
|
467
|
-
mov r9, r2
|
468
|
-
mov r10, r3
|
469
|
-
mov r11, r4
|
470
|
-
pop {r4-r6,pc}
|
471
|
-
align 4
|
472
|
-
ENDP
|
473
|
-
|
474
|
-
Xoodoo_Permute_RoundConstants
|
475
|
-
dcd 0x00000058
|
476
|
-
dcd 0x00000038
|
477
|
-
dcd 0x000003C0
|
478
|
-
dcd 0x000000D0
|
479
|
-
dcd 0x00000120
|
480
|
-
dcd 0x00000014
|
481
|
-
dcd 0x00000060
|
482
|
-
dcd 0x0000002C
|
483
|
-
dcd 0x00000380
|
484
|
-
dcd 0x000000F0
|
485
|
-
dcd 0x000001A0
|
486
|
-
dcd 0x00000012
|
487
|
-
Xoodoo_Permute_RoundConstants12
|
488
|
-
dcd 0
|
489
|
-
align 4
|
490
|
-
|
491
|
-
; ----------------------------------------------------------------------------
|
492
|
-
;
|
493
|
-
; void Xoodoo_Permute_6rounds( void *state )
|
494
|
-
;
|
495
|
-
EXPORT Xoodoo_Permute_6rounds
|
496
|
-
Xoodoo_Permute_6rounds PROC
|
497
|
-
movs r1, #6
|
498
|
-
b Xoodoo_Permute_Nrounds
|
499
|
-
align 4
|
500
|
-
ENDP
|
501
|
-
|
502
|
-
|
503
|
-
; ----------------------------------------------------------------------------
|
504
|
-
;
|
505
|
-
; void Xoodoo_Permute_12rounds( void *state )
|
506
|
-
;
|
507
|
-
EXPORT Xoodoo_Permute_12rounds
|
508
|
-
Xoodoo_Permute_12rounds PROC
|
509
|
-
movs r1, #12
|
510
|
-
b Xoodoo_Permute_Nrounds
|
511
|
-
align 4
|
512
|
-
ENDP
|
513
|
-
|
514
|
-
|
515
|
-
Xoofff_BlockSize equ 3*4*4
|
516
|
-
|
517
|
-
; ----------------------------------------------------------------------------
|
518
|
-
;
|
519
|
-
; void Xoofff_AddIs(BitSequence *output, const BitSequence *input, BitLength bitLen)
|
520
|
-
EXPORT Xoofff_AddIs
|
521
|
-
Xoofff_AddIs PROC
|
522
|
-
push {r4-r6,lr}
|
523
|
-
movs r3, r0 ; check input and output pointer both 32-bit aligned
|
524
|
-
orrs r3, r3, r1
|
525
|
-
lsls r3, r3, #30
|
526
|
-
bne Xoofff_AddIs_Bytes
|
527
|
-
subs r2, r2, #16*8
|
528
|
-
bcc Xoofff_AddIs_LessThan16
|
529
|
-
Xoofff_AddIs_16Loop
|
530
|
-
ldr r3, [r0, #0]
|
531
|
-
ldr r4, [r0, #4]
|
532
|
-
ldmia r1!, {r5,r6}
|
533
|
-
eors r3, r3, r5
|
534
|
-
eors r4, r4, r6
|
535
|
-
stmia r0!, {r3,r4}
|
536
|
-
ldr r3, [r0, #0]
|
537
|
-
ldr r4, [r0, #4]
|
538
|
-
ldmia r1!, {r5,r6}
|
539
|
-
eors r3, r3, r5
|
540
|
-
eors r4, r4, r6
|
541
|
-
stmia r0!, {r3,r4}
|
542
|
-
subs r2, r2, #16*8
|
543
|
-
bcs Xoofff_AddIs_16Loop
|
544
|
-
Xoofff_AddIs_LessThan16
|
545
|
-
adds r2, r2, #16*8
|
546
|
-
beq Xoofff_AddIs_Return
|
547
|
-
subs r2, r2, #4*8
|
548
|
-
bcc Xoofff_AddIs_LessThan4
|
549
|
-
Xoofff_AddIs_4Loop
|
550
|
-
ldr r3, [r0]
|
551
|
-
ldmia r1!, {r4}
|
552
|
-
eors r3, r3, r4
|
553
|
-
stmia r0!, {r3}
|
554
|
-
subs r2, r2, #4*8
|
555
|
-
bcs Xoofff_AddIs_4Loop
|
556
|
-
Xoofff_AddIs_LessThan4
|
557
|
-
adds r2, r2, #4*8
|
558
|
-
beq Xoofff_AddIs_Return
|
559
|
-
Xoofff_AddIs_Bytes
|
560
|
-
subs r2, r2, #8
|
561
|
-
bcc Xoofff_AddIs_LessThan1
|
562
|
-
Xoofff_AddIs_1Loop
|
563
|
-
ldrb r3, [r0]
|
564
|
-
ldrb r4, [r1]
|
565
|
-
adds r1, r1, #1
|
566
|
-
eors r3, r3, r4
|
567
|
-
strb r3, [r0]
|
568
|
-
adds r0, r0, #1
|
569
|
-
subs r2, r2, #8
|
570
|
-
bcs Xoofff_AddIs_1Loop
|
571
|
-
Xoofff_AddIs_LessThan1
|
572
|
-
adds r2, r2, #8
|
573
|
-
beq Xoofff_AddIs_Return
|
574
|
-
ldrb r3, [r0]
|
575
|
-
ldrb r4, [r1]
|
576
|
-
movs r1, #1
|
577
|
-
eors r3, r3, r4
|
578
|
-
lsls r1, r1, r2
|
579
|
-
subs r1, r1, #1
|
580
|
-
ands r3, r3, r1
|
581
|
-
strb r3, [r0]
|
582
|
-
Xoofff_AddIs_Return
|
583
|
-
pop {r4-r6,pc}
|
584
|
-
align 4
|
585
|
-
ENDP
|
586
|
-
|
587
|
-
MACRO
|
588
|
-
mLdu $rv, $ri, $tt
|
589
|
-
ldrb $rv, [$ri, #3]
|
590
|
-
lsls $rv, $rv, #8
|
591
|
-
ldrb $tt, [$ri, #2]
|
592
|
-
orrs $rv, $rv, $tt
|
593
|
-
lsls $rv, $rv, #8
|
594
|
-
ldrb $tt, [$ri, #1]
|
595
|
-
orrs $rv, $rv, $tt
|
596
|
-
lsls $rv, $rv, #8
|
597
|
-
ldrb $tt, [$ri, #0]
|
598
|
-
orrs $rv, $rv, $tt
|
599
|
-
adds $ri, $ri, #4
|
600
|
-
MEND
|
601
|
-
|
602
|
-
; ----------------------------------------------------------------------------
|
603
|
-
;
|
604
|
-
; size_t Xoofff_CompressFastLoop(unsigned char *kRoll, unsigned char *xAccu, const unsigned char *input, size_t length)
|
605
|
-
;
|
606
|
-
|
607
|
-
; offsets on stack
|
608
|
-
Xoofff_CompressFastLoop_offsetA03 equ 0
|
609
|
-
Xoofff_CompressFastLoop_offsetRC equ 4
|
610
|
-
Xoofff_CompressFastLoop_SAS equ 8
|
611
|
-
Xoofff_CompressFastLoop_kRoll equ Xoofff_CompressFastLoop_SAS+0
|
612
|
-
Xoofff_CompressFastLoop_input equ Xoofff_CompressFastLoop_SAS+4
|
613
|
-
Xoofff_CompressFastLoop_xAccu equ Xoofff_CompressFastLoop_SAS+8+16
|
614
|
-
Xoofff_CompressFastLoop_iInput equ Xoofff_CompressFastLoop_SAS+12+16
|
615
|
-
Xoofff_CompressFastLoop_length equ Xoofff_CompressFastLoop_SAS+16+16
|
616
|
-
|
617
|
-
EXPORT Xoofff_CompressFastLoop
|
618
|
-
Xoofff_CompressFastLoop PROC
|
619
|
-
subs r3, #Xoofff_BlockSize ; length must be greater than block size
|
620
|
-
push {r1-r7,lr}
|
621
|
-
mov r4, r8
|
622
|
-
mov r5, r9
|
623
|
-
mov r6, r10
|
624
|
-
mov r7, r11
|
625
|
-
push {r0,r2,r4-r7}
|
626
|
-
sub sp, #Xoofff_CompressFastLoop_SAS
|
627
|
-
ldm r0!, {r3,r5,r6,r7} ; get initial kRoll
|
628
|
-
mov r8, r5
|
629
|
-
mov r9, r6
|
630
|
-
str r7, [sp, #Xoofff_CompressFastLoop_offsetA03]
|
631
|
-
ldm r0!, {r4,r5,r6,r7}
|
632
|
-
mov r10, r4
|
633
|
-
mov r11, r5
|
634
|
-
mov r12, r6
|
635
|
-
mov lr, r7
|
636
|
-
ldm r0!, {r4,r5,r6,r7}
|
637
|
-
Xoofff_CompressFastLoop_Loop
|
638
|
-
adr r1, Xoofff_CompressFastLoop_RoundConstants6
|
639
|
-
str r1, [sp, #Xoofff_CompressFastLoop_offsetRC]
|
640
|
-
|
641
|
-
ldr r0, [sp, #Xoofff_CompressFastLoop_input] ; add input
|
642
|
-
lsls r1, r0, #30
|
643
|
-
bne Xoofff_CompressFastLoop_Unaligned
|
644
|
-
|
645
|
-
Xoofff_CompressFastLoop_Aligned
|
646
|
-
ldmia r0!, {r1}
|
647
|
-
eors r3, r3, r1
|
648
|
-
ldmia r0!, {r1}
|
649
|
-
mov r2, r8
|
650
|
-
eors r2, r2, r1
|
651
|
-
mov r8, r2
|
652
|
-
ldmia r0!, {r1}
|
653
|
-
mov r2, r9
|
654
|
-
eors r2, r2, r1
|
655
|
-
mov r9, r2
|
656
|
-
ldmia r0!, {r1}
|
657
|
-
ldr r2, [sp, #Xoofff_CompressFastLoop_offsetA03]
|
658
|
-
eors r2, r2, r1
|
659
|
-
str r2, [sp, #Xoofff_CompressFastLoop_offsetA03]
|
660
|
-
|
661
|
-
ldmia r0!, {r1}
|
662
|
-
mov r2, r10
|
663
|
-
eors r2, r2, r1
|
664
|
-
mov r10, r2
|
665
|
-
ldmia r0!, {r1}
|
666
|
-
mov r2, r11
|
667
|
-
eors r2, r2, r1
|
668
|
-
mov r11, r2
|
669
|
-
ldmia r0!, {r1}
|
670
|
-
mov r2, r12
|
671
|
-
eors r2, r2, r1
|
672
|
-
mov r12, r2
|
673
|
-
ldmia r0!, {r1}
|
674
|
-
mov r2, lr
|
675
|
-
eors r2, r2, r1
|
676
|
-
mov lr, r2
|
677
|
-
|
678
|
-
ldmia r0!, {r1,r2}
|
679
|
-
eors r4, r4, r1
|
680
|
-
eors r5, r5, r2
|
681
|
-
ldmia r0!, {r1,r2}
|
682
|
-
eors r6, r6, r1
|
683
|
-
eors r7, r7, r2
|
684
|
-
|
685
|
-
b Xoofff_CompressFastLoop_Permute
|
686
|
-
align 4
|
687
|
-
Xoofff_CompressFastLoop_RoundConstants6
|
688
|
-
dcd 0x00000060
|
689
|
-
dcd 0x0000002C
|
690
|
-
dcd 0x00000380
|
691
|
-
dcd 0x000000F0
|
692
|
-
dcd 0x000001A0
|
693
|
-
dcd 0x00000012
|
694
|
-
dcd 0
|
695
|
-
|
696
|
-
Xoofff_CompressFastLoop_Unaligned
|
697
|
-
mLdu r1, r0, r2
|
698
|
-
eors r3, r3, r1
|
699
|
-
mLdu r1, r0, r2
|
700
|
-
mov r2, r8
|
701
|
-
eors r2, r2, r1
|
702
|
-
mov r8, r2
|
703
|
-
mLdu r1, r0, r2
|
704
|
-
mov r2, r9
|
705
|
-
eors r2, r2, r1
|
706
|
-
mov r9, r2
|
707
|
-
mLdu r1, r0, r2
|
708
|
-
ldr r2, [sp, #Xoofff_CompressFastLoop_offsetA03]
|
709
|
-
eors r2, r2, r1
|
710
|
-
str r2, [sp, #Xoofff_CompressFastLoop_offsetA03]
|
711
|
-
|
712
|
-
mLdu r1, r0, r2
|
713
|
-
mov r2, r10
|
714
|
-
eors r2, r2, r1
|
715
|
-
mov r10, r2
|
716
|
-
mLdu r1, r0, r2
|
717
|
-
mov r2, r11
|
718
|
-
eors r2, r2, r1
|
719
|
-
mov r11, r2
|
720
|
-
mLdu r1, r0, r2
|
721
|
-
mov r2, r12
|
722
|
-
eors r2, r2, r1
|
723
|
-
mov r12, r2
|
724
|
-
mLdu r1, r0, r2
|
725
|
-
mov r2, lr
|
726
|
-
eors r2, r2, r1
|
727
|
-
mov lr, r2
|
728
|
-
|
729
|
-
mLdu r1, r0, r2
|
730
|
-
eors r4, r4, r1
|
731
|
-
mLdu r1, r0, r2
|
732
|
-
eors r5, r5, r1
|
733
|
-
mLdu r1, r0, r2
|
734
|
-
eors r6, r6, r1
|
735
|
-
mLdu r1, r0, r2
|
736
|
-
eors r7, r7, r1
|
737
|
-
|
738
|
-
Xoofff_CompressFastLoop_Permute
|
739
|
-
str r0, [sp, #Xoofff_CompressFastLoop_input]
|
740
|
-
Xoofff_CompressFastLoop_PermuteLoop
|
741
|
-
mRound Xoofff_CompressFastLoop_offsetRC, Xoofff_CompressFastLoop_offsetA03
|
742
|
-
ldr r0, [sp, #Xoofff_CompressFastLoop_offsetRC]
|
743
|
-
ldr r0, [r0]
|
744
|
-
cmp r0, #0
|
745
|
-
beq Xoofff_CompressFastLoop_PermuteDone
|
746
|
-
b Xoofff_CompressFastLoop_PermuteLoop
|
747
|
-
Xoofff_CompressFastLoop_PermuteDone
|
748
|
-
|
749
|
-
; Extract and add into xAccu
|
750
|
-
ldr r0, [sp, #Xoofff_CompressFastLoop_xAccu]
|
751
|
-
|
752
|
-
ldr r1, [r0]
|
753
|
-
eors r1, r1, r3
|
754
|
-
stmia r0!, {r1}
|
755
|
-
|
756
|
-
ldr r1, [r0]
|
757
|
-
mov r2, r8
|
758
|
-
eors r1, r1, r2
|
759
|
-
stmia r0!, {r1}
|
760
|
-
|
761
|
-
ldr r1, [r0]
|
762
|
-
mov r2, r9
|
763
|
-
eors r1, r1, r2
|
764
|
-
stmia r0!, {r1}
|
765
|
-
|
766
|
-
ldr r1, [r0]
|
767
|
-
ldr r2, [sp, #Xoofff_CompressFastLoop_offsetA03]
|
768
|
-
eors r1, r1, r2
|
769
|
-
stmia r0!, {r1}
|
770
|
-
|
771
|
-
|
772
|
-
ldr r1, [r0]
|
773
|
-
mov r2, r10
|
774
|
-
eors r1, r1, r2
|
775
|
-
stmia r0!, {r1}
|
776
|
-
ldr r1, [r0]
|
777
|
-
mov r2, r11
|
778
|
-
eors r1, r1, r2
|
779
|
-
stmia r0!, {r1}
|
780
|
-
ldr r1, [r0]
|
781
|
-
mov r2, r12
|
782
|
-
eors r1, r1, r2
|
783
|
-
stmia r0!, {r1}
|
784
|
-
ldr r1, [r0]
|
785
|
-
mov r2, lr
|
786
|
-
eors r1, r1, r2
|
787
|
-
stmia r0!, {r1}
|
788
|
-
|
789
|
-
ldr r1, [r0, #0]
|
790
|
-
ldr r2, [r0, #4]
|
791
|
-
ldr r3, [r0, #8]
|
792
|
-
eors r1, r1, r4
|
793
|
-
ldr r4, [r0, #12]
|
794
|
-
eors r2, r2, r5
|
795
|
-
eors r3, r3, r6
|
796
|
-
eors r4, r4, r7
|
797
|
-
stm r0!, {r1,r2,r3,r4}
|
798
|
-
|
799
|
-
;roll kRoll-c
|
800
|
-
ldr r0, [sp, #Xoofff_CompressFastLoop_kRoll]
|
801
|
-
ldmia r0!, {r7}
|
802
|
-
ldmia r0!, {r4-r6}
|
803
|
-
ldmia r0!, {r3}
|
804
|
-
ldmia r0!, {r1,r2}
|
805
|
-
mov r8, r1
|
806
|
-
mov r9, r2
|
807
|
-
ldmia r0!, {r1,r2}
|
808
|
-
str r1, [sp, #Xoofff_CompressFastLoop_offsetA03]
|
809
|
-
mov r10, r2
|
810
|
-
ldmia r0!, {r1,r2}
|
811
|
-
mov r11, r1
|
812
|
-
mov r12, r2
|
813
|
-
ldmia r0!, {r1}
|
814
|
-
mov lr, r1
|
815
|
-
|
816
|
-
lsls r1, r7, #13
|
817
|
-
eors r7, r7, r1
|
818
|
-
mov r1, r3
|
819
|
-
movs r2, #32-3
|
820
|
-
rors r1, r1, r2
|
821
|
-
eors r7, r7, r1
|
822
|
-
|
823
|
-
subs r0, r0, #Xoofff_BlockSize
|
824
|
-
stmia r0!, {r3}
|
825
|
-
mov r1, r8
|
826
|
-
mov r2, r9
|
827
|
-
stmia r0!, {r1,r2}
|
828
|
-
ldr r1, [sp, #Xoofff_CompressFastLoop_offsetA03]
|
829
|
-
mov r2, r10
|
830
|
-
stmia r0!, {r1,r2}
|
831
|
-
mov r1, r11
|
832
|
-
mov r2, r12
|
833
|
-
stmia r0!, {r1,r2}
|
834
|
-
mov r1, lr
|
835
|
-
stmia r0!, {r1,r4-r7}
|
836
|
-
|
837
|
-
; loop management
|
838
|
-
ldr r0, [sp, #Xoofff_CompressFastLoop_length]
|
839
|
-
subs r0, #Xoofff_BlockSize
|
840
|
-
str r0, [sp, #Xoofff_CompressFastLoop_length]
|
841
|
-
bcc Xoofff_CompressFastLoop_Done
|
842
|
-
b Xoofff_CompressFastLoop_Loop
|
843
|
-
Xoofff_CompressFastLoop_Done
|
844
|
-
; return number of bytes processed
|
845
|
-
ldr r0, [sp, #Xoofff_CompressFastLoop_input]
|
846
|
-
ldr r1, [sp, #Xoofff_CompressFastLoop_iInput]
|
847
|
-
subs r0, r0, r1
|
848
|
-
add sp, #Xoofff_CompressFastLoop_SAS+8
|
849
|
-
pop {r4-r7}
|
850
|
-
mov r8, r4
|
851
|
-
mov r9, r5
|
852
|
-
mov r10, r6
|
853
|
-
mov r11, r7
|
854
|
-
pop {r1-r7,pc}
|
855
|
-
align 4
|
856
|
-
ENDP
|
857
|
-
|
858
|
-
MACRO
|
859
|
-
mStu $rv, $ro
|
860
|
-
strb $rv, [$ro, #0]
|
861
|
-
lsrs $rv, $rv, #8
|
862
|
-
strb $rv, [$ro, #1]
|
863
|
-
lsrs $rv, $rv, #8
|
864
|
-
strb $rv, [$ro, #2]
|
865
|
-
lsrs $rv, $rv, #8
|
866
|
-
strb $rv, [$ro, #3]
|
867
|
-
adds $ro, $ro, #4
|
868
|
-
MEND
|
869
|
-
|
870
|
-
; ----------------------------------------------------------------------------
|
871
|
-
;
|
872
|
-
; size_t Xoofff_ExpandFastLoop(unsigned char *yAccu, const unsigned char *kRoll, unsigned char *output, size_t length)
|
873
|
-
;
|
874
|
-
|
875
|
-
; offsets on stack
|
876
|
-
Xoofff_ExpandFastLoop_offsetA03 equ 0
|
877
|
-
Xoofff_ExpandFastLoop_offsetRC equ 4
|
878
|
-
Xoofff_ExpandFastLoop_SAS equ 8
|
879
|
-
Xoofff_ExpandFastLoop_yAccu equ Xoofff_ExpandFastLoop_SAS+0
|
880
|
-
Xoofff_ExpandFastLoop_output equ Xoofff_ExpandFastLoop_SAS+4
|
881
|
-
Xoofff_ExpandFastLoop_kRoll equ Xoofff_ExpandFastLoop_SAS+8+16
|
882
|
-
Xoofff_ExpandFastLoop_iOutput equ Xoofff_ExpandFastLoop_SAS+12+16
|
883
|
-
Xoofff_ExpandFastLoop_length equ Xoofff_ExpandFastLoop_SAS+16+16
|
884
|
-
|
885
|
-
EXPORT Xoofff_ExpandFastLoop
|
886
|
-
Xoofff_ExpandFastLoop PROC
|
887
|
-
subs r3, #Xoofff_BlockSize ; length must be greater than block size
|
888
|
-
push {r1-r7,lr}
|
889
|
-
mov r4, r8
|
890
|
-
mov r5, r9
|
891
|
-
mov r6, r10
|
892
|
-
mov r7, r11
|
893
|
-
push {r0,r2,r4-r7}
|
894
|
-
sub sp, #Xoofff_ExpandFastLoop_SAS
|
895
|
-
|
896
|
-
ldm r0!, {r3,r5,r6,r7} ; get initial yAccu
|
897
|
-
mov r8, r5
|
898
|
-
mov r9, r6
|
899
|
-
str r7, [sp, #Xoofff_ExpandFastLoop_offsetA03]
|
900
|
-
ldm r0!, {r4,r5,r6,r7}
|
901
|
-
mov r10, r4
|
902
|
-
mov r11, r5
|
903
|
-
mov r12, r6
|
904
|
-
mov lr, r7
|
905
|
-
ldm r0!, {r4,r5,r6,r7}
|
906
|
-
Xoofff_ExpandFastLoop_Loop
|
907
|
-
adr r1, Xoofff_ExpandFastLoop_RoundConstants6
|
908
|
-
str r1, [sp, #Xoofff_ExpandFastLoop_offsetRC]
|
909
|
-
Xoofff_ExpandFastLoop_PermuteLoop
|
910
|
-
mRound Xoofff_ExpandFastLoop_offsetRC, Xoofff_ExpandFastLoop_offsetA03
|
911
|
-
ldr r0, [sp, #Xoofff_ExpandFastLoop_offsetRC]
|
912
|
-
ldr r0, [r0]
|
913
|
-
cmp r0, #0
|
914
|
-
beq Xoofff_ExpandFastLoop_PermuteDone
|
915
|
-
b Xoofff_ExpandFastLoop_PermuteLoop
|
916
|
-
Xoofff_ExpandFastLoop_RoundConstants6
|
917
|
-
dcd 0x00000060
|
918
|
-
dcd 0x0000002C
|
919
|
-
dcd 0x00000380
|
920
|
-
dcd 0x000000F0
|
921
|
-
dcd 0x000001A0
|
922
|
-
dcd 0x00000012
|
923
|
-
dcd 0
|
924
|
-
Xoofff_ExpandFastLoop_PermuteDone
|
925
|
-
; Add k and extract
|
926
|
-
ldr r0, [sp, #Xoofff_ExpandFastLoop_kRoll]
|
927
|
-
ldr r1, [sp, #Xoofff_ExpandFastLoop_output] ; add input
|
928
|
-
lsls r2, r1, #30
|
929
|
-
bne Xoofff_ExpandFastLoop_Unaligned
|
930
|
-
Xoofff_ExpandFastLoop_Aligned
|
931
|
-
ldmia r0!, {r2}
|
932
|
-
eors r2, r2, r3
|
933
|
-
stmia r1!, {r2}
|
934
|
-
ldmia r0!, {r2}
|
935
|
-
mov r3, r8
|
936
|
-
eors r2, r2, r3
|
937
|
-
stmia r1!, {r2}
|
938
|
-
ldmia r0!, {r2}
|
939
|
-
mov r3, r9
|
940
|
-
eors r2, r2, r3
|
941
|
-
stmia r1!, {r2}
|
942
|
-
ldmia r0!, {r2}
|
943
|
-
ldr r3, [sp, #Xoofff_ExpandFastLoop_offsetA03]
|
944
|
-
eors r2, r2, r3
|
945
|
-
stmia r1!, {r2}
|
946
|
-
|
947
|
-
ldmia r0!, {r2}
|
948
|
-
mov r3, r10
|
949
|
-
eors r2, r2, r3
|
950
|
-
stmia r1!, {r2}
|
951
|
-
ldmia r0!, {r2}
|
952
|
-
mov r3, r11
|
953
|
-
eors r2, r2, r3
|
954
|
-
stmia r1!, {r2}
|
955
|
-
ldmia r0!, {r2}
|
956
|
-
mov r3, r12
|
957
|
-
eors r2, r2, r3
|
958
|
-
stmia r1!, {r2}
|
959
|
-
ldmia r0!, {r2}
|
960
|
-
mov r3, lr
|
961
|
-
eors r2, r2, r3
|
962
|
-
stmia r1!, {r2}
|
963
|
-
|
964
|
-
ldmia r0!, {r2,r3}
|
965
|
-
eors r2, r2, r4
|
966
|
-
eors r3, r3, r5
|
967
|
-
stmia r1!, {r2,r3}
|
968
|
-
ldmia r0!, {r2,r3}
|
969
|
-
eors r2, r2, r6
|
970
|
-
eors r3, r3, r7
|
971
|
-
stmia r1!, {r2,r3}
|
972
|
-
b Xoofff_ExpandFastLoop_ExtractDone
|
973
|
-
|
974
|
-
Xoofff_ExpandFastLoop_Unaligned
|
975
|
-
ldmia r0!, {r2}
|
976
|
-
eors r2, r2, r3
|
977
|
-
mStu r2, r1
|
978
|
-
ldmia r0!, {r2}
|
979
|
-
mov r3, r8
|
980
|
-
eors r2, r2, r3
|
981
|
-
mStu r2, r1
|
982
|
-
ldmia r0!, {r2}
|
983
|
-
mov r3, r9
|
984
|
-
eors r2, r2, r3
|
985
|
-
mStu r2, r1
|
986
|
-
ldmia r0!, {r2}
|
987
|
-
ldr r3, [sp, #Xoofff_ExpandFastLoop_offsetA03]
|
988
|
-
eors r2, r2, r3
|
989
|
-
mStu r2, r1
|
990
|
-
|
991
|
-
ldmia r0!, {r2}
|
992
|
-
mov r3, r10
|
993
|
-
eors r2, r2, r3
|
994
|
-
mStu r2, r1
|
995
|
-
ldmia r0!, {r2}
|
996
|
-
mov r3, r11
|
997
|
-
eors r2, r2, r3
|
998
|
-
mStu r2, r1
|
999
|
-
ldmia r0!, {r2}
|
1000
|
-
mov r3, r12
|
1001
|
-
eors r2, r2, r3
|
1002
|
-
mStu r2, r1
|
1003
|
-
ldmia r0!, {r2}
|
1004
|
-
mov r3, lr
|
1005
|
-
eors r2, r2, r3
|
1006
|
-
mStu r2, r1
|
1007
|
-
|
1008
|
-
ldmia r0!, {r2,r3}
|
1009
|
-
eors r2, r2, r4
|
1010
|
-
mStu r2, r1
|
1011
|
-
eors r3, r3, r5
|
1012
|
-
mStu r3, r1
|
1013
|
-
ldmia r0!, {r2,r3}
|
1014
|
-
eors r2, r2, r6
|
1015
|
-
mStu r2, r1
|
1016
|
-
eors r3, r3, r7
|
1017
|
-
mStu r3, r1
|
1018
|
-
|
1019
|
-
Xoofff_ExpandFastLoop_ExtractDone
|
1020
|
-
str r1, [sp, #Xoofff_ExpandFastLoop_output]
|
1021
|
-
|
1022
|
-
; roll-e yAccu
|
1023
|
-
ldr r0, [sp, #Xoofff_ExpandFastLoop_yAccu]
|
1024
|
-
ldmia r0!, {r7}
|
1025
|
-
ldmia r0!, {r4-r6}
|
1026
|
-
ldmia r0!, {r3}
|
1027
|
-
ldmia r0!, {r1,r2}
|
1028
|
-
mov r8, r1
|
1029
|
-
mov r9, r2
|
1030
|
-
ldmia r0!, {r1,r2}
|
1031
|
-
str r1, [sp, #Xoofff_ExpandFastLoop_offsetA03]
|
1032
|
-
mov r10, r2
|
1033
|
-
ldmia r0!, {r1,r2}
|
1034
|
-
mov r11, r1
|
1035
|
-
mov r12, r2
|
1036
|
-
ldmia r0!, {r1}
|
1037
|
-
mov lr, r1
|
1038
|
-
|
1039
|
-
mov r1, r10
|
1040
|
-
ands r1, r1, r3
|
1041
|
-
movs r2, #32-5
|
1042
|
-
rors r7, r7, r2
|
1043
|
-
eors r7, r7, r1
|
1044
|
-
movs r2, #32-13
|
1045
|
-
mov r1, r3
|
1046
|
-
rors r1, r1, r2
|
1047
|
-
eors r7, r7, r1
|
1048
|
-
movs r1, #7
|
1049
|
-
eors r7, r7, r1
|
1050
|
-
|
1051
|
-
subs r0, r0, #Xoofff_BlockSize
|
1052
|
-
stmia r0!, {r3}
|
1053
|
-
mov r1, r8
|
1054
|
-
mov r2, r9
|
1055
|
-
stmia r0!, {r1,r2}
|
1056
|
-
ldr r1, [sp, #Xoofff_ExpandFastLoop_offsetA03]
|
1057
|
-
mov r2, r10
|
1058
|
-
stmia r0!, {r1,r2}
|
1059
|
-
mov r1, r11
|
1060
|
-
mov r2, r12
|
1061
|
-
stmia r0!, {r1,r2}
|
1062
|
-
mov r1, lr
|
1063
|
-
stmia r0!, {r1,r4-r7}
|
1064
|
-
|
1065
|
-
; loop management
|
1066
|
-
ldr r0, [sp, #Xoofff_ExpandFastLoop_length]
|
1067
|
-
subs r0, #Xoofff_BlockSize
|
1068
|
-
str r0, [sp, #Xoofff_ExpandFastLoop_length]
|
1069
|
-
bcc Xoofff_ExpandFastLoop_Done
|
1070
|
-
b Xoofff_ExpandFastLoop_Loop
|
1071
|
-
Xoofff_ExpandFastLoop_Done
|
1072
|
-
; return number of bytes processed
|
1073
|
-
ldr r0, [sp, #Xoofff_ExpandFastLoop_output]
|
1074
|
-
ldr r1, [sp, #Xoofff_ExpandFastLoop_iOutput]
|
1075
|
-
subs r0, r0, r1
|
1076
|
-
add sp, #Xoofff_ExpandFastLoop_SAS+8
|
1077
|
-
pop {r4-r7}
|
1078
|
-
mov r8, r4
|
1079
|
-
mov r9, r5
|
1080
|
-
mov r10, r6
|
1081
|
-
mov r11, r7
|
1082
|
-
pop {r1-r7,pc}
|
1083
|
-
align 4
|
1084
|
-
ENDP
|
1085
|
-
|
1086
|
-
END
|