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
@@ -1,823 +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: These functions work only on little endian CPU with ARMv7A + NEON architecture
|
26
|
-
; WARNING: State must be 256 bit (32 bytes) aligned, best is 64-byte (cache alignment).
|
27
|
-
; INFO: Tested on Cortex-A8 (BeagleBone Black), using gcc.
|
28
|
-
|
29
|
-
PRESERVE8
|
30
|
-
AREA |.text|, CODE, READONLY
|
31
|
-
|
32
|
-
; conditional assembly settings
|
33
|
-
LoopUnroll equ 1 ; possible values 1, 2, 4, 6, 12
|
34
|
-
|
35
|
-
; offsets in state
|
36
|
-
_ba equ 0*8
|
37
|
-
_be equ 1*8
|
38
|
-
_bi equ 2*8
|
39
|
-
_bo equ 3*8
|
40
|
-
_bu equ 4*8
|
41
|
-
_ga equ 5*8
|
42
|
-
_ge equ 6*8
|
43
|
-
_gi equ 7*8
|
44
|
-
_go equ 8*8
|
45
|
-
_gu equ 9*8
|
46
|
-
_ka equ 10*8
|
47
|
-
_ke equ 11*8
|
48
|
-
_ki equ 12*8
|
49
|
-
_ko equ 13*8
|
50
|
-
_ku equ 14*8
|
51
|
-
_ma equ 15*8
|
52
|
-
_me equ 16*8
|
53
|
-
_mi equ 17*8
|
54
|
-
_mo equ 18*8
|
55
|
-
_mu equ 19*8
|
56
|
-
_sa equ 20*8
|
57
|
-
_se equ 21*8
|
58
|
-
_si equ 22*8
|
59
|
-
_so equ 23*8
|
60
|
-
_su equ 24*8
|
61
|
-
|
62
|
-
; macros
|
63
|
-
|
64
|
-
MACRO
|
65
|
-
LoadState
|
66
|
-
vld1.64 d0, [r0:64]!
|
67
|
-
vld1.64 d2, [r0:64]!
|
68
|
-
vld1.64 d4, [r0:64]!
|
69
|
-
vld1.64 d6, [r0:64]!
|
70
|
-
vld1.64 d8, [r0:64]!
|
71
|
-
vld1.64 d1, [r0:64]!
|
72
|
-
vld1.64 d3, [r0:64]!
|
73
|
-
vld1.64 d5, [r0:64]!
|
74
|
-
vld1.64 d7, [r0:64]!
|
75
|
-
vld1.64 d9, [r0:64]!
|
76
|
-
vld1.64 d10, [r0:64]!
|
77
|
-
vld1.64 d12, [r0:64]!
|
78
|
-
vld1.64 d14, [r0:64]!
|
79
|
-
vld1.64 d16, [r0:64]!
|
80
|
-
vld1.64 d18, [r0:64]!
|
81
|
-
vld1.64 d11, [r0:64]!
|
82
|
-
vld1.64 d13, [r0:64]!
|
83
|
-
vld1.64 d15, [r0:64]!
|
84
|
-
vld1.64 d17, [r0:64]!
|
85
|
-
vld1.64 d19, [r0:64]!
|
86
|
-
vld1.64 { d20, d21 }, [r0:128]!
|
87
|
-
vld1.64 { d22, d23 }, [r0:128]!
|
88
|
-
vld1.64 d24, [r0:64]
|
89
|
-
sub r0, r0, #24*8
|
90
|
-
MEND
|
91
|
-
|
92
|
-
MACRO
|
93
|
-
StoreState
|
94
|
-
vst1.64 d0, [r0:64]!
|
95
|
-
vst1.64 d2, [r0:64]!
|
96
|
-
vst1.64 d4, [r0:64]!
|
97
|
-
vst1.64 d6, [r0:64]!
|
98
|
-
vst1.64 d8, [r0:64]!
|
99
|
-
vst1.64 d1, [r0:64]!
|
100
|
-
vst1.64 d3, [r0:64]!
|
101
|
-
vst1.64 d5, [r0:64]!
|
102
|
-
vst1.64 d7, [r0:64]!
|
103
|
-
vst1.64 d9, [r0:64]!
|
104
|
-
vst1.64 d10, [r0:64]!
|
105
|
-
vst1.64 d12, [r0:64]!
|
106
|
-
vst1.64 d14, [r0:64]!
|
107
|
-
vst1.64 d16, [r0:64]!
|
108
|
-
vst1.64 d18, [r0:64]!
|
109
|
-
vst1.64 d11, [r0:64]!
|
110
|
-
vst1.64 d13, [r0:64]!
|
111
|
-
vst1.64 d15, [r0:64]!
|
112
|
-
vst1.64 d17, [r0:64]!
|
113
|
-
vst1.64 d19, [r0:64]!
|
114
|
-
vst1.64 { d20, d21 }, [r0:128]!
|
115
|
-
vst1.64 { d22, d23 }, [r0:128]!
|
116
|
-
vst1.64 d24, [r0:64]
|
117
|
-
MEND
|
118
|
-
|
119
|
-
MACRO
|
120
|
-
RhoPi4 $dst1, $src1, $rot1, $dst2, $src2, $rot2, $dst3, $src3, $rot3, $dst4, $src4, $rot4
|
121
|
-
if ($rot1 :AND: 7) != 0
|
122
|
-
vshl.u64 $dst1, $src1, #$rot1
|
123
|
-
else
|
124
|
-
vext.8 $dst1, $src1, $src1, #8-$rot1/8
|
125
|
-
endif
|
126
|
-
if ($rot2 :AND: 7) != 0
|
127
|
-
vshl.u64 $dst2, $src2, #$rot2
|
128
|
-
else
|
129
|
-
vext.8 $dst2, $src2, $src2, #8-$rot2/8
|
130
|
-
endif
|
131
|
-
if ($rot3 :AND: 7) != 0
|
132
|
-
vshl.u64 $dst3, $src3, #$rot3
|
133
|
-
else
|
134
|
-
vext.8 $dst3, $src3, $src3, #8-$rot3/8
|
135
|
-
endif
|
136
|
-
if ($rot4 :AND: 7) != 0
|
137
|
-
vshl.u64 $dst4, $src4, #$rot4
|
138
|
-
else
|
139
|
-
vext.8 $dst4, $src4, $src4, #8-$rot4/8
|
140
|
-
endif
|
141
|
-
if ($rot1 :AND: 7) != 0
|
142
|
-
vsri.u64 $dst1, $src1, #64-$rot1
|
143
|
-
endif
|
144
|
-
if ($rot2 :AND: 7) != 0
|
145
|
-
vsri.u64 $dst2, $src2, #64-$rot2
|
146
|
-
endif
|
147
|
-
if ($rot3 :AND: 7) != 0
|
148
|
-
vsri.u64 $dst3, $src3, #64-$rot3
|
149
|
-
endif
|
150
|
-
if ($rot4 :AND: 7) != 0
|
151
|
-
vsri.u64 $dst4, $src4, #64-$rot4
|
152
|
-
endif
|
153
|
-
MEND
|
154
|
-
|
155
|
-
MACRO
|
156
|
-
KeccakRound
|
157
|
-
|
158
|
-
;Prepare Theta
|
159
|
-
veor.64 q13, q0, q5
|
160
|
-
vst1.64 {q12}, [r0:128]!
|
161
|
-
veor.64 q14, q1, q6
|
162
|
-
vst1.64 {q4}, [r0:128]!
|
163
|
-
veor.64 d26, d26, d27
|
164
|
-
vst1.64 {q9}, [r0:128]
|
165
|
-
veor.64 d28, d28, d29
|
166
|
-
veor.64 d26, d26, d20
|
167
|
-
veor.64 d27, d28, d21
|
168
|
-
|
169
|
-
veor.64 q14, q2, q7
|
170
|
-
veor.64 q15, q3, q8
|
171
|
-
veor.64 q4, q4, q9
|
172
|
-
veor.64 d28, d28, d29
|
173
|
-
veor.64 d30, d30, d31
|
174
|
-
veor.64 d25, d8, d9
|
175
|
-
veor.64 d28, d28, d22
|
176
|
-
veor.64 d29, d30, d23
|
177
|
-
veor.64 d25, d25, d24
|
178
|
-
sub r0, r0, #32
|
179
|
-
|
180
|
-
;Apply Theta
|
181
|
-
vadd.u64 d30, d27, d27
|
182
|
-
vadd.u64 d24, d28, d28
|
183
|
-
vadd.u64 d8, d29, d29
|
184
|
-
vadd.u64 d18, d25, d25
|
185
|
-
|
186
|
-
vsri.64 d30, d27, #63
|
187
|
-
vsri.64 d24, d28, #63
|
188
|
-
vsri.64 d8, d29, #63
|
189
|
-
vsri.64 d18, d25, #63
|
190
|
-
|
191
|
-
veor.64 d30, d30, d25
|
192
|
-
veor.64 d24, d24, d26
|
193
|
-
veor.64 d8, d8, d27
|
194
|
-
vadd.u64 d27, d26, d26 ;u
|
195
|
-
veor.64 d18, d18, d28
|
196
|
-
|
197
|
-
vmov.i64 d31, d30
|
198
|
-
vmov.i64 d25, d24
|
199
|
-
vsri.64 d27, d26, #63 ;u
|
200
|
-
vmov.i64 d9, d8
|
201
|
-
vmov.i64 d19, d18
|
202
|
-
|
203
|
-
veor.64 d20, d20, d30
|
204
|
-
veor.64 d21, d21, d24
|
205
|
-
veor.64 d27, d27, d29 ;u
|
206
|
-
veor.64 d22, d22, d8
|
207
|
-
veor.64 d23, d23, d18
|
208
|
-
vmov.i64 d26, d27 ;u
|
209
|
-
|
210
|
-
veor.64 q0, q0, q15
|
211
|
-
veor.64 q1, q1, q12
|
212
|
-
veor.64 q2, q2, q4
|
213
|
-
veor.64 q3, q3, q9
|
214
|
-
|
215
|
-
veor.64 q5, q5, q15
|
216
|
-
veor.64 q6, q6, q12
|
217
|
-
vld1.64 {q12}, [r0:128]!
|
218
|
-
veor.64 q7, q7, q4
|
219
|
-
vld1.64 {q4}, [r0:128]!
|
220
|
-
veor.64 q8, q8, q9
|
221
|
-
vld1.64 {q9}, [r0:128]
|
222
|
-
veor.64 d24, d24, d26 ;u
|
223
|
-
sub r0, r0, #32
|
224
|
-
veor.64 q4, q4, q13 ;u
|
225
|
-
veor.64 q9, q9, q13 ;u
|
226
|
-
|
227
|
-
;Rho Pi
|
228
|
-
vmov.i64 d27, d2
|
229
|
-
vmov.i64 d28, d4
|
230
|
-
vmov.i64 d29, d6
|
231
|
-
vmov.i64 d25, d8
|
232
|
-
|
233
|
-
RhoPi4 d2, d3, 44, d4, d14, 43, d8, d24, 14, d6, d17, 21 ; 1 < 6, 2 < 12, 4 < 24, 3 < 18
|
234
|
-
RhoPi4 d3, d9, 20, d14, d16, 25, d24, d21, 2, d17, d15, 15 ; 6 < 9, 12 < 13, 24 < 21, 18 < 17
|
235
|
-
RhoPi4 d9, d22, 61, d16, d19, 8, d21, d7, 55, d15, d12, 10 ; 9 < 22, 13 < 19, 21 < 8, 17 < 11
|
236
|
-
RhoPi4 d22, d18, 39, d19, d23, 56, d7, d13, 45, d12, d5, 6 ; 22 < 14, 19 < 23, 8 < 16, 11 < 7
|
237
|
-
RhoPi4 d18, d20, 18, d23, d11, 41, d13, d1, 36, d5, d10, 3 ; 14 < 20, 23 < 15, 16 < 5, 7 < 10
|
238
|
-
RhoPi4 d20, d28, 62, d11, d25, 27, d1, d29, 28, d10, d27, 1 ; 20 < 2, 15 < 4, 5 < 3, 10 < 1
|
239
|
-
|
240
|
-
;Chi b+g
|
241
|
-
vmov.i64 q13, q0
|
242
|
-
vbic.64 q15, q2, q1 ; ba ^= ~be & bi
|
243
|
-
veor.64 q0, q15
|
244
|
-
vmov.i64 q14, q1
|
245
|
-
vbic.64 q15, q3, q2 ; be ^= ~bi & bo
|
246
|
-
veor.64 q1, q15
|
247
|
-
vbic.64 q15, q4, q3 ; bi ^= ~bo & bu
|
248
|
-
veor.64 q2, q15
|
249
|
-
vbic.64 q15, q13, q4 ; bo ^= ~bu & ba
|
250
|
-
vbic.64 q13, q14, q13 ; bu ^= ~ba & be
|
251
|
-
veor.64 q3, q15
|
252
|
-
veor.64 q4, q13
|
253
|
-
|
254
|
-
;Chi k+m
|
255
|
-
vmov.i64 q13, q5
|
256
|
-
vbic.64 q15, q7, q6 ; ba ^= ~be & bi
|
257
|
-
veor.64 q5, q15
|
258
|
-
vmov.i64 q14, q6
|
259
|
-
vbic.64 q15, q8, q7 ; be ^= ~bi & bo
|
260
|
-
veor.64 q6, q15
|
261
|
-
vbic.64 q15, q9, q8 ; bi ^= ~bo & bu
|
262
|
-
veor.64 q7, q15
|
263
|
-
vbic.64 q15, q13, q9 ; bo ^= ~bu & ba
|
264
|
-
vbic.64 q13, q14, q13 ; bu ^= ~ba & be
|
265
|
-
veor.64 q8, q15
|
266
|
-
veor.64 q9, q13
|
267
|
-
|
268
|
-
;Chi s
|
269
|
-
vmov.i64 q13, q10
|
270
|
-
vbic.64 d30, d22, d21 ; ba ^= ~be & bi
|
271
|
-
vbic.64 d31, d23, d22 ; be ^= ~bi & bo
|
272
|
-
veor.64 q10, q15
|
273
|
-
vbic.64 d30, d24, d23 ; bi ^= ~bo & bu
|
274
|
-
vbic.64 d31, d26, d24 ; bo ^= ~bu & ba
|
275
|
-
vbic.64 d26, d27, d26 ; bu ^= ~ba & be
|
276
|
-
veor.64 q11, q15
|
277
|
-
vld1.64 d30, [r1:64]! ; Iota
|
278
|
-
veor.64 d24, d26
|
279
|
-
veor.64 d0, d0, d30 ; Iota
|
280
|
-
MEND
|
281
|
-
|
282
|
-
;----------------------------------------------------------------------------
|
283
|
-
;
|
284
|
-
; void KeccakP1600_StaticInitialize( void )
|
285
|
-
;
|
286
|
-
ALIGN
|
287
|
-
EXPORT KeccakP1600_StaticInitialize
|
288
|
-
KeccakP1600_StaticInitialize PROC
|
289
|
-
bx lr
|
290
|
-
ENDP
|
291
|
-
|
292
|
-
;----------------------------------------------------------------------------
|
293
|
-
;
|
294
|
-
; void KeccakP1600_Initialize(void *state)
|
295
|
-
;
|
296
|
-
ALIGN
|
297
|
-
EXPORT KeccakP1600_Initialize
|
298
|
-
KeccakP1600_Initialize PROC
|
299
|
-
vmov.i64 q0, #0
|
300
|
-
vmov.i64 q1, #0
|
301
|
-
vmov.i64 q2, #0
|
302
|
-
vmov.i64 q3, #0
|
303
|
-
vstm r0!, { d0 - d7 } ; clear 8 lanes at a time
|
304
|
-
vstm r0!, { d0 - d7 }
|
305
|
-
vstm r0!, { d0 - d7 }
|
306
|
-
vstm r0!, { d0 }
|
307
|
-
bx lr
|
308
|
-
ENDP
|
309
|
-
|
310
|
-
; ----------------------------------------------------------------------------
|
311
|
-
;
|
312
|
-
; void KeccakP1600_AddByte(void *state, unsigned char byte, unsigned int offset)
|
313
|
-
;
|
314
|
-
ALIGN
|
315
|
-
EXPORT KeccakP1600_AddByte
|
316
|
-
KeccakP1600_AddByte PROC
|
317
|
-
ldrb r3, [r0, r2]
|
318
|
-
eors r3, r3, r1
|
319
|
-
strb r3, [r0, r2]
|
320
|
-
bx lr
|
321
|
-
ENDP
|
322
|
-
|
323
|
-
; ----------------------------------------------------------------------------
|
324
|
-
;
|
325
|
-
; void KeccakP1600_AddBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
326
|
-
;
|
327
|
-
ALIGN
|
328
|
-
EXPORT KeccakP1600_AddBytes
|
329
|
-
KeccakP1600_AddBytes PROC
|
330
|
-
push {r4,lr}
|
331
|
-
adds r0, r0, r2 ; state += offset
|
332
|
-
subs r3, r3, #8 ; if length >= lane size
|
333
|
-
bcc KeccakP1600_AddBytes_Bytes
|
334
|
-
KeccakP1600_AddBytes_LanesLoop ; then, perform on lanes
|
335
|
-
ldr r2, [r0]
|
336
|
-
ldr r4, [r1], #4
|
337
|
-
ldr r12, [r0, #4]
|
338
|
-
ldr lr, [r1], #4
|
339
|
-
eors r2, r2, r4
|
340
|
-
eors r12, r12, lr
|
341
|
-
subs r3, r3, #8
|
342
|
-
str r2, [r0], #4
|
343
|
-
str r12, [r0], #4
|
344
|
-
bcs KeccakP1600_AddBytes_LanesLoop
|
345
|
-
KeccakP1600_AddBytes_Bytes
|
346
|
-
adds r3, r3, #7
|
347
|
-
bcc KeccakP1600_AddBytes_Exit
|
348
|
-
KeccakP1600_AddBytes_BytesLoop
|
349
|
-
ldrb r2, [r0]
|
350
|
-
ldrb r4, [r1], #1
|
351
|
-
eors r2, r2, r4
|
352
|
-
strb r2, [r0], #1
|
353
|
-
subs r3, r3, #1
|
354
|
-
bcs KeccakP1600_AddBytes_BytesLoop
|
355
|
-
KeccakP1600_AddBytes_Exit
|
356
|
-
pop {r4,pc}
|
357
|
-
ENDP
|
358
|
-
|
359
|
-
; ----------------------------------------------------------------------------
|
360
|
-
;
|
361
|
-
; void KeccakP1600_OverwriteBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
362
|
-
;
|
363
|
-
ALIGN
|
364
|
-
EXPORT KeccakP1600_OverwriteBytes
|
365
|
-
KeccakP1600_OverwriteBytes PROC
|
366
|
-
adds r0, r0, r2 ; state += offset
|
367
|
-
subs r3, r3, #8 ; if length >= lane size
|
368
|
-
bcc KeccakP1600_OverwriteBytes_Bytes
|
369
|
-
KeccakP1600_OverwriteBytes_LanesLoop ; then, perform on lanes
|
370
|
-
ldr r2, [r1], #4
|
371
|
-
ldr r12, [r1], #4
|
372
|
-
subs r3, r3, #8
|
373
|
-
str r2, [r0], #4
|
374
|
-
str r12, [r0], #4
|
375
|
-
bcs KeccakP1600_OverwriteBytes_LanesLoop
|
376
|
-
KeccakP1600_OverwriteBytes_Bytes
|
377
|
-
adds r3, r3, #7
|
378
|
-
bcc KeccakP1600_OverwriteBytes_Exit
|
379
|
-
KeccakP1600_OverwriteBytes_BytesLoop
|
380
|
-
ldrb r2, [r1], #1
|
381
|
-
subs r3, r3, #1
|
382
|
-
strb r2, [r0], #1
|
383
|
-
bcs KeccakP1600_OverwriteBytes_BytesLoop
|
384
|
-
KeccakP1600_OverwriteBytes_Exit
|
385
|
-
bx lr
|
386
|
-
ENDP
|
387
|
-
|
388
|
-
;----------------------------------------------------------------------------
|
389
|
-
;
|
390
|
-
; void KeccakP1600_OverwriteWithZeroes(void *state, unsigned int byteCount)
|
391
|
-
;
|
392
|
-
ALIGN
|
393
|
-
EXPORT KeccakP1600_OverwriteWithZeroes
|
394
|
-
KeccakP1600_OverwriteWithZeroes PROC
|
395
|
-
lsrs r2, r1, #3
|
396
|
-
beq KeccakP1600_OverwriteWithZeroes_Bytes
|
397
|
-
vmov.i64 d0, #0
|
398
|
-
KeccakP1600_OverwriteWithZeroes_LoopLanes
|
399
|
-
subs r2, r2, #1
|
400
|
-
vstm r0!, { d0 }
|
401
|
-
bne KeccakP1600_OverwriteWithZeroes_LoopLanes
|
402
|
-
KeccakP1600_OverwriteWithZeroes_Bytes
|
403
|
-
ands r1, #7
|
404
|
-
beq KeccakP1600_OverwriteWithZeroes_Exit
|
405
|
-
movs r3, #0
|
406
|
-
KeccakP1600_OverwriteWithZeroes_LoopBytes
|
407
|
-
subs r1, r1, #1
|
408
|
-
strb r3, [r0], #1
|
409
|
-
bne KeccakP1600_OverwriteWithZeroes_LoopBytes
|
410
|
-
KeccakP1600_OverwriteWithZeroes_Exit
|
411
|
-
bx lr
|
412
|
-
ENDP
|
413
|
-
|
414
|
-
; ----------------------------------------------------------------------------
|
415
|
-
;
|
416
|
-
; void KeccakP1600_ExtractBytes(void *state, const unsigned char *data, unsigned int offset, unsigned int length)
|
417
|
-
;
|
418
|
-
ALIGN
|
419
|
-
EXPORT KeccakP1600_ExtractBytes
|
420
|
-
KeccakP1600_ExtractBytes PROC
|
421
|
-
adds r0, r0, r2 ; state += offset
|
422
|
-
subs r3, r3, #8 ; if length >= lane size
|
423
|
-
bcc KeccakP1600_ExtractBytes_Bytes
|
424
|
-
KeccakP1600_ExtractBytes_LanesLoop ; then, handle lanes
|
425
|
-
ldr r2, [r0], #4
|
426
|
-
ldr r12, [r0], #4
|
427
|
-
subs r3, r3, #8
|
428
|
-
str r2, [r1], #4
|
429
|
-
str r12, [r1], #4
|
430
|
-
bcs KeccakP1600_ExtractBytes_LanesLoop
|
431
|
-
KeccakP1600_ExtractBytes_Bytes
|
432
|
-
adds r3, r3, #7
|
433
|
-
bcc KeccakP1600_ExtractBytes_Exit
|
434
|
-
KeccakP1600_ExtractBytes_BytesLoop
|
435
|
-
ldrb r2, [r0], #1
|
436
|
-
subs r3, r3, #1
|
437
|
-
strb r2, [r1], #1
|
438
|
-
bcs KeccakP1600_ExtractBytes_BytesLoop
|
439
|
-
KeccakP1600_ExtractBytes_Exit
|
440
|
-
bx lr
|
441
|
-
ENDP
|
442
|
-
|
443
|
-
; ----------------------------------------------------------------------------
|
444
|
-
;
|
445
|
-
; void KeccakP800_ExtractAndAddBytes(void *state, const unsigned char *input, unsigned char *output, unsigned int offset, unsigned int length)
|
446
|
-
;
|
447
|
-
ALIGN
|
448
|
-
EXPORT KeccakP1600_ExtractAndAddBytes
|
449
|
-
KeccakP1600_ExtractAndAddBytes PROC
|
450
|
-
push {r4,r5}
|
451
|
-
add r0, r0, r3 ; state += offset (offset register no longer needed, reuse for length)
|
452
|
-
ldr r3, [sp, #8] ; get length argument from stack
|
453
|
-
subs r3, r3, #8 ; if length >= lane size
|
454
|
-
bcc KeccakP1600_ExtractAndAddBytes_Bytes
|
455
|
-
KeccakP1600_ExtractAndAddBytes_LanesLoop ; then, handle lanes
|
456
|
-
ldr r5, [r0], #4
|
457
|
-
ldr r4, [r1], #4
|
458
|
-
eor r5, r5, r4
|
459
|
-
str r5, [r2], #4
|
460
|
-
subs r3, r3, #8
|
461
|
-
ldr r5, [r0], #4
|
462
|
-
ldr r4, [r1], #4
|
463
|
-
eor r5, r5, r4
|
464
|
-
str r5, [r2], #4
|
465
|
-
bcs KeccakP1600_ExtractAndAddBytes_LanesLoop
|
466
|
-
KeccakP1600_ExtractAndAddBytes_Bytes
|
467
|
-
adds r3, r3, #7
|
468
|
-
bcc KeccakP1600_ExtractAndAddBytes_Exit
|
469
|
-
KeccakP1600_ExtractAndAddBytes_BytesLoop
|
470
|
-
ldrb r5, [r0], #1
|
471
|
-
ldrb r4, [r1], #1
|
472
|
-
eor r5, r5, r4
|
473
|
-
strb r5, [r2], #1
|
474
|
-
subs r3, r3, #1
|
475
|
-
bcs KeccakP1600_ExtractAndAddBytes_BytesLoop
|
476
|
-
KeccakP1600_ExtractAndAddBytes_Exit
|
477
|
-
pop {r4,r5}
|
478
|
-
bx lr
|
479
|
-
ENDP
|
480
|
-
|
481
|
-
; ----------------------------------------------------------------------------
|
482
|
-
;
|
483
|
-
; void KeccakP1600_Permute_Nrounds(void *state, unsigned int nrounds)
|
484
|
-
;
|
485
|
-
ALIGN
|
486
|
-
EXPORT KeccakP1600_Permute_Nrounds
|
487
|
-
KeccakP1600_Permute_Nrounds PROC
|
488
|
-
movs r2, r1
|
489
|
-
adr r1, KeccakP1600_Permute_RoundConstants0
|
490
|
-
sub r1, r1, r2, LSL #3
|
491
|
-
b KeccakP1600_Permute
|
492
|
-
ENDP
|
493
|
-
|
494
|
-
; ----------------------------------------------------------------------------
|
495
|
-
;
|
496
|
-
; void KeccakP1600_Permute_12rounds( void *state )
|
497
|
-
;
|
498
|
-
ALIGN
|
499
|
-
EXPORT KeccakP1600_Permute_12rounds
|
500
|
-
KeccakP1600_Permute_12rounds PROC
|
501
|
-
adr r1, KeccakP1600_Permute_RoundConstants12
|
502
|
-
movs r2, #12
|
503
|
-
b KeccakP1600_Permute
|
504
|
-
ENDP
|
505
|
-
|
506
|
-
; ----------------------------------------------------------------------------
|
507
|
-
;
|
508
|
-
; void KeccakP1600_Permute_24rounds( void *state )
|
509
|
-
;
|
510
|
-
ALIGN
|
511
|
-
EXPORT KeccakP1600_Permute_24rounds
|
512
|
-
KeccakP1600_Permute_24rounds PROC
|
513
|
-
adr r1, KeccakP1600_Permute_RoundConstants24
|
514
|
-
movs r2, #24
|
515
|
-
b KeccakP1600_Permute
|
516
|
-
ENDP
|
517
|
-
|
518
|
-
ALIGN
|
519
|
-
KeccakP1600_Permute_RoundConstants24
|
520
|
-
dcq 0x0000000000000001
|
521
|
-
dcq 0x0000000000008082
|
522
|
-
dcq 0x800000000000808a
|
523
|
-
dcq 0x8000000080008000
|
524
|
-
dcq 0x000000000000808b
|
525
|
-
dcq 0x0000000080000001
|
526
|
-
dcq 0x8000000080008081
|
527
|
-
dcq 0x8000000000008009
|
528
|
-
dcq 0x000000000000008a
|
529
|
-
dcq 0x0000000000000088
|
530
|
-
dcq 0x0000000080008009
|
531
|
-
dcq 0x000000008000000a
|
532
|
-
KeccakP1600_Permute_RoundConstants12
|
533
|
-
dcq 0x000000008000808b
|
534
|
-
dcq 0x800000000000008b
|
535
|
-
dcq 0x8000000000008089
|
536
|
-
dcq 0x8000000000008003
|
537
|
-
dcq 0x8000000000008002
|
538
|
-
dcq 0x8000000000000080
|
539
|
-
dcq 0x000000000000800a
|
540
|
-
dcq 0x800000008000000a
|
541
|
-
dcq 0x8000000080008081
|
542
|
-
dcq 0x8000000000008080
|
543
|
-
dcq 0x0000000080000001
|
544
|
-
dcq 0x8000000080008008
|
545
|
-
KeccakP1600_Permute_RoundConstants0
|
546
|
-
|
547
|
-
ALIGN
|
548
|
-
KeccakP1600_XORandPermuteAsmOnly PROC
|
549
|
-
|
550
|
-
add pc, pc, r5, LSL #3
|
551
|
-
mov r1, #0 ; dummy instruction for PC alignment, not executed
|
552
|
-
veor.64 d0, d0, d30
|
553
|
-
b KeccakP1600_PermuteAsmOnly
|
554
|
-
veor.64 d2, d2, d30
|
555
|
-
b KeccakP1600_PermuteAsmOnly
|
556
|
-
veor.64 d4, d4, d30
|
557
|
-
b KeccakP1600_PermuteAsmOnly
|
558
|
-
veor.64 d6, d6, d30
|
559
|
-
b KeccakP1600_PermuteAsmOnly
|
560
|
-
veor.64 d8, d8, d30
|
561
|
-
b KeccakP1600_PermuteAsmOnly
|
562
|
-
|
563
|
-
veor.64 d1, d1, d30
|
564
|
-
b KeccakP1600_PermuteAsmOnly
|
565
|
-
veor.64 d3, d3, d30
|
566
|
-
b KeccakP1600_PermuteAsmOnly
|
567
|
-
veor.64 d5, d5, d30
|
568
|
-
b KeccakP1600_PermuteAsmOnly
|
569
|
-
veor.64 d7, d7, d30
|
570
|
-
b KeccakP1600_PermuteAsmOnly
|
571
|
-
veor.64 d9, d9, d30
|
572
|
-
b KeccakP1600_PermuteAsmOnly
|
573
|
-
|
574
|
-
veor.64 d10, d10, d30
|
575
|
-
b KeccakP1600_PermuteAsmOnly
|
576
|
-
veor.64 d12, d12, d30
|
577
|
-
b KeccakP1600_PermuteAsmOnly
|
578
|
-
veor.64 d14, d14, d30
|
579
|
-
b KeccakP1600_PermuteAsmOnly
|
580
|
-
veor.64 d16, d16, d30
|
581
|
-
b KeccakP1600_PermuteAsmOnly
|
582
|
-
veor.64 d18, d18, d30
|
583
|
-
b KeccakP1600_PermuteAsmOnly
|
584
|
-
|
585
|
-
veor.64 d11, d11, d30
|
586
|
-
b KeccakP1600_PermuteAsmOnly
|
587
|
-
veor.64 d13, d13, d30
|
588
|
-
b KeccakP1600_PermuteAsmOnly
|
589
|
-
veor.64 d15, d15, d30
|
590
|
-
b KeccakP1600_PermuteAsmOnly
|
591
|
-
veor.64 d17, d17, d30
|
592
|
-
b KeccakP1600_PermuteAsmOnly
|
593
|
-
veor.64 d19, d19, d30
|
594
|
-
b KeccakP1600_PermuteAsmOnly
|
595
|
-
|
596
|
-
veor.64 d20, d20, d30
|
597
|
-
b KeccakP1600_PermuteAsmOnly
|
598
|
-
veor.64 d21, d21, d30
|
599
|
-
b KeccakP1600_PermuteAsmOnly
|
600
|
-
veor.64 d22, d22, d30
|
601
|
-
b KeccakP1600_PermuteAsmOnly
|
602
|
-
veor.64 d23, d23, d30
|
603
|
-
b KeccakP1600_PermuteAsmOnly
|
604
|
-
veor.64 d24, d24, d30
|
605
|
-
KeccakP1600_PermuteAsmOnly
|
606
|
-
KeccakP1600_Permute_RoundLoop
|
607
|
-
KeccakRound
|
608
|
-
if LoopUnroll > 1
|
609
|
-
KeccakRound
|
610
|
-
if LoopUnroll > 2
|
611
|
-
KeccakRound
|
612
|
-
KeccakRound
|
613
|
-
if LoopUnroll > 4
|
614
|
-
KeccakRound
|
615
|
-
KeccakRound
|
616
|
-
if LoopUnroll > 6
|
617
|
-
KeccakRound
|
618
|
-
KeccakRound
|
619
|
-
KeccakRound
|
620
|
-
KeccakRound
|
621
|
-
KeccakRound
|
622
|
-
KeccakRound
|
623
|
-
endif
|
624
|
-
endif
|
625
|
-
endif
|
626
|
-
endif
|
627
|
-
subs r2, #LoopUnroll
|
628
|
-
bne KeccakP1600_Permute_RoundLoop
|
629
|
-
bx lr
|
630
|
-
ENDP
|
631
|
-
|
632
|
-
;----------------------------------------------------------------------------
|
633
|
-
;
|
634
|
-
; void KeccakP1600_Permute( void *state, void *roundConstants, unsigned int numberOfRounds )
|
635
|
-
;
|
636
|
-
ALIGN
|
637
|
-
EXPORT KeccakP1600_Permute
|
638
|
-
KeccakP1600_Permute PROC
|
639
|
-
mov r3, lr
|
640
|
-
vpush {q4-q7}
|
641
|
-
LoadState
|
642
|
-
bl KeccakP1600_PermuteAsmOnly
|
643
|
-
StoreState
|
644
|
-
vpop {q4-q7}
|
645
|
-
bx r3
|
646
|
-
ENDP
|
647
|
-
|
648
|
-
if FastLoop != 0
|
649
|
-
|
650
|
-
;----------------------------------------------------------------------------
|
651
|
-
;
|
652
|
-
; size_t KeccakF1600_FastLoop_Absorb( void *state, unsigned int laneCount, unsigned char *data,
|
653
|
-
; size_t dataByteLen, unsigned char trailingBits )
|
654
|
-
;
|
655
|
-
ALIGN
|
656
|
-
EXPORT KeccakF1600_FastLoop_Absorb
|
657
|
-
KeccakF1600_FastLoop_Absorb PROC
|
658
|
-
push {r4-r8,lr} ; 6 CPU registers (24 bytes)
|
659
|
-
lsr r3, r3, #3 ; r3 nbrLanes = dataByteLen / SnP_laneLengthInBytes
|
660
|
-
mov r6, r2 ; r6 data pointer
|
661
|
-
subs r3, r3, r1 ; if (nbrLanes >= laneCount)
|
662
|
-
mov r4, r2 ; r4 initial data pointer
|
663
|
-
bcc KeccakF1600_FastLoop_Absorb_Exit
|
664
|
-
mov r5, r1
|
665
|
-
vpush {q4-q7} ; 4 quad registers (64 bytes)
|
666
|
-
LoadState
|
667
|
-
|
668
|
-
sub sp, sp, #8 ; alloc space for trailingBits lane
|
669
|
-
veor.64 d30, d30, d30
|
670
|
-
add r7, sp, #(6+16+2)*4
|
671
|
-
vld1.8 {d30[0]}, [r7]
|
672
|
-
vst1.64 {d30}, [sp:64]
|
673
|
-
|
674
|
-
cmp r5, #21
|
675
|
-
bne KeccakF1600_FastLoop_Absorb_Not21Lanes
|
676
|
-
KeccakF1600_FastLoop_Absorb_Loop21Lanes
|
677
|
-
vld1.64 { d26, d27, d28, d29 }, [r6]! ; XOR first 21 lanes
|
678
|
-
veor.64 d0, d0, d26
|
679
|
-
veor.64 d2, d2, d27
|
680
|
-
veor.64 d4, d4, d28
|
681
|
-
veor.64 d6, d6, d29
|
682
|
-
vld1.64 { d26, d27, d28, d29 }, [r6]!
|
683
|
-
veor.64 d8, d8, d26
|
684
|
-
veor.64 d1, d1, d27
|
685
|
-
veor.64 d3, d3, d28
|
686
|
-
veor.64 d5, d5, d29
|
687
|
-
vld1.64 { d26, d27, d28, d29 }, [r6]!
|
688
|
-
veor.64 d7, d7, d26
|
689
|
-
veor.64 d9, d9, d27
|
690
|
-
veor.64 d10, d10, d28
|
691
|
-
veor.64 d12, d12, d29
|
692
|
-
vld1.64 { d26, d27, d28, d29 }, [r6]!
|
693
|
-
veor.64 d14, d14, d26
|
694
|
-
veor.64 d16, d16, d27
|
695
|
-
veor.64 d18, d18, d28
|
696
|
-
veor.64 d11, d11, d29
|
697
|
-
vld1.64 { d26, d27, d28, d29 }, [r6]!
|
698
|
-
veor.64 d13, d13, d26
|
699
|
-
veor.64 d15, d15, d27
|
700
|
-
veor.64 d17, d17, d28
|
701
|
-
veor.64 d19, d19, d29
|
702
|
-
vld1.64 { d26 }, [r6]!
|
703
|
-
veor.64 d20, d20, d26
|
704
|
-
|
705
|
-
vld1.64 {d30}, [sp:64] ; xor trailingBits
|
706
|
-
veor.64 d21, d21, d30
|
707
|
-
bl KeccakP1600_PermuteAsmOnly
|
708
|
-
subs r3, r3, r5 ; nbrLanes -= laneCount
|
709
|
-
bcs KeccakF1600_FastLoop_Absorb_Loop21Lanes
|
710
|
-
KeccakF1600_FastLoop_Absorb_Done
|
711
|
-
add sp, sp, #8 ; free trailingBits lane
|
712
|
-
StoreState
|
713
|
-
vpop {q4-q7}
|
714
|
-
KeccakF1600_FastLoop_Absorb_Exit
|
715
|
-
sub r0, r6, r4 ; processed = data pointer - initial data pointer
|
716
|
-
pop {r4-r8,pc}
|
717
|
-
KeccakF1600_FastLoop_Absorb_Not21Lanes
|
718
|
-
cmp r5, #16
|
719
|
-
mvn r7, #7 ; r7 = -8
|
720
|
-
blo KeccakF1600_FastLoop_Absorb_LoopLessThan16Lanes
|
721
|
-
KeccakF1600_FastLoop_Absorb_Loop16OrMoreLanes
|
722
|
-
vld1.64 { d26, d27, d28, d29 }, [r6]! ; XOR first 16 lanes
|
723
|
-
veor.64 d0, d0, d26
|
724
|
-
veor.64 d2, d2, d27
|
725
|
-
veor.64 d4, d4, d28
|
726
|
-
veor.64 d6, d6, d29
|
727
|
-
vld1.64 { d26, d27, d28, d29 }, [r6]!
|
728
|
-
veor.64 d8, d8, d26
|
729
|
-
veor.64 d1, d1, d27
|
730
|
-
veor.64 d3, d3, d28
|
731
|
-
veor.64 d5, d5, d29
|
732
|
-
vld1.64 { d26, d27, d28, d29 }, [r6]!
|
733
|
-
veor.64 d7, d7, d26
|
734
|
-
veor.64 d9, d9, d27
|
735
|
-
veor.64 d10, d10, d28
|
736
|
-
veor.64 d12, d12, d29
|
737
|
-
vld1.64 { d26, d27, d28, d29 }, [r6]!
|
738
|
-
veor.64 d14, d14, d26
|
739
|
-
veor.64 d16, d16, d27
|
740
|
-
veor.64 d18, d18, d28
|
741
|
-
veor.64 d11, d11, d29
|
742
|
-
|
743
|
-
sub r2, r5, #16 ; XOR last n lanes, maximum 9
|
744
|
-
rsb r1, r2, #9
|
745
|
-
add r6, r6, r2, LSL #3 ; data += n lanes * 8
|
746
|
-
sub r2, r6, #8 ; r2 tempdata = data - 8
|
747
|
-
add pc, pc, r1, LSL #3
|
748
|
-
mov r1, #0 ; dummy instruction for PC alignment, not executed
|
749
|
-
vld1.64 d30, [r2], r7
|
750
|
-
veor.64 d24, d24, d30
|
751
|
-
vld1.64 d30, [r2], r7
|
752
|
-
veor.64 d23, d23, d30
|
753
|
-
vld1.64 d30, [r2], r7
|
754
|
-
veor.64 d22, d22, d30
|
755
|
-
vld1.64 d30, [r2], r7
|
756
|
-
veor.64 d21, d21, d30
|
757
|
-
vld1.64 d30, [r2], r7
|
758
|
-
veor.64 d20, d20, d30
|
759
|
-
|
760
|
-
vld1.64 d30, [r2], r7
|
761
|
-
veor.64 d19, d19, d30
|
762
|
-
vld1.64 d30, [r2], r7
|
763
|
-
veor.64 d17, d17, d30
|
764
|
-
vld1.64 d30, [r2], r7
|
765
|
-
veor.64 d15, d15, d30
|
766
|
-
vld1.64 d30, [r2], r7
|
767
|
-
veor.64 d13, d13, d30
|
768
|
-
|
769
|
-
vld1.64 {d30}, [sp:64]
|
770
|
-
bl KeccakP1600_XORandPermuteAsmOnly
|
771
|
-
subs r3, r3, r5 ; nbrLanes -= laneCount
|
772
|
-
bcs KeccakF1600_FastLoop_Absorb_Loop16OrMoreLanes
|
773
|
-
b KeccakF1600_FastLoop_Absorb_Done
|
774
|
-
KeccakF1600_FastLoop_Absorb_LoopLessThan16Lanes
|
775
|
-
rsb r1, r5, #15 ; XOR up to 15 lanes
|
776
|
-
add r6, r6, r5, LSL #3 ; data += laneCount * 8
|
777
|
-
sub r2, r6, #8 ; r2 tempdata = data - 8
|
778
|
-
add pc, pc, r1, LSL #3
|
779
|
-
mov r1, #0 ; dummy instruction for PC alignment, not executed
|
780
|
-
|
781
|
-
vld1.64 d30, [r2], r7
|
782
|
-
veor.64 d18, d18, d30
|
783
|
-
vld1.64 d30, [r2], r7
|
784
|
-
veor.64 d16, d16, d30
|
785
|
-
vld1.64 d30, [r2], r7
|
786
|
-
veor.64 d14, d14, d30
|
787
|
-
vld1.64 d30, [r2], r7
|
788
|
-
veor.64 d12, d12, d30
|
789
|
-
vld1.64 d30, [r2], r7
|
790
|
-
veor.64 d10, d10, d30
|
791
|
-
|
792
|
-
vld1.64 d30, [r2], r7
|
793
|
-
veor.64 d9, d9, d30
|
794
|
-
vld1.64 d30, [r2], r7
|
795
|
-
veor.64 d7, d7, d30
|
796
|
-
vld1.64 d30, [r2], r7
|
797
|
-
veor.64 d5, d5, d30
|
798
|
-
vld1.64 d30, [r2], r7
|
799
|
-
veor.64 d3, d3, d30
|
800
|
-
vld1.64 d30, [r2], r7
|
801
|
-
veor.64 d1, d1, d30
|
802
|
-
|
803
|
-
vld1.64 d30, [r2], r7
|
804
|
-
veor.64 d8, d8, d30
|
805
|
-
vld1.64 d30, [r2], r7
|
806
|
-
veor.64 d6, d6, d30
|
807
|
-
vld1.64 d30, [r2], r7
|
808
|
-
veor.64 d4, d4, d30
|
809
|
-
vld1.64 d30, [r2], r7
|
810
|
-
veor.64 d2, d2, d30
|
811
|
-
vld1.64 d30, [r2], r7
|
812
|
-
veor.64 d0, d0, d30
|
813
|
-
|
814
|
-
vld1.64 {d30}, [sp:64]
|
815
|
-
bl KeccakP1600_XORandPermuteAsmOnly
|
816
|
-
subs r3, r3, r5 ; nbrLanes -= laneCount
|
817
|
-
bcs KeccakF1600_FastLoop_Absorb_LoopLessThan16Lanes
|
818
|
-
b KeccakF1600_FastLoop_Absorb_Done
|
819
|
-
ENDP
|
820
|
-
|
821
|
-
endif
|
822
|
-
|
823
|
-
END
|