sleeping_kangaroo12 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +34 -67
- 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/version.rb +1 -1
- metadata +33 -276
- 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
@@ -1,332 +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
|
-
#define VERBOSE 0
|
18
|
-
|
19
|
-
#include <stdio.h>
|
20
|
-
#include <string.h>
|
21
|
-
#include <smmintrin.h>
|
22
|
-
#include <wmmintrin.h>
|
23
|
-
#include <immintrin.h>
|
24
|
-
#include <emmintrin.h>
|
25
|
-
#include "align.h"
|
26
|
-
#include "brg_endian.h"
|
27
|
-
#include "Xoodoo.h"
|
28
|
-
#include "Xoodyak-parameters.h"
|
29
|
-
|
30
|
-
#if (PLATFORM_BYTE_ORDER != IS_LITTLE_ENDIAN)
|
31
|
-
#error Expecting a little-endian platform
|
32
|
-
#endif
|
33
|
-
|
34
|
-
#if (VERBOSE > 0)
|
35
|
-
#define Dump(__t) Vars2State; \
|
36
|
-
printf(__t "\n"); \
|
37
|
-
printf("a00 %08x, a01 %08x, a02 %08x, a03 %08x\n", state[0+0], state[0+1], state[0+2], state[0+3] ); \
|
38
|
-
printf("a10 %08x, a11 %08x, a12 %08x, a13 %08x\n", state[4+0], state[4+1], state[4+2], state[4+3] ); \
|
39
|
-
printf("a20 %08x, a21 %08x, a22 %08x, a23 %08x\n\n", state[8+0], state[8+1], state[8+2], state[8+3] );
|
40
|
-
#else
|
41
|
-
#define Dump(__t)
|
42
|
-
#endif
|
43
|
-
|
44
|
-
#if (VERBOSE >= 1)
|
45
|
-
#define Dump1(__t) Dump(__t)
|
46
|
-
#else
|
47
|
-
#define Dump1(__t)
|
48
|
-
#endif
|
49
|
-
|
50
|
-
#if (VERBOSE >= 2)
|
51
|
-
#define Dump2(__t) Dump(__t)
|
52
|
-
#else
|
53
|
-
#define Dump2(__t)
|
54
|
-
#endif
|
55
|
-
|
56
|
-
#if (VERBOSE >= 3)
|
57
|
-
#define Dump3(__t) Dump(__t)
|
58
|
-
#else
|
59
|
-
#define Dump3(__t)
|
60
|
-
#endif
|
61
|
-
|
62
|
-
|
63
|
-
typedef __m128i V128;
|
64
|
-
|
65
|
-
ALIGN(16) static const uint8_t maskRhoEast2[16] = {
|
66
|
-
11, 8, 9, 10,
|
67
|
-
15, 12, 13, 14,
|
68
|
-
3, 0, 1, 2,
|
69
|
-
7, 4, 5, 6,
|
70
|
-
};
|
71
|
-
|
72
|
-
#define ANDnu128(a, b) _mm_andnot_si128(a, b)
|
73
|
-
#define CONST128(a) _mm_load_si128((const V128 *)&(a))
|
74
|
-
#define LOAD128(a) _mm_load_si128((const V128 *)&(a))
|
75
|
-
#define LOAD128u(a) _mm_loadu_si128((const V128 *)&(a))
|
76
|
-
#define ROL32(a, o) _mm_rol_epi32(a, o)
|
77
|
-
#define STORE128(a, b) _mm_store_si128((V128 *)&(a), b)
|
78
|
-
#define STORE128u(a, b) _mm_storeu_si128((V128 *)&(a), b)
|
79
|
-
#define STORE64L(a, b) _mm_storel_epi64((V128 *)&(a), b)
|
80
|
-
#define XOR(a, b) _mm_xor_si128(a, b)
|
81
|
-
#define XOR3(a,b,c) _mm_ternarylogic_epi32(a,b,c,0x96)
|
82
|
-
#define Chi(a,b,c) _mm_ternarylogic_epi32(a,b,c,0xD2)
|
83
|
-
|
84
|
-
#define DeclareVars V128 a0, a1, a2, p, e; \
|
85
|
-
V128 rhoEast2 = CONST128(maskRhoEast2)
|
86
|
-
|
87
|
-
#define State2Vars(state) a0 = LOAD128(((uint32_t*)state)[0]), a1 = LOAD128(((uint32_t*)state)[4]), a2 = LOAD128(((uint32_t*)state)[8]);
|
88
|
-
|
89
|
-
#define Vars2State(state) STORE128(((uint32_t*)state)[0], a0), STORE128(((uint32_t*)state)[4], a1), STORE128(((uint32_t*)state)[8], a2);
|
90
|
-
|
91
|
-
#define Round(__rc) \
|
92
|
-
/* Theta: Column Parity Mixer */ \
|
93
|
-
p = XOR3( a0, a1, a2 ); \
|
94
|
-
p = _mm_shuffle_epi32( p, 0x93); \
|
95
|
-
e = ROL32( p, 5 ); \
|
96
|
-
p = ROL32( p, 14 ); \
|
97
|
-
a0 = XOR3( a0, e, p); \
|
98
|
-
a1 = XOR3( a1, e, p); \
|
99
|
-
a2 = XOR3( a2, e, p); \
|
100
|
-
Dump3("Theta"); \
|
101
|
-
\
|
102
|
-
/* Rho-west: Plane shift */ \
|
103
|
-
a1 = _mm_shuffle_epi32( a1, 0x93); \
|
104
|
-
a2 = ROL32(a2, 11); \
|
105
|
-
Dump3("Rho-west"); \
|
106
|
-
\
|
107
|
-
/* Iota: round constants */ \
|
108
|
-
a0 = XOR(a0, _mm_set_epi32(0, 0, 0, (__rc))); \
|
109
|
-
Dump3("Iota"); \
|
110
|
-
\
|
111
|
-
/* Chi: non linear step, on colums */ \
|
112
|
-
a0 = Chi(a0, a1, a2); \
|
113
|
-
a1 = Chi(a1, a2, a0); \
|
114
|
-
a2 = Chi(a2, a0, a1); \
|
115
|
-
Dump3("Chi"); \
|
116
|
-
\
|
117
|
-
/* Rho-east: Plane shift */ \
|
118
|
-
a1 = ROL32(a1, 1); \
|
119
|
-
a2 = _mm_shuffle_epi8( a2, rhoEast2); \
|
120
|
-
Dump3("Rho-east")
|
121
|
-
|
122
|
-
static const uint32_t RC[MAXROUNDS] = {
|
123
|
-
_rc12,
|
124
|
-
_rc11,
|
125
|
-
_rc10,
|
126
|
-
_rc9,
|
127
|
-
_rc8,
|
128
|
-
_rc7,
|
129
|
-
_rc6,
|
130
|
-
_rc5,
|
131
|
-
_rc4,
|
132
|
-
_rc3,
|
133
|
-
_rc2,
|
134
|
-
_rc1
|
135
|
-
};
|
136
|
-
|
137
|
-
size_t Xoodyak_AbsorbKeyedFullBlocks(void *state, const uint8_t *X, size_t XLen)
|
138
|
-
{
|
139
|
-
size_t initialLength = XLen;
|
140
|
-
DeclareVars;
|
141
|
-
|
142
|
-
State2Vars(state);
|
143
|
-
do {
|
144
|
-
Round(_rc12); /* Xoodyak_Up(instance, NULL, 0, 0); */
|
145
|
-
Round(_rc11);
|
146
|
-
Round(_rc10);
|
147
|
-
Round(_rc9);
|
148
|
-
Round(_rc8);
|
149
|
-
Round(_rc7);
|
150
|
-
Round(_rc6);
|
151
|
-
Round(_rc5);
|
152
|
-
Round(_rc4);
|
153
|
-
Round(_rc3);
|
154
|
-
Round(_rc2);
|
155
|
-
Round(_rc1);
|
156
|
-
a0 = XOR(a0, LOAD128u(X[0])); /* Xoodyak_Down(instance, X, Xoodyak_Rkin, 0); */
|
157
|
-
a1 = XOR(a1, LOAD128u(X[16]));
|
158
|
-
a2 = XOR(a2, _mm_set_epi32(1, *(uint32_t*)(&X[40]), *(uint32_t*)(&X[36]), *(uint32_t*)(&X[32])));
|
159
|
-
X += Xoodyak_Rkin;
|
160
|
-
XLen -= Xoodyak_Rkin;
|
161
|
-
} while (XLen >= Xoodyak_Rkin);
|
162
|
-
Vars2State(state);
|
163
|
-
|
164
|
-
return initialLength - XLen;
|
165
|
-
}
|
166
|
-
|
167
|
-
size_t Xoodyak_AbsorbHashFullBlocks(void *state, const uint8_t *X, size_t XLen)
|
168
|
-
{
|
169
|
-
size_t initialLength = XLen;
|
170
|
-
V128 one = _mm_set_epi32(0, 0, 0, 1);
|
171
|
-
DeclareVars;
|
172
|
-
|
173
|
-
State2Vars(state);
|
174
|
-
do {
|
175
|
-
Round(_rc12); /* Xoodyak_Up(instance, NULL, 0, 0); */
|
176
|
-
Round(_rc11);
|
177
|
-
Round(_rc10);
|
178
|
-
Round(_rc9);
|
179
|
-
Round(_rc8);
|
180
|
-
Round(_rc7);
|
181
|
-
Round(_rc6);
|
182
|
-
Round(_rc5);
|
183
|
-
Round(_rc4);
|
184
|
-
Round(_rc3);
|
185
|
-
Round(_rc2);
|
186
|
-
Round(_rc1);
|
187
|
-
a0 = XOR(a0, LOAD128u(X[0])); /* Xoodyak_Down(instance, X, Xoodyak_Rhash, 0); */
|
188
|
-
a1 = XOR(a1, one);
|
189
|
-
X += Xoodyak_Rhash;
|
190
|
-
XLen -= Xoodyak_Rhash;
|
191
|
-
} while (XLen >= Xoodyak_Rhash);
|
192
|
-
Vars2State(state);
|
193
|
-
|
194
|
-
return initialLength - XLen;
|
195
|
-
}
|
196
|
-
|
197
|
-
|
198
|
-
size_t Xoodyak_SqueezeKeyedFullBlocks(void *state, uint8_t *Y, size_t YLen)
|
199
|
-
{
|
200
|
-
size_t initialLength = YLen;
|
201
|
-
V128 one = _mm_set_epi32(0, 0, 0, 1);
|
202
|
-
DeclareVars;
|
203
|
-
|
204
|
-
State2Vars(state);
|
205
|
-
do {
|
206
|
-
a0 = XOR(a0, one); /* Xoodyak_Down(instance, NULL, 0, 0); */
|
207
|
-
Round(_rc12); /* Xoodyak_Up(instance, Y, Xoodyak_Rkout, 0); */
|
208
|
-
Round(_rc11);
|
209
|
-
Round(_rc10);
|
210
|
-
Round(_rc9);
|
211
|
-
Round(_rc8);
|
212
|
-
Round(_rc7);
|
213
|
-
Round(_rc6);
|
214
|
-
Round(_rc5);
|
215
|
-
Round(_rc4);
|
216
|
-
Round(_rc3);
|
217
|
-
Round(_rc2);
|
218
|
-
Round(_rc1);
|
219
|
-
STORE128u(Y[0], a0);
|
220
|
-
STORE64L(Y[16], a1);
|
221
|
-
Y += Xoodyak_Rkout;
|
222
|
-
YLen -= Xoodyak_Rkout;
|
223
|
-
} while (YLen >= Xoodyak_Rkout);
|
224
|
-
Vars2State(state);
|
225
|
-
|
226
|
-
return initialLength - YLen;
|
227
|
-
}
|
228
|
-
|
229
|
-
size_t Xoodyak_SqueezeHashFullBlocks(void *state, uint8_t *Y, size_t YLen)
|
230
|
-
{
|
231
|
-
size_t initialLength = YLen;
|
232
|
-
V128 one = _mm_set_epi32(0, 0, 0, 1);
|
233
|
-
DeclareVars;
|
234
|
-
|
235
|
-
State2Vars(state);
|
236
|
-
do {
|
237
|
-
a0 = XOR(a0, one); /* Xoodyak_Down(instance, NULL, 0, 0); */
|
238
|
-
Round(_rc12); /* Xoodyak_Up(instance, Y, Xoodyak_Rhash, 0); */
|
239
|
-
Round(_rc11);
|
240
|
-
Round(_rc10);
|
241
|
-
Round(_rc9);
|
242
|
-
Round(_rc8);
|
243
|
-
Round(_rc7);
|
244
|
-
Round(_rc6);
|
245
|
-
Round(_rc5);
|
246
|
-
Round(_rc4);
|
247
|
-
Round(_rc3);
|
248
|
-
Round(_rc2);
|
249
|
-
Round(_rc1);
|
250
|
-
STORE128u(Y[0], a0);
|
251
|
-
Y += Xoodyak_Rhash;
|
252
|
-
YLen -= Xoodyak_Rhash;
|
253
|
-
} while (YLen >= Xoodyak_Rhash);
|
254
|
-
Vars2State(state);
|
255
|
-
|
256
|
-
return initialLength - YLen;
|
257
|
-
}
|
258
|
-
|
259
|
-
size_t Xoodyak_EncryptFullBlocks(void *state, const uint8_t *I, uint8_t *O, size_t IOLen)
|
260
|
-
{
|
261
|
-
size_t initialLength = IOLen;
|
262
|
-
DeclareVars;
|
263
|
-
|
264
|
-
State2Vars(state);
|
265
|
-
do {
|
266
|
-
Round(_rc12);
|
267
|
-
Round(_rc11);
|
268
|
-
Round(_rc10);
|
269
|
-
Round(_rc9);
|
270
|
-
Round(_rc8);
|
271
|
-
Round(_rc7);
|
272
|
-
Round(_rc6);
|
273
|
-
Round(_rc5);
|
274
|
-
Round(_rc4);
|
275
|
-
Round(_rc3);
|
276
|
-
Round(_rc2);
|
277
|
-
Round(_rc1);
|
278
|
-
a0 = XOR(a0, LOAD128u(I[0]));
|
279
|
-
a1 = XOR(a1, _mm_set_epi32(0, 1, *(uint32_t*)(&I[20]), *(uint32_t*)(&I[16])));
|
280
|
-
STORE128u(O[0], a0);
|
281
|
-
STORE64L(O[16], a1);
|
282
|
-
I += Xoodyak_Rkout;
|
283
|
-
O += Xoodyak_Rkout;
|
284
|
-
IOLen -= Xoodyak_Rkout;
|
285
|
-
} while (IOLen >= Xoodyak_Rkout);
|
286
|
-
Vars2State(state);
|
287
|
-
|
288
|
-
return initialLength - IOLen;
|
289
|
-
}
|
290
|
-
|
291
|
-
size_t Xoodyak_DecryptFullBlocks(void *state, const uint8_t *I, uint8_t *O, size_t IOLen)
|
292
|
-
{
|
293
|
-
size_t initialLength = IOLen;
|
294
|
-
V128 o0;
|
295
|
-
V128 one = _mm_set_epi32(0, 1, 0, 0);
|
296
|
-
DeclareVars;
|
297
|
-
|
298
|
-
State2Vars(state);
|
299
|
-
do {
|
300
|
-
Round(_rc12);
|
301
|
-
Round(_rc11);
|
302
|
-
Round(_rc10);
|
303
|
-
Round(_rc9);
|
304
|
-
Round(_rc8);
|
305
|
-
Round(_rc7);
|
306
|
-
Round(_rc6);
|
307
|
-
Round(_rc5);
|
308
|
-
Round(_rc4);
|
309
|
-
Round(_rc3);
|
310
|
-
Round(_rc2);
|
311
|
-
Round(_rc1);
|
312
|
-
o0 = XOR(a0, LOAD128u(I[0]));
|
313
|
-
#if defined(__i386__) || defined(_M_IX86)
|
314
|
-
*((uint32_t*)(O+16)) = *((uint32_t*)(I+16)) ^ _mm_extract_epi32(a1, 0);
|
315
|
-
*((uint32_t*)(O+20)) = *((uint32_t*)(I+20)) ^ _mm_extract_epi32(a1, 1);
|
316
|
-
a1 = _mm_insert_epi32(a1, *((uint32_t*)(I+16)), 0);
|
317
|
-
a1 = _mm_insert_epi32(a1, *((uint32_t*)(I+20)), 1);
|
318
|
-
#else
|
319
|
-
*((uint64_t*)(O+16)) = *((uint64_t*)(I+16)) ^ _mm_extract_epi64(a1, 0);
|
320
|
-
a1 = _mm_insert_epi64(a1, *((uint64_t*)(I+16)), 0);
|
321
|
-
#endif
|
322
|
-
STORE128u(O[0], o0);
|
323
|
-
a0 = XOR(a0, o0);
|
324
|
-
a1 = XOR(a1, one);
|
325
|
-
I += Xoodyak_Rkout;
|
326
|
-
O += Xoodyak_Rkout;
|
327
|
-
IOLen -= Xoodyak_Rkout;
|
328
|
-
} while (IOLen >= Xoodyak_Rkout);
|
329
|
-
Vars2State(state);
|
330
|
-
|
331
|
-
return initialLength - IOLen;
|
332
|
-
}
|
@@ -1,329 +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
|
-
#define VERBOSE 0
|
18
|
-
|
19
|
-
#include <stdio.h>
|
20
|
-
#include <stdlib.h>
|
21
|
-
#include <string.h>
|
22
|
-
#include <emmintrin.h>
|
23
|
-
#include <pmmintrin.h>
|
24
|
-
#include <tmmintrin.h>
|
25
|
-
#include "align.h"
|
26
|
-
#include "Xoodoo.h"
|
27
|
-
|
28
|
-
#include "brg_endian.h"
|
29
|
-
#if (PLATFORM_BYTE_ORDER != IS_LITTLE_ENDIAN)
|
30
|
-
#error Expecting a little-endian platform
|
31
|
-
#endif
|
32
|
-
|
33
|
-
#if (VERBOSE > 0)
|
34
|
-
#define Dump(__t) Vars2State; \
|
35
|
-
printf(__t "\n"); \
|
36
|
-
printf("a00 %08x, a01 %08x, a02 %08x, a03 %08x\n", state[0+0], state[0+1], state[0+2], state[0+3] ); \
|
37
|
-
printf("a10 %08x, a11 %08x, a12 %08x, a13 %08x\n", state[4+0], state[4+1], state[4+2], state[4+3] ); \
|
38
|
-
printf("a20 %08x, a21 %08x, a22 %08x, a23 %08x\n\n", state[8+0], state[8+1], state[8+2], state[8+3] );
|
39
|
-
#else
|
40
|
-
#define Dump(__t)
|
41
|
-
#endif
|
42
|
-
|
43
|
-
#if (VERBOSE >= 1)
|
44
|
-
#define Dump1(__t) Dump(__t)
|
45
|
-
#else
|
46
|
-
#define Dump1(__t)
|
47
|
-
#endif
|
48
|
-
|
49
|
-
#if (VERBOSE >= 2)
|
50
|
-
#define Dump2(__t) Dump(__t)
|
51
|
-
#else
|
52
|
-
#define Dump2(__t)
|
53
|
-
#endif
|
54
|
-
|
55
|
-
#if (VERBOSE >= 3)
|
56
|
-
#define Dump3(__t) Dump(__t)
|
57
|
-
#else
|
58
|
-
#define Dump3(__t)
|
59
|
-
#endif
|
60
|
-
|
61
|
-
|
62
|
-
/* ---------------------------------------------------------------- */
|
63
|
-
|
64
|
-
void Xoodoo_Initialize(void *state)
|
65
|
-
{
|
66
|
-
memset(state, 0, NLANES*sizeof(tXoodooLane));
|
67
|
-
}
|
68
|
-
|
69
|
-
/* ---------------------------------------------------------------- */
|
70
|
-
|
71
|
-
void Xoodoo_AddBytes(void *argState, const unsigned char *data, unsigned int offset, unsigned int length)
|
72
|
-
{
|
73
|
-
#if (PLATFORM_BYTE_ORDER == IS_LITTLE_ENDIAN)
|
74
|
-
unsigned int sizeLeft = length;
|
75
|
-
unsigned int lanePosition = offset/4;
|
76
|
-
unsigned int offsetInLane = offset%4;
|
77
|
-
const unsigned char *curData = data;
|
78
|
-
uint32_t *state = (uint32_t*)argState;
|
79
|
-
|
80
|
-
state += lanePosition;
|
81
|
-
if ((sizeLeft > 0) && (offsetInLane != 0)) {
|
82
|
-
unsigned int bytesInLane = 4 - offsetInLane;
|
83
|
-
uint32_t lane = 0;
|
84
|
-
if (bytesInLane > sizeLeft)
|
85
|
-
bytesInLane = sizeLeft;
|
86
|
-
memcpy((unsigned char*)&lane + offsetInLane, curData, bytesInLane);
|
87
|
-
*state++ ^= lane;
|
88
|
-
sizeLeft -= bytesInLane;
|
89
|
-
curData += bytesInLane;
|
90
|
-
}
|
91
|
-
|
92
|
-
while(sizeLeft >= 4) {
|
93
|
-
*state++ ^= READ32_UNALIGNED( curData );
|
94
|
-
sizeLeft -= 4;
|
95
|
-
curData += 4;
|
96
|
-
}
|
97
|
-
|
98
|
-
if (sizeLeft > 0) {
|
99
|
-
uint32_t lane = 0;
|
100
|
-
memcpy(&lane, curData, sizeLeft);
|
101
|
-
*state ^= lane;
|
102
|
-
}
|
103
|
-
#else
|
104
|
-
#error "Not yet implemented"
|
105
|
-
#endif
|
106
|
-
}
|
107
|
-
|
108
|
-
/* ---------------------------------------------------------------- */
|
109
|
-
|
110
|
-
void Xoodoo_OverwriteBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
111
|
-
{
|
112
|
-
#if (PLATFORM_BYTE_ORDER == IS_LITTLE_ENDIAN)
|
113
|
-
memcpy((unsigned char*)state+offset, data, length);
|
114
|
-
#else
|
115
|
-
#error "Not yet implemented"
|
116
|
-
#endif
|
117
|
-
}
|
118
|
-
|
119
|
-
/* ---------------------------------------------------------------- */
|
120
|
-
|
121
|
-
void Xoodoo_OverwriteWithZeroes(void *state, unsigned int byteCount)
|
122
|
-
{
|
123
|
-
#if (PLATFORM_BYTE_ORDER == IS_LITTLE_ENDIAN)
|
124
|
-
memset(state, 0, byteCount);
|
125
|
-
#else
|
126
|
-
#error "Not yet implemented"
|
127
|
-
#endif
|
128
|
-
}
|
129
|
-
|
130
|
-
/* ---------------------------------------------------------------- */
|
131
|
-
|
132
|
-
void Xoodoo_ExtractBytes(const void *state, unsigned char *data, unsigned int offset, unsigned int length)
|
133
|
-
{
|
134
|
-
#if (PLATFORM_BYTE_ORDER == IS_LITTLE_ENDIAN)
|
135
|
-
memcpy(data, (unsigned char*)state+offset, length);
|
136
|
-
#else
|
137
|
-
#error "Not yet implemented"
|
138
|
-
#endif
|
139
|
-
}
|
140
|
-
|
141
|
-
/* ---------------------------------------------------------------- */
|
142
|
-
|
143
|
-
void Xoodoo_ExtractAndAddBytes(const void *argState, const unsigned char *input, unsigned char *output, unsigned int offset, unsigned int length)
|
144
|
-
{
|
145
|
-
#if (PLATFORM_BYTE_ORDER == IS_LITTLE_ENDIAN)
|
146
|
-
unsigned int sizeLeft = length;
|
147
|
-
unsigned int lanePosition = offset/4;
|
148
|
-
unsigned int offsetInLane = offset%4;
|
149
|
-
const unsigned char *curInput = input;
|
150
|
-
unsigned char *curOutput = output;
|
151
|
-
const uint32_t *state = (const uint32_t*)argState;
|
152
|
-
|
153
|
-
state += lanePosition;
|
154
|
-
if ((sizeLeft > 0) && (offsetInLane != 0)) {
|
155
|
-
unsigned int bytesInLane = 4 - offsetInLane;
|
156
|
-
uint32_t lane = *state++ >> (offsetInLane * 8);
|
157
|
-
if (bytesInLane > sizeLeft)
|
158
|
-
bytesInLane = sizeLeft;
|
159
|
-
sizeLeft -= bytesInLane;
|
160
|
-
do {
|
161
|
-
*curOutput++ = (*curInput++) ^ (unsigned char)lane;
|
162
|
-
lane >>= 8;
|
163
|
-
}
|
164
|
-
while ( --bytesInLane != 0);
|
165
|
-
}
|
166
|
-
|
167
|
-
while(sizeLeft >= 4) {
|
168
|
-
WRITE32_UNALIGNED( curOutput, READ32_UNALIGNED( curInput ) ^ *state++ );
|
169
|
-
sizeLeft -= 4;
|
170
|
-
curInput += 4;
|
171
|
-
curOutput += 4;
|
172
|
-
}
|
173
|
-
|
174
|
-
if (sizeLeft > 0) {
|
175
|
-
uint32_t lane = *state;
|
176
|
-
do {
|
177
|
-
*curOutput++ = (*curInput++) ^ (unsigned char)lane;
|
178
|
-
lane >>= 8;
|
179
|
-
}
|
180
|
-
while ( --sizeLeft != 0 );
|
181
|
-
}
|
182
|
-
#else
|
183
|
-
#error "Not yet implemented"
|
184
|
-
#endif
|
185
|
-
}
|
186
|
-
|
187
|
-
/* ---------------------------------------------------------------- */
|
188
|
-
|
189
|
-
typedef __m128i V128;
|
190
|
-
|
191
|
-
ALIGN(16) static const uint8_t maskRhoEast2[16] = {
|
192
|
-
11, 8, 9, 10,
|
193
|
-
15, 12, 13, 14,
|
194
|
-
3, 0, 1, 2,
|
195
|
-
7, 4, 5, 6,
|
196
|
-
};
|
197
|
-
|
198
|
-
#define ANDnu128(a, b) _mm_andnot_si128(a, b)
|
199
|
-
#define CONST128(a) _mm_load_si128((const V128 *)&(a))
|
200
|
-
#define LOAD128(a) _mm_load_si128((const V128 *)&(a))
|
201
|
-
#if defined(Waffel_useXOP)
|
202
|
-
#define ROL32in128(a, o) _mm_roti_epi32(a, o)
|
203
|
-
#else
|
204
|
-
#define ROL32in128(a, o) _mm_or_si128(_mm_slli_epi32(a, o), _mm_srli_epi32(a, 32-(o)))
|
205
|
-
#endif
|
206
|
-
#define STORE128(a, b) _mm_store_si128((V128 *)&(a), b)
|
207
|
-
#define XOR128(a, b) _mm_xor_si128(a, b)
|
208
|
-
|
209
|
-
#define DeclareVars V128 a0, a1, a2, p, e; \
|
210
|
-
V128 rhoEast2 = CONST128(maskRhoEast2)
|
211
|
-
|
212
|
-
#define State2Vars a0 = LOAD128(state[0]), a1 = LOAD128(state[4]), a2 = LOAD128(state[8]);
|
213
|
-
|
214
|
-
#define Vars2State STORE128(state[0], a0), STORE128(state[4], a1), STORE128(state[8], a2);
|
215
|
-
|
216
|
-
/*
|
217
|
-
** Theta: Column Parity Mixer
|
218
|
-
*/
|
219
|
-
#define Theta() p = XOR128( a0, a1 ); \
|
220
|
-
p = XOR128( p, a2 ); \
|
221
|
-
p = _mm_shuffle_epi32( p, 0x93); \
|
222
|
-
e = ROL32in128( p, 5 ); \
|
223
|
-
p = ROL32in128( p, 14 ); \
|
224
|
-
e = XOR128( e, p ); \
|
225
|
-
a0 = XOR128( a0, e ); \
|
226
|
-
a1 = XOR128( a1, e ); \
|
227
|
-
a2 = XOR128( a2, e );
|
228
|
-
|
229
|
-
/*
|
230
|
-
** Rho-west: Plane shift
|
231
|
-
*/
|
232
|
-
#define Rho_west() a1 = _mm_shuffle_epi32( a1, 0x93); \
|
233
|
-
a2 = ROL32in128(a2, 11);
|
234
|
-
|
235
|
-
/*
|
236
|
-
** Iota: round constants
|
237
|
-
*/
|
238
|
-
#define Iota(__rc) a0 = XOR128(a0, _mm_set_epi32(0, 0, 0, (__rc)));
|
239
|
-
|
240
|
-
/*
|
241
|
-
** Chi: non linear step, on colums
|
242
|
-
*/
|
243
|
-
#define Chi() a0 = XOR128(a0, ANDnu128(a1, a2)); \
|
244
|
-
a1 = XOR128(a1, ANDnu128(a2, a0)); \
|
245
|
-
a2 = XOR128(a2, ANDnu128(a0, a1));
|
246
|
-
|
247
|
-
/*
|
248
|
-
** Rho-east: Plane shift
|
249
|
-
*/
|
250
|
-
#define Rho_east() a1 = ROL32in128(a1, 1); \
|
251
|
-
a2 = _mm_shuffle_epi8( a2, rhoEast2);
|
252
|
-
|
253
|
-
|
254
|
-
#define Round(__rc) \
|
255
|
-
Theta(); \
|
256
|
-
Dump3("Theta"); \
|
257
|
-
Rho_west(); \
|
258
|
-
Dump3("Rho-west"); \
|
259
|
-
Iota(__rc); \
|
260
|
-
Dump3("Iota"); \
|
261
|
-
Chi(); \
|
262
|
-
Dump3("Chi"); \
|
263
|
-
Rho_east(); \
|
264
|
-
Dump3("Rho-east")
|
265
|
-
|
266
|
-
static const uint32_t RC[MAXROUNDS] = {
|
267
|
-
_rc12,
|
268
|
-
_rc11,
|
269
|
-
_rc10,
|
270
|
-
_rc9,
|
271
|
-
_rc8,
|
272
|
-
_rc7,
|
273
|
-
_rc6,
|
274
|
-
_rc5,
|
275
|
-
_rc4,
|
276
|
-
_rc3,
|
277
|
-
_rc2,
|
278
|
-
_rc1
|
279
|
-
};
|
280
|
-
|
281
|
-
void Xoodoo_Permute_Nrounds( uint32_t * state, uint32_t nr )
|
282
|
-
{
|
283
|
-
DeclareVars;
|
284
|
-
uint32_t i;
|
285
|
-
|
286
|
-
State2Vars;
|
287
|
-
for (i = MAXROUNDS - nr; i < MAXROUNDS; ++i ) {
|
288
|
-
Round(RC[i]);
|
289
|
-
Dump2("Round");
|
290
|
-
}
|
291
|
-
Dump1("Permutation");
|
292
|
-
Vars2State;
|
293
|
-
}
|
294
|
-
|
295
|
-
void Xoodoo_Permute_6rounds( uint32_t * state)
|
296
|
-
{
|
297
|
-
DeclareVars;
|
298
|
-
|
299
|
-
State2Vars;
|
300
|
-
Round(_rc6);
|
301
|
-
Round(_rc5);
|
302
|
-
Round(_rc4);
|
303
|
-
Round(_rc3);
|
304
|
-
Round(_rc2);
|
305
|
-
Round(_rc1);
|
306
|
-
Dump1("Permutation");
|
307
|
-
Vars2State;
|
308
|
-
}
|
309
|
-
|
310
|
-
void Xoodoo_Permute_12rounds( uint32_t * state)
|
311
|
-
{
|
312
|
-
DeclareVars;
|
313
|
-
|
314
|
-
State2Vars;
|
315
|
-
Round(_rc12);
|
316
|
-
Round(_rc11);
|
317
|
-
Round(_rc10);
|
318
|
-
Round(_rc9);
|
319
|
-
Round(_rc8);
|
320
|
-
Round(_rc7);
|
321
|
-
Round(_rc6);
|
322
|
-
Round(_rc5);
|
323
|
-
Round(_rc4);
|
324
|
-
Round(_rc3);
|
325
|
-
Round(_rc2);
|
326
|
-
Round(_rc1);
|
327
|
-
Dump1("Permutation");
|
328
|
-
Vars2State;
|
329
|
-
}
|
@@ -1,53 +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
|
-
#ifndef _Xoodoo_SnP_h_
|
18
|
-
#define _Xoodoo_SnP_h_
|
19
|
-
|
20
|
-
#include <stddef.h>
|
21
|
-
#include <stdint.h>
|
22
|
-
|
23
|
-
/** For the documentation, see SnP-documentation.h.
|
24
|
-
*/
|
25
|
-
|
26
|
-
#define Xoodoo_implementation "SIMD-128 optimized implementation"
|
27
|
-
#define Xoodoo_stateSizeInBytes (3*4*4)
|
28
|
-
#define Xoodoo_stateAlignment 16
|
29
|
-
#define Xoodoo_HasNround
|
30
|
-
|
31
|
-
/* void Xoodoo_StaticInitialize( void ); */
|
32
|
-
#define Xoodoo_StaticInitialize()
|
33
|
-
void Xoodoo_Initialize(void *state);
|
34
|
-
/* void Xoodoo_AddByte(void *state, uint8_t data, unsigned int offset); */
|
35
|
-
#define Xoodoo_AddByte(argS, argData, argOffset) ((uint8_t*)argS)[argOffset] ^= (argData)
|
36
|
-
void Xoodoo_AddBytes(void *state, const uint8_t *data, unsigned int offset, unsigned int length);
|
37
|
-
void Xoodoo_OverwriteBytes(void *state, const uint8_t *data, unsigned int offset, unsigned int length);
|
38
|
-
void Xoodoo_OverwriteWithZeroes(void *state, unsigned int byteCount);
|
39
|
-
void Xoodoo_Permute_Nrounds(void *state, unsigned int nrounds);
|
40
|
-
void Xoodoo_Permute_6rounds(void *state);
|
41
|
-
void Xoodoo_Permute_12rounds(void *state);
|
42
|
-
void Xoodoo_ExtractBytes(const void *state, uint8_t *data, unsigned int offset, unsigned int length);
|
43
|
-
void Xoodoo_ExtractAndAddBytes(const void *state, const uint8_t *input, uint8_t *output, unsigned int offset, unsigned int length);
|
44
|
-
|
45
|
-
#define CyclistFullBlocks_supported
|
46
|
-
size_t Xoodyak_AbsorbKeyedFullBlocks(void *state, const uint8_t *X, size_t XLen);
|
47
|
-
size_t Xoodyak_AbsorbHashFullBlocks(void *state, const uint8_t *X, size_t XLen);
|
48
|
-
size_t Xoodyak_SqueezeHashFullBlocks(void *state, uint8_t *Y, size_t YLen);
|
49
|
-
size_t Xoodyak_SqueezeKeyedFullBlocks(void *state, uint8_t *Y, size_t YLen);
|
50
|
-
size_t Xoodyak_EncryptFullBlocks(void *state, const uint8_t *I, uint8_t *O, size_t IOLen);
|
51
|
-
size_t Xoodyak_DecryptFullBlocks(void *state, const uint8_t *I, uint8_t *O, size_t IOLen);
|
52
|
-
|
53
|
-
#endif
|