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
@@ -1,1124 +0,0 @@
|
|
1
|
-
//
|
2
|
-
// The eXtended Keccak Code Package (XKCP)
|
3
|
-
// https://github.com/XKCP/XKCP
|
4
|
-
//
|
5
|
-
// The Keccak-p permutations, designed by Guido Bertoni, Joan Daemen, Michaël Peeters and Gilles Van Assche.
|
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
|
-
//
|
18
|
-
// This file implements Keccak-p[1600] in a SnP-compatible way.
|
19
|
-
// Please refer to SnP-documentation.h for more details.
|
20
|
-
//
|
21
|
-
// This implementation comes with KeccakP-1600-SnP.h in the same folder.
|
22
|
-
// Please refer to LowLevel.build for the exact list of other files it must be combined with.
|
23
|
-
//
|
24
|
-
|
25
|
-
// WARNING: State must be 256 bit (32 bytes) aligned, better is 64-byte aligned (cache line)
|
26
|
-
|
27
|
-
// Modification Stephane Leon 8.4.2016 Change syntax for apple syntax (old gas syntax)
|
28
|
-
// Modification Stephane Leon 12.5.2016 Use the right register for pxor in macro for simd
|
29
|
-
// Modification Stephane Leon 4.2.2017 Fix absolute addressing problem for 64 bit mode
|
30
|
-
|
31
|
-
.text
|
32
|
-
|
33
|
-
// conditional assembly settings
|
34
|
-
#define InlinePerm 1
|
35
|
-
|
36
|
-
// offsets in state
|
37
|
-
#define _ba 0*8
|
38
|
-
#define _be 1*8
|
39
|
-
#define _bi 2*8
|
40
|
-
#define _bo 3*8
|
41
|
-
#define _bu 4*8
|
42
|
-
#define _ga 5*8
|
43
|
-
#define _ge 6*8
|
44
|
-
#define _gi 7*8
|
45
|
-
#define _go 8*8
|
46
|
-
#define _gu 9*8
|
47
|
-
#define _ka 10*8
|
48
|
-
#define _ke 11*8
|
49
|
-
#define _ki 12*8
|
50
|
-
#define _ko 13*8
|
51
|
-
#define _ku 14*8
|
52
|
-
#define _ma 15*8
|
53
|
-
#define _me 16*8
|
54
|
-
#define _mi 17*8
|
55
|
-
#define _mo 18*8
|
56
|
-
#define _mu 19*8
|
57
|
-
#define _sa 20*8
|
58
|
-
#define _se 21*8
|
59
|
-
#define _si 22*8
|
60
|
-
#define _so 23*8
|
61
|
-
#define _su 24*8
|
62
|
-
|
63
|
-
// arguments passed in registers
|
64
|
-
#define arg1 %rdi
|
65
|
-
#define arg2 %rsi
|
66
|
-
#define arg3 %rdx
|
67
|
-
#define arg4 %rcx
|
68
|
-
#define arg5 %r8
|
69
|
-
#define arg6 %r9
|
70
|
-
|
71
|
-
// temporary registers
|
72
|
-
#define rT1 %rax
|
73
|
-
#define rT1a rT1
|
74
|
-
#define rT1e %rbx
|
75
|
-
#define rT1i %r14
|
76
|
-
#define rT1o %r15
|
77
|
-
#define rT1u arg6
|
78
|
-
#define rT2a %r10
|
79
|
-
#define rT2e %r11
|
80
|
-
#define rT2i %r12
|
81
|
-
#define rT2o %r13
|
82
|
-
#define rT2u arg5
|
83
|
-
|
84
|
-
// round vars
|
85
|
-
#define rpState arg1
|
86
|
-
#define rpStack %rsp
|
87
|
-
|
88
|
-
#define rDa %rbx
|
89
|
-
#define rDe %rcx
|
90
|
-
#define rDi %rdx
|
91
|
-
#define rDo %r8
|
92
|
-
#define rDu %r9
|
93
|
-
|
94
|
-
#define rBa %r10
|
95
|
-
#define rBe %r11
|
96
|
-
#define rBi %r12
|
97
|
-
#define rBo %r13
|
98
|
-
#define rBu %r14
|
99
|
-
|
100
|
-
#define rCa %rsi
|
101
|
-
#define rCe %rbp
|
102
|
-
#define rCi rBi
|
103
|
-
#define rCo rBo
|
104
|
-
#define rCu %r15
|
105
|
-
|
106
|
-
.macro mKeccakRound iState, oState, rc, lastRound
|
107
|
-
|
108
|
-
// prepare Theta bis
|
109
|
-
movq rCe, rDa
|
110
|
-
rolq rDa
|
111
|
-
|
112
|
-
movq _bi(\iState), rCi
|
113
|
-
xorq _gi(\iState), rDi
|
114
|
-
xorq rCu, rDa
|
115
|
-
xorq _ki(\iState), rCi
|
116
|
-
xorq _mi(\iState), rDi
|
117
|
-
xorq rDi, rCi
|
118
|
-
|
119
|
-
movq rCi, rDe
|
120
|
-
rolq rDe
|
121
|
-
|
122
|
-
movq _bo(\iState), rCo
|
123
|
-
xorq _go(\iState), rDo
|
124
|
-
xorq rCa, rDe
|
125
|
-
xorq _ko(\iState), rCo
|
126
|
-
xorq _mo(\iState), rDo
|
127
|
-
xorq rDo, rCo
|
128
|
-
|
129
|
-
movq rCo, rDi
|
130
|
-
rolq rDi
|
131
|
-
|
132
|
-
movq rCu, rDo
|
133
|
-
xorq rCe, rDi
|
134
|
-
rolq rDo
|
135
|
-
|
136
|
-
movq rCa, rDu
|
137
|
-
xorq rCi, rDo
|
138
|
-
rolq rDu
|
139
|
-
|
140
|
-
// Theta Rho Pi Chi Iota, result b
|
141
|
-
movq _ba(\iState), rBa
|
142
|
-
movq _ge(\iState), rBe
|
143
|
-
xorq rCo, rDu
|
144
|
-
movq _ki(\iState), rBi
|
145
|
-
movq _mo(\iState), rBo
|
146
|
-
movq _su(\iState), rBu
|
147
|
-
xorq rDe, rBe
|
148
|
-
rolq $44, rBe
|
149
|
-
xorq rDi, rBi
|
150
|
-
xorq rDa, rBa
|
151
|
-
rolq $43, rBi
|
152
|
-
|
153
|
-
movq rBe, rCa
|
154
|
-
movq $\rc, rT1
|
155
|
-
orq rBi, rCa
|
156
|
-
xorq rBa, rT1
|
157
|
-
xorq rT1, rCa
|
158
|
-
movq rCa, _ba(\oState)
|
159
|
-
|
160
|
-
xorq rDu, rBu
|
161
|
-
rolq $14, rBu
|
162
|
-
movq rBa, rCu
|
163
|
-
andq rBe, rCu
|
164
|
-
xorq rBu, rCu
|
165
|
-
movq rCu, _bu(\oState)
|
166
|
-
|
167
|
-
xorq rDo, rBo
|
168
|
-
rolq $21, rBo
|
169
|
-
movq rBo, rT1
|
170
|
-
andq rBu, rT1
|
171
|
-
xorq rBi, rT1
|
172
|
-
movq rT1, _bi(\oState)
|
173
|
-
|
174
|
-
notq rBi
|
175
|
-
orq rBa, rBu
|
176
|
-
orq rBo, rBi
|
177
|
-
xorq rBo, rBu
|
178
|
-
xorq rBe, rBi
|
179
|
-
movq rBu, _bo(\oState)
|
180
|
-
movq rBi, _be(\oState)
|
181
|
-
.if \lastRound == 0
|
182
|
-
movq rBi, rCe
|
183
|
-
.endif
|
184
|
-
|
185
|
-
// Theta Rho Pi Chi, result g
|
186
|
-
movq _gu(\iState), rBe
|
187
|
-
xorq rDu, rBe
|
188
|
-
movq _ka(\iState), rBi
|
189
|
-
rolq $20, rBe
|
190
|
-
xorq rDa, rBi
|
191
|
-
rolq $3, rBi
|
192
|
-
movq _bo(\iState), rBa
|
193
|
-
movq rBe, rT1
|
194
|
-
orq rBi, rT1
|
195
|
-
xorq rDo, rBa
|
196
|
-
movq _me(\iState), rBo
|
197
|
-
movq _si(\iState), rBu
|
198
|
-
rolq $28, rBa
|
199
|
-
xorq rBa, rT1
|
200
|
-
movq rT1, _ga(\oState)
|
201
|
-
.if \lastRound == 0
|
202
|
-
xorq rT1, rCa
|
203
|
-
.endif
|
204
|
-
|
205
|
-
xorq rDe, rBo
|
206
|
-
rolq $45, rBo
|
207
|
-
movq rBi, rT1
|
208
|
-
andq rBo, rT1
|
209
|
-
xorq rBe, rT1
|
210
|
-
movq rT1, _ge(\oState)
|
211
|
-
.if \lastRound == 0
|
212
|
-
xorq rT1, rCe
|
213
|
-
.endif
|
214
|
-
|
215
|
-
xorq rDi, rBu
|
216
|
-
rolq $61, rBu
|
217
|
-
movq rBu, rT1
|
218
|
-
orq rBa, rT1
|
219
|
-
xorq rBo, rT1
|
220
|
-
movq rT1, _go(\oState)
|
221
|
-
|
222
|
-
andq rBe, rBa
|
223
|
-
xorq rBu, rBa
|
224
|
-
movq rBa, _gu(\oState)
|
225
|
-
notq rBu
|
226
|
-
.if \lastRound == 0
|
227
|
-
xorq rBa, rCu
|
228
|
-
.endif
|
229
|
-
|
230
|
-
orq rBu, rBo
|
231
|
-
xorq rBi, rBo
|
232
|
-
movq rBo, _gi(\oState)
|
233
|
-
|
234
|
-
// Theta Rho Pi Chi, result k
|
235
|
-
movq _be(\iState), rBa
|
236
|
-
movq _gi(\iState), rBe
|
237
|
-
movq _ko(\iState), rBi
|
238
|
-
movq _mu(\iState), rBo
|
239
|
-
movq _sa(\iState), rBu
|
240
|
-
xorq rDi, rBe
|
241
|
-
rolq $6, rBe
|
242
|
-
xorq rDo, rBi
|
243
|
-
rolq $25, rBi
|
244
|
-
movq rBe, rT1
|
245
|
-
orq rBi, rT1
|
246
|
-
xorq rDe, rBa
|
247
|
-
rolq $1, rBa
|
248
|
-
xorq rBa, rT1
|
249
|
-
movq rT1, _ka(\oState)
|
250
|
-
.if \lastRound == 0
|
251
|
-
xorq rT1, rCa
|
252
|
-
.endif
|
253
|
-
|
254
|
-
xorq rDu, rBo
|
255
|
-
rolq $8, rBo
|
256
|
-
movq rBi, rT1
|
257
|
-
andq rBo, rT1
|
258
|
-
xorq rBe, rT1
|
259
|
-
movq rT1, _ke(\oState)
|
260
|
-
.if \lastRound == 0
|
261
|
-
xorq rT1, rCe
|
262
|
-
.endif
|
263
|
-
|
264
|
-
xorq rDa, rBu
|
265
|
-
rolq $18, rBu
|
266
|
-
notq rBo
|
267
|
-
movq rBo, rT1
|
268
|
-
andq rBu, rT1
|
269
|
-
xorq rBi, rT1
|
270
|
-
movq rT1, _ki(\oState)
|
271
|
-
|
272
|
-
movq rBu, rT1
|
273
|
-
orq rBa, rT1
|
274
|
-
xorq rBo, rT1
|
275
|
-
movq rT1, _ko(\oState)
|
276
|
-
|
277
|
-
andq rBe, rBa
|
278
|
-
xorq rBu, rBa
|
279
|
-
movq rBa, _ku(\oState)
|
280
|
-
.if \lastRound == 0
|
281
|
-
xorq rBa, rCu
|
282
|
-
.endif
|
283
|
-
|
284
|
-
// Theta Rho Pi Chi, result m
|
285
|
-
movq _ga(\iState), rBe
|
286
|
-
xorq rDa, rBe
|
287
|
-
movq _ke(\iState), rBi
|
288
|
-
rolq $36, rBe
|
289
|
-
xorq rDe, rBi
|
290
|
-
movq _bu(\iState), rBa
|
291
|
-
rolq $10, rBi
|
292
|
-
movq rBe, rT1
|
293
|
-
movq _mi(\iState), rBo
|
294
|
-
andq rBi, rT1
|
295
|
-
xorq rDu, rBa
|
296
|
-
movq _so(\iState), rBu
|
297
|
-
rolq $27, rBa
|
298
|
-
xorq rBa, rT1
|
299
|
-
movq rT1, _ma(\oState)
|
300
|
-
.if \lastRound == 0
|
301
|
-
xorq rT1, rCa
|
302
|
-
.endif
|
303
|
-
|
304
|
-
xorq rDi, rBo
|
305
|
-
rolq $15, rBo
|
306
|
-
movq rBi, rT1
|
307
|
-
orq rBo, rT1
|
308
|
-
xorq rBe, rT1
|
309
|
-
movq rT1, _me(\oState)
|
310
|
-
.if \lastRound == 0
|
311
|
-
xorq rT1, rCe
|
312
|
-
.endif
|
313
|
-
|
314
|
-
xorq rDo, rBu
|
315
|
-
rolq $56, rBu
|
316
|
-
notq rBo
|
317
|
-
movq rBo, rT1
|
318
|
-
orq rBu, rT1
|
319
|
-
xorq rBi, rT1
|
320
|
-
movq rT1, _mi(\oState)
|
321
|
-
|
322
|
-
orq rBa, rBe
|
323
|
-
xorq rBu, rBe
|
324
|
-
movq rBe, _mu(\oState)
|
325
|
-
|
326
|
-
andq rBa, rBu
|
327
|
-
xorq rBo, rBu
|
328
|
-
movq rBu, _mo(\oState)
|
329
|
-
.if \lastRound == 0
|
330
|
-
xorq rBe, rCu
|
331
|
-
.endif
|
332
|
-
|
333
|
-
// Theta Rho Pi Chi, result s
|
334
|
-
movq _bi(\iState), rBa
|
335
|
-
movq _go(\iState), rBe
|
336
|
-
movq _ku(\iState), rBi
|
337
|
-
xorq rDi, rBa
|
338
|
-
movq _ma(\iState), rBo
|
339
|
-
rolq $62, rBa
|
340
|
-
xorq rDo, rBe
|
341
|
-
movq _se(\iState), rBu
|
342
|
-
rolq $55, rBe
|
343
|
-
|
344
|
-
xorq rDu, rBi
|
345
|
-
movq rBa, rDu
|
346
|
-
xorq rDe, rBu
|
347
|
-
rolq $2, rBu
|
348
|
-
andq rBe, rDu
|
349
|
-
xorq rBu, rDu
|
350
|
-
movq rDu, _su(\oState)
|
351
|
-
|
352
|
-
rolq $39, rBi
|
353
|
-
.if \lastRound == 0
|
354
|
-
xorq rDu, rCu
|
355
|
-
.endif
|
356
|
-
notq rBe
|
357
|
-
xorq rDa, rBo
|
358
|
-
movq rBe, rDa
|
359
|
-
andq rBi, rDa
|
360
|
-
xorq rBa, rDa
|
361
|
-
movq rDa, _sa(\oState)
|
362
|
-
.if \lastRound == 0
|
363
|
-
xorq rDa, rCa
|
364
|
-
.endif
|
365
|
-
|
366
|
-
rolq $41, rBo
|
367
|
-
movq rBi, rDe
|
368
|
-
orq rBo, rDe
|
369
|
-
xorq rBe, rDe
|
370
|
-
movq rDe, _se(\oState)
|
371
|
-
.if \lastRound == 0
|
372
|
-
xorq rDe, rCe
|
373
|
-
.endif
|
374
|
-
|
375
|
-
movq rBo, rDi
|
376
|
-
movq rBu, rDo
|
377
|
-
andq rBu, rDi
|
378
|
-
orq rBa, rDo
|
379
|
-
xorq rBi, rDi
|
380
|
-
xorq rBo, rDo
|
381
|
-
movq rDi, _si(\oState)
|
382
|
-
movq rDo, _so(\oState)
|
383
|
-
|
384
|
-
.endm
|
385
|
-
|
386
|
-
.macro mKeccakPermutation12
|
387
|
-
|
388
|
-
subq $(200), %rsp // 200 = 8*25
|
389
|
-
|
390
|
-
movq _ba(rpState), rCa
|
391
|
-
movq _be(rpState), rCe
|
392
|
-
movq _bu(rpState), rCu
|
393
|
-
|
394
|
-
xorq _ga(rpState), rCa
|
395
|
-
xorq _ge(rpState), rCe
|
396
|
-
xorq _gu(rpState), rCu
|
397
|
-
|
398
|
-
xorq _ka(rpState), rCa
|
399
|
-
xorq _ke(rpState), rCe
|
400
|
-
xorq _ku(rpState), rCu
|
401
|
-
|
402
|
-
xorq _ma(rpState), rCa
|
403
|
-
xorq _me(rpState), rCe
|
404
|
-
xorq _mu(rpState), rCu
|
405
|
-
|
406
|
-
xorq _sa(rpState), rCa
|
407
|
-
xorq _se(rpState), rCe
|
408
|
-
movq _si(rpState), rDi
|
409
|
-
movq _so(rpState), rDo
|
410
|
-
xorq _su(rpState), rCu
|
411
|
-
|
412
|
-
mKeccakRound rpState, rpStack, 0x000000008000808b, 0
|
413
|
-
mKeccakRound rpStack, rpState, 0x800000000000008b, 0
|
414
|
-
mKeccakRound rpState, rpStack, 0x8000000000008089, 0
|
415
|
-
mKeccakRound rpStack, rpState, 0x8000000000008003, 0
|
416
|
-
mKeccakRound rpState, rpStack, 0x8000000000008002, 0
|
417
|
-
mKeccakRound rpStack, rpState, 0x8000000000000080, 0
|
418
|
-
mKeccakRound rpState, rpStack, 0x000000000000800a, 0
|
419
|
-
mKeccakRound rpStack, rpState, 0x800000008000000a, 0
|
420
|
-
mKeccakRound rpState, rpStack, 0x8000000080008081, 0
|
421
|
-
mKeccakRound rpStack, rpState, 0x8000000000008080, 0
|
422
|
-
mKeccakRound rpState, rpStack, 0x0000000080000001, 0
|
423
|
-
mKeccakRound rpStack, rpState, 0x8000000080008008, 1
|
424
|
-
addq $(200), %rsp // 200 = 8*25
|
425
|
-
.endm
|
426
|
-
|
427
|
-
.macro mKeccakPermutation24
|
428
|
-
|
429
|
-
subq $(200), %rsp // 200 = 8*25
|
430
|
-
|
431
|
-
movq _ba(rpState), rCa
|
432
|
-
movq _be(rpState), rCe
|
433
|
-
movq _bu(rpState), rCu
|
434
|
-
|
435
|
-
xorq _ga(rpState), rCa
|
436
|
-
xorq _ge(rpState), rCe
|
437
|
-
xorq _gu(rpState), rCu
|
438
|
-
|
439
|
-
xorq _ka(rpState), rCa
|
440
|
-
xorq _ke(rpState), rCe
|
441
|
-
xorq _ku(rpState), rCu
|
442
|
-
|
443
|
-
xorq _ma(rpState), rCa
|
444
|
-
xorq _me(rpState), rCe
|
445
|
-
xorq _mu(rpState), rCu
|
446
|
-
|
447
|
-
xorq _sa(rpState), rCa
|
448
|
-
xorq _se(rpState), rCe
|
449
|
-
movq _si(rpState), rDi
|
450
|
-
movq _so(rpState), rDo
|
451
|
-
xorq _su(rpState), rCu
|
452
|
-
|
453
|
-
mKeccakRound rpState, rpStack, 0x0000000000000001, 0
|
454
|
-
mKeccakRound rpStack, rpState, 0x0000000000008082, 0
|
455
|
-
mKeccakRound rpState, rpStack, 0x800000000000808a, 0
|
456
|
-
mKeccakRound rpStack, rpState, 0x8000000080008000, 0
|
457
|
-
mKeccakRound rpState, rpStack, 0x000000000000808b, 0
|
458
|
-
mKeccakRound rpStack, rpState, 0x0000000080000001, 0
|
459
|
-
mKeccakRound rpState, rpStack, 0x8000000080008081, 0
|
460
|
-
mKeccakRound rpStack, rpState, 0x8000000000008009, 0
|
461
|
-
mKeccakRound rpState, rpStack, 0x000000000000008a, 0
|
462
|
-
mKeccakRound rpStack, rpState, 0x0000000000000088, 0
|
463
|
-
mKeccakRound rpState, rpStack, 0x0000000080008009, 0
|
464
|
-
mKeccakRound rpStack, rpState, 0x000000008000000a, 0
|
465
|
-
|
466
|
-
mKeccakRound rpState, rpStack, 0x000000008000808b, 0
|
467
|
-
mKeccakRound rpStack, rpState, 0x800000000000008b, 0
|
468
|
-
mKeccakRound rpState, rpStack, 0x8000000000008089, 0
|
469
|
-
mKeccakRound rpStack, rpState, 0x8000000000008003, 0
|
470
|
-
mKeccakRound rpState, rpStack, 0x8000000000008002, 0
|
471
|
-
mKeccakRound rpStack, rpState, 0x8000000000000080, 0
|
472
|
-
mKeccakRound rpState, rpStack, 0x000000000000800a, 0
|
473
|
-
mKeccakRound rpStack, rpState, 0x800000008000000a, 0
|
474
|
-
mKeccakRound rpState, rpStack, 0x8000000080008081, 0
|
475
|
-
mKeccakRound rpStack, rpState, 0x8000000000008080, 0
|
476
|
-
mKeccakRound rpState, rpStack, 0x0000000080000001, 0
|
477
|
-
mKeccakRound rpStack, rpState, 0x8000000080008008, 1
|
478
|
-
addq $(200), %rsp // 200 = 8*25
|
479
|
-
.endm
|
480
|
-
|
481
|
-
.macro mKeccakPermutationInlinable24
|
482
|
-
.if InlinePerm == 1
|
483
|
-
mKeccakPermutation24
|
484
|
-
.else
|
485
|
-
callq _KeccakP1600_Permute_24rounds
|
486
|
-
.endif
|
487
|
-
.endm
|
488
|
-
|
489
|
-
.macro mPushRegs
|
490
|
-
pushq %rbx
|
491
|
-
pushq %rbp
|
492
|
-
pushq %r12
|
493
|
-
pushq %r13
|
494
|
-
pushq %r14
|
495
|
-
pushq %r15
|
496
|
-
.endm
|
497
|
-
|
498
|
-
.macro mPopRegs
|
499
|
-
popq %r15
|
500
|
-
popq %r14
|
501
|
-
popq %r13
|
502
|
-
popq %r12
|
503
|
-
popq %rbp
|
504
|
-
popq %rbx
|
505
|
-
.endm
|
506
|
-
|
507
|
-
.macro mXor128 input, output, offset
|
508
|
-
movdqu \offset(\input), %xmm0
|
509
|
-
movdqu \offset(\output), %xmm1
|
510
|
-
pxor %xmm1, %xmm0
|
511
|
-
movdqu %xmm0, \offset(\output)
|
512
|
-
.endm
|
513
|
-
|
514
|
-
.macro mXor256 input, output, offset
|
515
|
-
movdqu \offset(\input), %xmm0
|
516
|
-
movdqu \offset(\output), %xmm1
|
517
|
-
pxor %xmm1, %xmm0
|
518
|
-
movdqu %xmm0, \offset(\output)
|
519
|
-
movdqu \offset+16(\input), %xmm0
|
520
|
-
movdqu \offset+16(\output), %xmm1
|
521
|
-
pxor %xmm1, %xmm0
|
522
|
-
movdqu %xmm0, \offset+16(\output)
|
523
|
-
.endm
|
524
|
-
|
525
|
-
.macro mXor512 input, output, offset
|
526
|
-
movdqu \offset(\input), %xmm0
|
527
|
-
movdqu \offset(\output), %xmm1
|
528
|
-
pxor %xmm1, %xmm0
|
529
|
-
movdqu %xmm0, \offset(\output)
|
530
|
-
movdqu \offset+16(\input), %xmm0
|
531
|
-
movdqu \offset+16(\output), %xmm1
|
532
|
-
pxor %xmm1, %xmm0
|
533
|
-
movdqu %xmm0, \offset+16(\output)
|
534
|
-
movdqu \offset+32(\input), %xmm0
|
535
|
-
movdqu \offset+32(\output), %xmm1
|
536
|
-
pxor %xmm1, %xmm0
|
537
|
-
movdqu %xmm0, \offset+32(\output)
|
538
|
-
movdqu \offset+48(\input), %xmm0
|
539
|
-
movdqu \offset+48(\output), %xmm1
|
540
|
-
pxor %xmm1, %xmm0
|
541
|
-
movdqu %xmm0, \offset+48(\output)
|
542
|
-
.endm
|
543
|
-
|
544
|
-
//----------------------------------------------------------------------------
|
545
|
-
//
|
546
|
-
// void KeccakP1600_StaticInitialize( void )
|
547
|
-
//
|
548
|
-
.align 8
|
549
|
-
.globl _KeccakP1600_StaticInitialize
|
550
|
-
_KeccakP1600_StaticInitialize:
|
551
|
-
retq
|
552
|
-
|
553
|
-
//----------------------------------------------------------------------------
|
554
|
-
//
|
555
|
-
// void KeccakP1600_Initialize(void *state)
|
556
|
-
//
|
557
|
-
.align 8
|
558
|
-
.globl _KeccakP1600_Initialize
|
559
|
-
_KeccakP1600_Initialize:
|
560
|
-
xorq %rax, %rax
|
561
|
-
xorq %rcx, %rcx
|
562
|
-
notq %rcx
|
563
|
-
pxor %xmm0, %xmm0
|
564
|
-
movq %rax, _ba(arg1)
|
565
|
-
movq %rcx, _be(arg1)
|
566
|
-
movq %rcx, _bi(arg1)
|
567
|
-
movq %rax, _bo(arg1)
|
568
|
-
movdqu %xmm0, _bu(arg1)
|
569
|
-
movdqu %xmm0, _ge(arg1)
|
570
|
-
movq %rcx, _go(arg1)
|
571
|
-
movq %rax, _gu(arg1)
|
572
|
-
movdqu %xmm0, _ka(arg1)
|
573
|
-
movq %rcx, _ki(arg1)
|
574
|
-
movq %rax, _ko(arg1)
|
575
|
-
movdqu %xmm0, _ku(arg1)
|
576
|
-
movq %rax, _me(arg1)
|
577
|
-
movq %rcx, _mi(arg1)
|
578
|
-
movdqu %xmm0, _mo(arg1)
|
579
|
-
movq %rcx, _sa(arg1)
|
580
|
-
movq %rax, _se(arg1)
|
581
|
-
movdqu %xmm0, _si(arg1)
|
582
|
-
movq %rax, _su(arg1)
|
583
|
-
retq
|
584
|
-
|
585
|
-
//----------------------------------------------------------------------------
|
586
|
-
//
|
587
|
-
// void KeccakP1600_AddByte(void *state, unsigned char data, unsigned int offset)
|
588
|
-
//
|
589
|
-
.align 8
|
590
|
-
.globl _KeccakP1600_AddByte
|
591
|
-
_KeccakP1600_AddByte:
|
592
|
-
addq arg3, arg1
|
593
|
-
mov arg2, %rax
|
594
|
-
xorb %al, (arg1)
|
595
|
-
retq
|
596
|
-
|
597
|
-
//----------------------------------------------------------------------------
|
598
|
-
//
|
599
|
-
// void KeccakP1600_AddBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
600
|
-
//
|
601
|
-
.align 8
|
602
|
-
.globl _KeccakP1600_AddBytes
|
603
|
-
_KeccakP1600_AddBytes:
|
604
|
-
pushq rT1e
|
605
|
-
pushq rT1i
|
606
|
-
pushq rT1o
|
607
|
-
addq arg3, arg1
|
608
|
-
testq $0xF8, arg4
|
609
|
-
jz KeccakP1600_AddBytes_Bytes
|
610
|
-
movq arg4, arg6
|
611
|
-
shrq $3, arg6
|
612
|
-
testq $16, arg6
|
613
|
-
jz KeccakP1600_AddBytes_8Lanes
|
614
|
-
mXor512 arg2, arg1, 0
|
615
|
-
mXor512 arg2, arg1, 64
|
616
|
-
addq $128, arg2
|
617
|
-
addq $128, arg1
|
618
|
-
KeccakP1600_AddBytes_8Lanes:
|
619
|
-
testq $8, arg6
|
620
|
-
jz KeccakP1600_AddBytes_4Lanes
|
621
|
-
mXor512 arg2, arg1, 0
|
622
|
-
addq $64, arg2
|
623
|
-
addq $64, arg1
|
624
|
-
KeccakP1600_AddBytes_4Lanes:
|
625
|
-
testq $4, arg6
|
626
|
-
jz KeccakP1600_AddBytes_2Lanes
|
627
|
-
mXor256 arg2, arg1, 0
|
628
|
-
addq $32, arg2
|
629
|
-
addq $32, arg1
|
630
|
-
KeccakP1600_AddBytes_2Lanes:
|
631
|
-
testq $2, arg6
|
632
|
-
jz KeccakP1600_AddBytes_1Lane
|
633
|
-
mXor128 arg2, arg1, 0
|
634
|
-
addq $16, arg2
|
635
|
-
addq $16, arg1
|
636
|
-
KeccakP1600_AddBytes_1Lane:
|
637
|
-
testq $1, arg6
|
638
|
-
jz KeccakP1600_AddBytes_Bytes
|
639
|
-
movq (arg2), rT1
|
640
|
-
xorq rT1, (arg1)
|
641
|
-
addq $8, arg2
|
642
|
-
addq $8, arg1
|
643
|
-
KeccakP1600_AddBytes_Bytes:
|
644
|
-
andq $7, arg4
|
645
|
-
jz KeccakP1600_AddBytes_Exit
|
646
|
-
KeccakP1600_AddBytes_BytesLoop:
|
647
|
-
movb (arg2), %al
|
648
|
-
xorb %al, (arg1)
|
649
|
-
addq $1, arg2
|
650
|
-
addq $1, arg1
|
651
|
-
subq $1, arg4
|
652
|
-
jnz KeccakP1600_AddBytes_BytesLoop
|
653
|
-
KeccakP1600_AddBytes_Exit:
|
654
|
-
popq rT1o
|
655
|
-
popq rT1i
|
656
|
-
popq rT1e
|
657
|
-
retq
|
658
|
-
|
659
|
-
|
660
|
-
KeccakLaneComplementTable:
|
661
|
-
.quad 0
|
662
|
-
.quad 0xFFFFFFFFFFFFFFFF // 1 be
|
663
|
-
.quad 0xFFFFFFFFFFFFFFFF // 2 bi
|
664
|
-
.quad 0
|
665
|
-
.quad 0
|
666
|
-
|
667
|
-
.quad 0
|
668
|
-
.quad 0
|
669
|
-
.quad 0
|
670
|
-
.quad 0xFFFFFFFFFFFFFFFF // 8 go
|
671
|
-
.quad 0
|
672
|
-
|
673
|
-
.quad 0
|
674
|
-
.quad 0
|
675
|
-
.quad 0xFFFFFFFFFFFFFFFF // 12 ki
|
676
|
-
.quad 0
|
677
|
-
.quad 0
|
678
|
-
|
679
|
-
.quad 0
|
680
|
-
.quad 0
|
681
|
-
.quad 0xFFFFFFFFFFFFFFFF // 17 mi
|
682
|
-
.quad 0
|
683
|
-
.quad 0
|
684
|
-
|
685
|
-
.quad 0xFFFFFFFFFFFFFFFF // 20 sa
|
686
|
-
.quad 0
|
687
|
-
.quad 0
|
688
|
-
.quad 0
|
689
|
-
.quad 0
|
690
|
-
|
691
|
-
//----------------------------------------------------------------------------
|
692
|
-
//
|
693
|
-
// void KeccakP1600_OverwriteBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
694
|
-
//
|
695
|
-
.align 8
|
696
|
-
.globl _KeccakP1600_OverwriteBytes
|
697
|
-
_KeccakP1600_OverwriteBytes:
|
698
|
-
addq arg3, arg1
|
699
|
-
leaq KeccakLaneComplementTable(%rip), arg5
|
700
|
-
addq arg3, arg5
|
701
|
-
subq $8, arg4
|
702
|
-
jc KeccakP1600_OverwriteBytes_Bytes
|
703
|
-
KeccakP1600_OverwriteBytes_LanesLoop:
|
704
|
-
movq (arg2), rT1
|
705
|
-
xorq (arg5), rT1
|
706
|
-
movq rT1, (arg1)
|
707
|
-
addq $8, arg2
|
708
|
-
addq $8, arg5
|
709
|
-
addq $8, arg1
|
710
|
-
subq $8, arg4
|
711
|
-
jnc KeccakP1600_OverwriteBytes_LanesLoop
|
712
|
-
KeccakP1600_OverwriteBytes_Bytes:
|
713
|
-
addq $8, arg4
|
714
|
-
jz KeccakP1600_OverwriteBytes_Exit
|
715
|
-
KeccakP1600_OverwriteBytes_BytesLoop:
|
716
|
-
movb (arg2), %al
|
717
|
-
xorb (arg5), %al
|
718
|
-
movb %al, (arg1)
|
719
|
-
addq $1, arg2
|
720
|
-
addq $1, arg5
|
721
|
-
addq $1, arg1
|
722
|
-
subq $1, arg4
|
723
|
-
jnz KeccakP1600_OverwriteBytes_BytesLoop
|
724
|
-
KeccakP1600_OverwriteBytes_Exit:
|
725
|
-
retq
|
726
|
-
|
727
|
-
//----------------------------------------------------------------------------
|
728
|
-
//
|
729
|
-
// void KeccakP1600_OverwriteWithZeroes(void *state, unsigned int byteCount)
|
730
|
-
//
|
731
|
-
.align 8
|
732
|
-
.globl _KeccakP1600_OverwriteWithZeroes
|
733
|
-
_KeccakP1600_OverwriteWithZeroes:
|
734
|
-
leaq KeccakLaneComplementTable(%rip), arg5
|
735
|
-
subq $8, arg2
|
736
|
-
jc KeccakP1600_OverwriteWithZeroes_Bytes
|
737
|
-
KeccakP1600_OverwriteWithZeroes_LanesLoop:
|
738
|
-
movq $0, rT1
|
739
|
-
xorq (arg5), rT1
|
740
|
-
movq rT1, (arg1)
|
741
|
-
addq $8, arg5
|
742
|
-
addq $8, arg1
|
743
|
-
subq $8, arg2
|
744
|
-
jnc KeccakP1600_OverwriteWithZeroes_LanesLoop
|
745
|
-
KeccakP1600_OverwriteWithZeroes_Bytes:
|
746
|
-
addq $8, arg2
|
747
|
-
jz KeccakP1600_OverwriteWithZeroes_Exit
|
748
|
-
KeccakP1600_OverwriteWithZeroes_BytesLoop:
|
749
|
-
movb $0, %al
|
750
|
-
xorb (arg5), %al
|
751
|
-
movb %al, (arg1)
|
752
|
-
addq $1, arg5
|
753
|
-
addq $1, arg1
|
754
|
-
subq $1, arg2
|
755
|
-
jnz KeccakP1600_OverwriteWithZeroes_BytesLoop
|
756
|
-
KeccakP1600_OverwriteWithZeroes_Exit:
|
757
|
-
retq
|
758
|
-
|
759
|
-
//----------------------------------------------------------------------------
|
760
|
-
//
|
761
|
-
// void KeccakP1600_ExtractBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
762
|
-
//
|
763
|
-
.align 8
|
764
|
-
.globl _KeccakP1600_ExtractBytes
|
765
|
-
_KeccakP1600_ExtractBytes:
|
766
|
-
addq arg3, arg1
|
767
|
-
leaq KeccakLaneComplementTable(%rip), arg5
|
768
|
-
addq arg3, arg5
|
769
|
-
subq $8, arg4
|
770
|
-
jc KeccakP1600_ExtractBytes_Bytes
|
771
|
-
KeccakP1600_ExtractBytes_LanesLoop:
|
772
|
-
movq (arg1), rT1
|
773
|
-
xorq (arg5), rT1
|
774
|
-
movq rT1, (arg2)
|
775
|
-
addq $8, arg2
|
776
|
-
addq $8, arg5
|
777
|
-
addq $8, arg1
|
778
|
-
subq $8, arg4
|
779
|
-
jnc KeccakP1600_ExtractBytes_LanesLoop
|
780
|
-
KeccakP1600_ExtractBytes_Bytes:
|
781
|
-
addq $8, arg4
|
782
|
-
jz KeccakP1600_ExtractBytes_Exit
|
783
|
-
KeccakP1600_ExtractBytes_BytesLoop:
|
784
|
-
movb (arg1), %al
|
785
|
-
xorb (arg5), %al
|
786
|
-
movb %al, (arg2)
|
787
|
-
addq $1, arg2
|
788
|
-
addq $1, arg5
|
789
|
-
addq $1, arg1
|
790
|
-
subq $1, arg4
|
791
|
-
jnz KeccakP1600_ExtractBytes_BytesLoop
|
792
|
-
KeccakP1600_ExtractBytes_Exit:
|
793
|
-
retq
|
794
|
-
|
795
|
-
//----------------------------------------------------------------------------
|
796
|
-
//
|
797
|
-
// void KeccakP1600_ExtractAndAddBytes(void *state, const unsigned char *input, unsigned char *output, unsigned int offset, unsigned int length)
|
798
|
-
//
|
799
|
-
.align 8
|
800
|
-
.globl _KeccakP1600_ExtractAndAddBytes
|
801
|
-
_KeccakP1600_ExtractAndAddBytes:
|
802
|
-
addq arg4, arg1
|
803
|
-
leaq KeccakLaneComplementTable(%rip), arg6
|
804
|
-
addq arg4, arg6
|
805
|
-
subq $8, arg5
|
806
|
-
jc KeccakP1600_ExtractAndAddBytes_Bytes
|
807
|
-
KeccakP1600_ExtractAndAddBytes_LanesLoop:
|
808
|
-
movq (arg1), rT1
|
809
|
-
xorq (arg6), rT1
|
810
|
-
xorq (arg2), rT1
|
811
|
-
movq rT1, (arg3)
|
812
|
-
addq $8, arg2
|
813
|
-
addq $8, arg3
|
814
|
-
addq $8, arg6
|
815
|
-
addq $8, arg1
|
816
|
-
subq $8, arg5
|
817
|
-
jnc KeccakP1600_ExtractAndAddBytes_LanesLoop
|
818
|
-
KeccakP1600_ExtractAndAddBytes_Bytes:
|
819
|
-
addq $8, arg5
|
820
|
-
jz KeccakP1600_ExtractAndAddBytes_Exit
|
821
|
-
KeccakP1600_ExtractAndAddBytes_BytesLoop:
|
822
|
-
movb (arg1), %al
|
823
|
-
xorb (arg6), %al
|
824
|
-
xorb (arg2), %al
|
825
|
-
movb %al, (arg3)
|
826
|
-
addq $1, arg2
|
827
|
-
addq $1, arg3
|
828
|
-
addq $1, arg6
|
829
|
-
addq $1, arg1
|
830
|
-
subq $1, arg5
|
831
|
-
jnz KeccakP1600_ExtractAndAddBytes_BytesLoop
|
832
|
-
KeccakP1600_ExtractAndAddBytes_Exit:
|
833
|
-
retq
|
834
|
-
|
835
|
-
//----------------------------------------------------------------------------
|
836
|
-
//
|
837
|
-
// void KeccakP1600_Permute_Nrounds( void *state, unsigned int nrounds )
|
838
|
-
//
|
839
|
-
.align 8
|
840
|
-
.globl _KeccakP1600_Permute_Nrounds
|
841
|
-
_KeccakP1600_Permute_Nrounds:
|
842
|
-
mPushRegs
|
843
|
-
subq $8*25, %rsp
|
844
|
-
movq arg2, rT1
|
845
|
-
|
846
|
-
movq _ba(rpState), rCa
|
847
|
-
movq _be(rpState), rCe
|
848
|
-
movq _bu(rpState), rCu
|
849
|
-
|
850
|
-
xorq _ga(rpState), rCa
|
851
|
-
xorq _ge(rpState), rCe
|
852
|
-
xorq _gu(rpState), rCu
|
853
|
-
|
854
|
-
xorq _ka(rpState), rCa
|
855
|
-
xorq _ke(rpState), rCe
|
856
|
-
xorq _ku(rpState), rCu
|
857
|
-
|
858
|
-
xorq _ma(rpState), rCa
|
859
|
-
xorq _me(rpState), rCe
|
860
|
-
xorq _mu(rpState), rCu
|
861
|
-
|
862
|
-
xorq _sa(rpState), rCa
|
863
|
-
xorq _se(rpState), rCe
|
864
|
-
movq _si(rpState), rDi
|
865
|
-
movq _so(rpState), rDo
|
866
|
-
xorq _su(rpState), rCu
|
867
|
-
|
868
|
-
testq $1, rT1
|
869
|
-
jz KeccakP1600_Permute_Nrounds_Dispatch
|
870
|
-
movq _ba(rpState), rT2a // copy to stack
|
871
|
-
movq rT2a, _ba(rpStack)
|
872
|
-
movq _be(rpState), rT2a
|
873
|
-
movq rT2a, _be(rpStack)
|
874
|
-
movq _bi(rpState), rT2a
|
875
|
-
movq rT2a, _bi(rpStack)
|
876
|
-
movq _bo(rpState), rT2a
|
877
|
-
movq rT2a, _bo(rpStack)
|
878
|
-
movq _bu(rpState), rT2a
|
879
|
-
movq rT2a, _bu(rpStack)
|
880
|
-
movq _ga(rpState), rT2a
|
881
|
-
movq rT2a, _ga(rpStack)
|
882
|
-
movq _ge(rpState), rT2a
|
883
|
-
movq rT2a, _ge(rpStack)
|
884
|
-
movq _gi(rpState), rT2a
|
885
|
-
movq rT2a, _gi(rpStack)
|
886
|
-
movq _go(rpState), rT2a
|
887
|
-
movq rT2a, _go(rpStack)
|
888
|
-
movq _gu(rpState), rT2a
|
889
|
-
movq rT2a, _gu(rpStack)
|
890
|
-
movq _ka(rpState), rT2a
|
891
|
-
movq rT2a, _ka(rpStack)
|
892
|
-
movq _ke(rpState), rT2a
|
893
|
-
movq rT2a, _ke(rpStack)
|
894
|
-
movq _ki(rpState), rT2a
|
895
|
-
movq rT2a, _ki(rpStack)
|
896
|
-
movq _ko(rpState), rT2a
|
897
|
-
movq rT2a, _ko(rpStack)
|
898
|
-
movq _ku(rpState), rT2a
|
899
|
-
movq rT2a, _ku(rpStack)
|
900
|
-
movq _ma(rpState), rT2a
|
901
|
-
movq rT2a, _ma(rpStack)
|
902
|
-
movq _me(rpState), rT2a
|
903
|
-
movq rT2a, _me(rpStack)
|
904
|
-
movq _mi(rpState), rT2a
|
905
|
-
movq rT2a, _mi(rpStack)
|
906
|
-
movq _mo(rpState), rT2a
|
907
|
-
movq rT2a, _mo(rpStack)
|
908
|
-
movq _mu(rpState), rT2a
|
909
|
-
movq rT2a, _mu(rpStack)
|
910
|
-
movq _sa(rpState), rT2a
|
911
|
-
movq rT2a, _sa(rpStack)
|
912
|
-
movq _se(rpState), rT2a
|
913
|
-
movq rT2a, _se(rpStack)
|
914
|
-
movq _si(rpState), rT2a
|
915
|
-
movq rT2a, _si(rpStack)
|
916
|
-
movq _so(rpState), rT2a
|
917
|
-
movq rT2a, _so(rpStack)
|
918
|
-
movq _su(rpState), rT2a
|
919
|
-
movq rT2a, _su(rpStack)
|
920
|
-
KeccakP1600_Permute_Nrounds_Dispatch:
|
921
|
-
shlq $3, rT1
|
922
|
-
lea KeccakP1600_Permute_NroundsTable(%rip), %rbx
|
923
|
-
jmp *-8(%rbx, %rax)
|
924
|
-
|
925
|
-
KeccakP1600_Permute_Nrounds24:
|
926
|
-
mKeccakRound rpState, rpStack, 0x0000000000000001, 0
|
927
|
-
KeccakP1600_Permute_Nrounds23:
|
928
|
-
mKeccakRound rpStack, rpState, 0x0000000000008082, 0
|
929
|
-
KeccakP1600_Permute_Nrounds22:
|
930
|
-
mKeccakRound rpState, rpStack, 0x800000000000808a, 0
|
931
|
-
KeccakP1600_Permute_Nrounds21:
|
932
|
-
mKeccakRound rpStack, rpState, 0x8000000080008000, 0
|
933
|
-
KeccakP1600_Permute_Nrounds20:
|
934
|
-
mKeccakRound rpState, rpStack, 0x000000000000808b, 0
|
935
|
-
KeccakP1600_Permute_Nrounds19:
|
936
|
-
mKeccakRound rpStack, rpState, 0x0000000080000001, 0
|
937
|
-
KeccakP1600_Permute_Nrounds18:
|
938
|
-
mKeccakRound rpState, rpStack, 0x8000000080008081, 0
|
939
|
-
KeccakP1600_Permute_Nrounds17:
|
940
|
-
mKeccakRound rpStack, rpState, 0x8000000000008009, 0
|
941
|
-
KeccakP1600_Permute_Nrounds16:
|
942
|
-
mKeccakRound rpState, rpStack, 0x000000000000008a, 0
|
943
|
-
KeccakP1600_Permute_Nrounds15:
|
944
|
-
mKeccakRound rpStack, rpState, 0x0000000000000088, 0
|
945
|
-
KeccakP1600_Permute_Nrounds14:
|
946
|
-
mKeccakRound rpState, rpStack, 0x0000000080008009, 0
|
947
|
-
KeccakP1600_Permute_Nrounds13:
|
948
|
-
mKeccakRound rpStack, rpState, 0x000000008000000a, 0
|
949
|
-
KeccakP1600_Permute_Nrounds12:
|
950
|
-
mKeccakRound rpState, rpStack, 0x000000008000808b, 0
|
951
|
-
KeccakP1600_Permute_Nrounds11:
|
952
|
-
mKeccakRound rpStack, rpState, 0x800000000000008b, 0
|
953
|
-
KeccakP1600_Permute_Nrounds10:
|
954
|
-
mKeccakRound rpState, rpStack, 0x8000000000008089, 0
|
955
|
-
KeccakP1600_Permute_Nrounds9:
|
956
|
-
mKeccakRound rpStack, rpState, 0x8000000000008003, 0
|
957
|
-
KeccakP1600_Permute_Nrounds8:
|
958
|
-
mKeccakRound rpState, rpStack, 0x8000000000008002, 0
|
959
|
-
KeccakP1600_Permute_Nrounds7:
|
960
|
-
mKeccakRound rpStack, rpState, 0x8000000000000080, 0
|
961
|
-
KeccakP1600_Permute_Nrounds6:
|
962
|
-
mKeccakRound rpState, rpStack, 0x000000000000800a, 0
|
963
|
-
KeccakP1600_Permute_Nrounds5:
|
964
|
-
mKeccakRound rpStack, rpState, 0x800000008000000a, 0
|
965
|
-
KeccakP1600_Permute_Nrounds4:
|
966
|
-
mKeccakRound rpState, rpStack, 0x8000000080008081, 0
|
967
|
-
KeccakP1600_Permute_Nrounds3:
|
968
|
-
mKeccakRound rpStack, rpState, 0x8000000000008080, 0
|
969
|
-
KeccakP1600_Permute_Nrounds2:
|
970
|
-
mKeccakRound rpState, rpStack, 0x0000000080000001, 0
|
971
|
-
KeccakP1600_Permute_Nrounds1:
|
972
|
-
mKeccakRound rpStack, rpState, 0x8000000080008008, 1
|
973
|
-
addq $8*25, %rsp
|
974
|
-
mPopRegs
|
975
|
-
retq
|
976
|
-
|
977
|
-
KeccakP1600_Permute_NroundsTable:
|
978
|
-
.quad KeccakP1600_Permute_Nrounds1
|
979
|
-
.quad KeccakP1600_Permute_Nrounds2
|
980
|
-
.quad KeccakP1600_Permute_Nrounds3
|
981
|
-
.quad KeccakP1600_Permute_Nrounds4
|
982
|
-
.quad KeccakP1600_Permute_Nrounds5
|
983
|
-
.quad KeccakP1600_Permute_Nrounds6
|
984
|
-
.quad KeccakP1600_Permute_Nrounds7
|
985
|
-
.quad KeccakP1600_Permute_Nrounds8
|
986
|
-
.quad KeccakP1600_Permute_Nrounds9
|
987
|
-
.quad KeccakP1600_Permute_Nrounds10
|
988
|
-
.quad KeccakP1600_Permute_Nrounds11
|
989
|
-
.quad KeccakP1600_Permute_Nrounds12
|
990
|
-
.quad KeccakP1600_Permute_Nrounds13
|
991
|
-
.quad KeccakP1600_Permute_Nrounds14
|
992
|
-
.quad KeccakP1600_Permute_Nrounds15
|
993
|
-
.quad KeccakP1600_Permute_Nrounds16
|
994
|
-
.quad KeccakP1600_Permute_Nrounds17
|
995
|
-
.quad KeccakP1600_Permute_Nrounds18
|
996
|
-
.quad KeccakP1600_Permute_Nrounds19
|
997
|
-
.quad KeccakP1600_Permute_Nrounds20
|
998
|
-
.quad KeccakP1600_Permute_Nrounds21
|
999
|
-
.quad KeccakP1600_Permute_Nrounds22
|
1000
|
-
.quad KeccakP1600_Permute_Nrounds23
|
1001
|
-
.quad KeccakP1600_Permute_Nrounds24
|
1002
|
-
|
1003
|
-
//----------------------------------------------------------------------------
|
1004
|
-
//
|
1005
|
-
// void KeccakP1600_Permute_12rounds( void *state )
|
1006
|
-
//
|
1007
|
-
.align 8
|
1008
|
-
.globl _KeccakP1600_Permute_12rounds
|
1009
|
-
_KeccakP1600_Permute_12rounds:
|
1010
|
-
mPushRegs
|
1011
|
-
mKeccakPermutation12
|
1012
|
-
mPopRegs
|
1013
|
-
retq
|
1014
|
-
|
1015
|
-
//----------------------------------------------------------------------------
|
1016
|
-
//
|
1017
|
-
// void KeccakP1600_Permute_24rounds( void *state )
|
1018
|
-
//
|
1019
|
-
.align 8
|
1020
|
-
.globl _KeccakP1600_Permute_24rounds
|
1021
|
-
_KeccakP1600_Permute_24rounds:
|
1022
|
-
mPushRegs
|
1023
|
-
mKeccakPermutation24
|
1024
|
-
mPopRegs
|
1025
|
-
retq
|
1026
|
-
|
1027
|
-
//----------------------------------------------------------------------------
|
1028
|
-
//
|
1029
|
-
// size_t KeccakF1600_FastLoop_Absorb( void *state, unsigned int laneCount, unsigned char *data,
|
1030
|
-
// size_t dataByteLen, unsigned char trailingBits )
|
1031
|
-
//
|
1032
|
-
.align 8
|
1033
|
-
.globl _KeccakF1600_FastLoop_Absorb
|
1034
|
-
_KeccakF1600_FastLoop_Absorb:
|
1035
|
-
mPushRegs
|
1036
|
-
pushq arg3 // save initial data pointer
|
1037
|
-
pushq arg5 // save trailingBits
|
1038
|
-
shrq $3, arg4 // nbrLanes = dataByteLen / SnP_laneLengthInBytes
|
1039
|
-
subq arg2, arg4 // if (nbrLanes >= laneCount)
|
1040
|
-
jc KeccakF1600_FastLoop_Absorb_Exit
|
1041
|
-
cmpq $21, arg2
|
1042
|
-
jnz KeccakF1600_FastLoop_Absorb_VariableLaneCountLoop
|
1043
|
-
KeccakF1600_FastLoop_Absorb_Loop21: // Fixed laneCount = 21 (rate = 1344, capacity = 256)
|
1044
|
-
movq _ba(arg3), rT1a
|
1045
|
-
movq _be(arg3), rT1e
|
1046
|
-
movq _bi(arg3), rT1i
|
1047
|
-
movq _bo(arg3), rT1o
|
1048
|
-
movq _bu(arg3), rT1u
|
1049
|
-
movq _ga(arg3), rT2a
|
1050
|
-
movq _ge(arg3), rT2e
|
1051
|
-
movq _gi(arg3), rT2i
|
1052
|
-
movq _go(arg3), rT2o
|
1053
|
-
movq _gu(arg3), rT2u
|
1054
|
-
xorq rT1a, _ba(arg1)
|
1055
|
-
xorq rT1e, _be(arg1)
|
1056
|
-
xorq rT1i, _bi(arg1)
|
1057
|
-
xorq rT1o, _bo(arg1)
|
1058
|
-
xorq rT1u, _bu(arg1)
|
1059
|
-
xorq rT2a, _ga(arg1)
|
1060
|
-
xorq rT2e, _ge(arg1)
|
1061
|
-
xorq rT2i, _gi(arg1)
|
1062
|
-
xorq rT2o, _go(arg1)
|
1063
|
-
xorq rT2u, _gu(arg1)
|
1064
|
-
movq _ka(arg3), rT1a
|
1065
|
-
movq _ke(arg3), rT1e
|
1066
|
-
movq _ki(arg3), rT1i
|
1067
|
-
movq _ko(arg3), rT1o
|
1068
|
-
movq _ku(arg3), rT1u
|
1069
|
-
movq _ma(arg3), rT2a
|
1070
|
-
movq _me(arg3), rT2e
|
1071
|
-
movq _mi(arg3), rT2i
|
1072
|
-
movq _mo(arg3), rT2o
|
1073
|
-
movq _mu(arg3), rT2u
|
1074
|
-
xorq rT1a, _ka(arg1)
|
1075
|
-
xorq rT1e, _ke(arg1)
|
1076
|
-
xorq rT1i, _ki(arg1)
|
1077
|
-
xorq rT1o, _ko(arg1)
|
1078
|
-
xorq rT1u, _ku(arg1)
|
1079
|
-
movq _sa(arg3), rT1a
|
1080
|
-
movq (%rsp), rT1e // xor trailingBits
|
1081
|
-
xorq rT2a, _ma(arg1)
|
1082
|
-
xorq rT2e, _me(arg1)
|
1083
|
-
xorq rT2i, _mi(arg1)
|
1084
|
-
addq $_se, arg3
|
1085
|
-
xorq rT2o, _mo(arg1)
|
1086
|
-
xorq rT2u, _mu(arg1)
|
1087
|
-
xorq rT1a, _sa(arg1)
|
1088
|
-
xorq rT1e, _se(arg1)
|
1089
|
-
pushq arg3
|
1090
|
-
pushq arg4
|
1091
|
-
mKeccakPermutationInlinable24
|
1092
|
-
popq arg4
|
1093
|
-
popq arg3
|
1094
|
-
subq $21, arg4 // while (nbrLanes >= 21)
|
1095
|
-
jnc KeccakF1600_FastLoop_Absorb_Loop21
|
1096
|
-
KeccakF1600_FastLoop_Absorb_Exit:
|
1097
|
-
addq $8, %rsp // free trailingBits
|
1098
|
-
popq rT1a // restore initial data pointer
|
1099
|
-
subq rT1a, arg3 // processed = data pointer - initial data pointer
|
1100
|
-
movq arg3, rT1a
|
1101
|
-
mPopRegs
|
1102
|
-
retq
|
1103
|
-
KeccakF1600_FastLoop_Absorb_VariableLaneCountLoop:
|
1104
|
-
pushq arg4
|
1105
|
-
pushq arg2
|
1106
|
-
pushq arg1
|
1107
|
-
movq arg2, arg4 // prepare xor call: length (in bytes)
|
1108
|
-
shlq $3, arg4
|
1109
|
-
movq arg3, arg2 // data pointer
|
1110
|
-
xorq arg3, arg3 // offset = 0
|
1111
|
-
callq _KeccakP1600_AddBytes // (void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
1112
|
-
movq arg2, arg3 // updated data pointer
|
1113
|
-
movq 24(%rsp), rT1a // xor trailingBits
|
1114
|
-
xorq rT1a, (arg1)
|
1115
|
-
popq arg1
|
1116
|
-
pushq arg3
|
1117
|
-
callq _KeccakP1600_Permute_24rounds
|
1118
|
-
popq arg3
|
1119
|
-
popq arg2
|
1120
|
-
popq arg4
|
1121
|
-
subq arg2, arg4 // while (nbrLanes >= 21)
|
1122
|
-
jnc KeccakF1600_FastLoop_Absorb_VariableLaneCountLoop
|
1123
|
-
jmp KeccakF1600_FastLoop_Absorb_Exit
|
1124
|
-
|