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
data/ext/xkcp/lib/low/KeccakP-1600-times2/ARMv7A-NEON/KeccakP-1600-inplace-pl2-armv7a-neon-le-gcc.s
DELETED
@@ -1,1394 +0,0 @@
|
|
1
|
-
@
|
2
|
-
@ The Keccak-p permutations, designed by Guido Bertoni, Joan Daemen, Micha�l Peeters and Gilles Van Assche.
|
3
|
-
@
|
4
|
-
@ Implementation by Ronny Van Keer, hereby denoted as "the implementer".
|
5
|
-
@
|
6
|
-
@ For more information, feedback or questions, please refer to the Keccak Team website:
|
7
|
-
@ https://keccak.team/
|
8
|
-
@
|
9
|
-
@ To the extent possible under law, the implementer has waived all copyright
|
10
|
-
@ and related or neighboring rights to the source code in this file.
|
11
|
-
@ http://creativecommons.org/publicdomain/zero/1.0/
|
12
|
-
@
|
13
|
-
@ ---
|
14
|
-
@
|
15
|
-
@ This file implements Keccak-p[1600]�2 in a PlSnP-compatible way.
|
16
|
-
@ Please refer to PlSnP-documentation.h for more details.
|
17
|
-
@
|
18
|
-
@ This implementation comes with KeccakP-1600-times2-SnP.h in the same folder.
|
19
|
-
@ Please refer to LowLevel.build for the exact list of other files it must be combined with.
|
20
|
-
@
|
21
|
-
|
22
|
-
@ WARNING: These functions work only on little endian CPU with@ ARMv7A + NEON architecture
|
23
|
-
@ WARNING: State must be 256 bit (32 bytes) aligned, best is 64-byte (cache alignment).
|
24
|
-
|
25
|
-
@ INFO: Tested on Cortex-A8 (BeagleBone Black), using gcc.
|
26
|
-
@ INFO: Parallel execution of Keccak-P permutation on 2 lane interleaved states.
|
27
|
-
|
28
|
-
@ INFO: KeccakP1600times2_PermuteAll_12rounds() execution time is 7690 cycles on a Cortex-A8 (BeagleBone Black)
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
.text
|
33
|
-
|
34
|
-
@----------------------------------------------------------------------------
|
35
|
-
|
36
|
-
@ --- offsets in state
|
37
|
-
.equ _ba , 0*16
|
38
|
-
.equ _be , 1*16
|
39
|
-
.equ _bi , 2*16
|
40
|
-
.equ _bo , 3*16
|
41
|
-
.equ _bu , 4*16
|
42
|
-
.equ _ga , 5*16
|
43
|
-
.equ _ge , 6*16
|
44
|
-
.equ _gi , 7*16
|
45
|
-
.equ _go , 8*16
|
46
|
-
.equ _gu , 9*16
|
47
|
-
.equ _ka , 10*16
|
48
|
-
.equ _ke , 11*16
|
49
|
-
.equ _ki , 12*16
|
50
|
-
.equ _ko , 13*16
|
51
|
-
.equ _ku , 14*16
|
52
|
-
.equ _ma , 15*16
|
53
|
-
.equ _me , 16*16
|
54
|
-
.equ _mi , 17*16
|
55
|
-
.equ _mo , 18*16
|
56
|
-
.equ _mu , 19*16
|
57
|
-
.equ _sa , 20*16
|
58
|
-
.equ _se , 21*16
|
59
|
-
.equ _si , 22*16
|
60
|
-
.equ _so , 23*16
|
61
|
-
.equ _su , 24*16
|
62
|
-
|
63
|
-
@ --- macros for Single permutation
|
64
|
-
|
65
|
-
.macro KeccakS_ThetaRhoPiChiIota argA1, argA2, argA3, argA4, argA5
|
66
|
-
|
67
|
-
@Prepare Theta
|
68
|
-
@ Ca = Aba^Aga^Aka^Ama^Asa
|
69
|
-
@ Ce = Abe^Age^Ake^Ame^Ase
|
70
|
-
@ Ci = Abi^Agi^Aki^Ami^Asi
|
71
|
-
@ Co = Abo^Ago^Ako^Amo^Aso
|
72
|
-
@ Cu = Abu^Agu^Aku^Amu^Asu
|
73
|
-
@ De = Ca^ROL64(Ci, 1)
|
74
|
-
@ Di = Ce^ROL64(Co, 1)
|
75
|
-
@ Do = Ci^ROL64(Cu, 1)
|
76
|
-
@ Du = Co^ROL64(Ca, 1)
|
77
|
-
@ Da = Cu^ROL64(Ce, 1)
|
78
|
-
veor.64 q4, q6, q7
|
79
|
-
veor.64 q5, q9, q10
|
80
|
-
veor.64 d8, d8, d9
|
81
|
-
veor.64 d10, d10, d11
|
82
|
-
veor.64 d1, d8, d16
|
83
|
-
veor.64 d2, d10, d17
|
84
|
-
|
85
|
-
veor.64 q4, q11, q12
|
86
|
-
veor.64 q5, q14, q15
|
87
|
-
veor.64 d8, d8, d9
|
88
|
-
veor.64 d10, d10, d11
|
89
|
-
veor.64 d3, d8, d26
|
90
|
-
|
91
|
-
vadd.u64 q4, q1, q1
|
92
|
-
veor.64 d4, d10, d27
|
93
|
-
vmov.64 d0, d5
|
94
|
-
vsri.64 q4, q1, #63
|
95
|
-
|
96
|
-
vadd.u64 q5, q2, q2
|
97
|
-
veor.64 q4, q4, q0
|
98
|
-
vsri.64 q5, q2, #63
|
99
|
-
vadd.u64 d7, d1, d1
|
100
|
-
veor.64 \argA2, \argA2, d8
|
101
|
-
veor.64 q5, q5, q1
|
102
|
-
|
103
|
-
vsri.64 d7, d1, #63
|
104
|
-
vshl.u64 d1, \argA2, #44
|
105
|
-
veor.64 \argA3, \argA3, d9
|
106
|
-
veor.64 d7, d7, d4
|
107
|
-
|
108
|
-
@ Ba = argA1^Da
|
109
|
-
@ Be = ROL64((argA2^De), 44)
|
110
|
-
@ Bi = ROL64((argA3^Di), 43)
|
111
|
-
@ Bo = ROL64((argA4^Do), 21)
|
112
|
-
@ Bu = ROL64((argA5^Du), 14)
|
113
|
-
@ argA2 = Be ^((~Bi)& Bo )
|
114
|
-
@ argA3 = Bi ^((~Bo)& Bu )
|
115
|
-
@ argA4 = Bo ^((~Bu)& Ba )
|
116
|
-
@ argA5 = Bu ^((~Ba)& Be )
|
117
|
-
@ argA1 = Ba ^((~Be)& Bi )
|
118
|
-
@ argA1 ^= KeccakP1600RoundConstants[i+round]
|
119
|
-
vsri.64 d1, \argA2, #64-44
|
120
|
-
vshl.u64 d2, \argA3, #43
|
121
|
-
vldr.64 d0, [r0, #\argA1]
|
122
|
-
veor.64 \argA4, \argA4, d10
|
123
|
-
vsri.64 d2, \argA3, #64-43
|
124
|
-
vshl.u64 d3, \argA4, #21
|
125
|
-
veor.64 \argA5, \argA5, d11
|
126
|
-
veor.64 d0, d0, d7
|
127
|
-
vsri.64 d3, \argA4, #64-21
|
128
|
-
vbic.64 d5, d2, d1
|
129
|
-
vshl.u64 d4, \argA5, #14
|
130
|
-
vbic.64 \argA2, d3, d2
|
131
|
-
vld1.64 d6, [r1]!
|
132
|
-
veor.64 d5, d0
|
133
|
-
vsri.64 d4, \argA5, #64-14
|
134
|
-
veor.64 d5, d6
|
135
|
-
vbic.64 \argA5, d1, d0
|
136
|
-
vbic.64 \argA3, d4, d3
|
137
|
-
vbic.64 \argA4, d0, d4
|
138
|
-
veor.64 \argA2, d1
|
139
|
-
vstr.64 d5, [r0, #\argA1]
|
140
|
-
veor.64 \argA3, d2
|
141
|
-
veor.64 \argA4, d3
|
142
|
-
veor.64 \argA5, d4
|
143
|
-
.endm
|
144
|
-
|
145
|
-
.macro KeccakS_ThetaRhoPiChi1 argA1, argA2, argA3, argA4, argA5
|
146
|
-
|
147
|
-
@ Bi = ROL64((argA1^Da), 3)
|
148
|
-
@ Bo = ROL64((argA2^De), 45)
|
149
|
-
@ Bu = ROL64((argA3^Di), 61)
|
150
|
-
@ Ba = ROL64((argA4^Do), 28)
|
151
|
-
@ Be = ROL64((argA5^Du), 20)
|
152
|
-
@ argA1 = Ba ^((~Be)& Bi )
|
153
|
-
@ Ca ^= argA1
|
154
|
-
@ argA2 = Be ^((~Bi)& Bo )
|
155
|
-
@ argA3 = Bi ^((~Bo)& Bu )
|
156
|
-
@ argA4 = Bo ^((~Bu)& Ba )
|
157
|
-
@ argA5 = Bu ^((~Ba)& Be )
|
158
|
-
veor.64 \argA2, \argA2, d8
|
159
|
-
veor.64 \argA3, \argA3, d9
|
160
|
-
vshl.u64 d3, \argA2, #45
|
161
|
-
vldr.64 d6, [r0, #\argA1]
|
162
|
-
vshl.u64 d4, \argA3, #61
|
163
|
-
veor.64 \argA4, \argA4, d10
|
164
|
-
vsri.64 d3, \argA2, #64-45
|
165
|
-
veor.64 \argA5, \argA5, d11
|
166
|
-
vsri.64 d4, \argA3, #64-61
|
167
|
-
vshl.u64 d0, \argA4, #28
|
168
|
-
veor.64 d6, d6, d7
|
169
|
-
vshl.u64 d1, \argA5, #20
|
170
|
-
vbic.64 \argA3, d4, d3
|
171
|
-
vsri.64 d0, \argA4, #64-28
|
172
|
-
vbic.64 \argA4, d0, d4
|
173
|
-
vshl.u64 d2, d6, #3
|
174
|
-
vsri.64 d1, \argA5, #64-20
|
175
|
-
veor.64 \argA4, d3
|
176
|
-
vsri.64 d2, d6, #64-3
|
177
|
-
vbic.64 \argA5, d1, d0
|
178
|
-
vbic.64 d6, d2, d1
|
179
|
-
vbic.64 \argA2, d3, d2
|
180
|
-
veor.64 d6, d0
|
181
|
-
veor.64 \argA2, d1
|
182
|
-
vstr.64 d6, [r0, #\argA1]
|
183
|
-
veor.64 \argA3, d2
|
184
|
-
veor.64 d5, d6
|
185
|
-
veor.64 \argA5, d4
|
186
|
-
.endm
|
187
|
-
|
188
|
-
.macro KeccakS_ThetaRhoPiChi2 argA1, argA2, argA3, argA4, argA5
|
189
|
-
|
190
|
-
@ Bu = ROL64((argA1^Da), 18)
|
191
|
-
@ Ba = ROL64((argA2^De), 1)
|
192
|
-
@ Be = ROL64((argA3^Di), 6)
|
193
|
-
@ Bi = ROL64((argA4^Do), 25)
|
194
|
-
@ Bo = ROL64((argA5^Du), 8)
|
195
|
-
@ argA1 = Ba ^((~Be)& Bi )
|
196
|
-
@ Ca ^= argA1@
|
197
|
-
@ argA2 = Be ^((~Bi)& Bo )
|
198
|
-
@ argA3 = Bi ^((~Bo)& Bu )
|
199
|
-
@ argA4 = Bo ^((~Bu)& Ba )
|
200
|
-
@ argA5 = Bu ^((~Ba)& Be )
|
201
|
-
veor.64 \argA3, \argA3, d9
|
202
|
-
veor.64 \argA4, \argA4, d10
|
203
|
-
vshl.u64 d1, \argA3, #6
|
204
|
-
vldr.64 d6, [r0, #\argA1]
|
205
|
-
vshl.u64 d2, \argA4, #25
|
206
|
-
veor.64 \argA5, \argA5, d11
|
207
|
-
vsri.64 d1, \argA3, #64-6
|
208
|
-
veor.64 \argA2, \argA2, d8
|
209
|
-
vsri.64 d2, \argA4, #64-25
|
210
|
-
vext.8 d3, \argA5, \argA5, #7
|
211
|
-
veor.64 d6, d6, d7
|
212
|
-
vbic.64 \argA3, d2, d1
|
213
|
-
vadd.u64 d0, \argA2, \argA2
|
214
|
-
vbic.64 \argA4, d3, d2
|
215
|
-
vsri.64 d0, \argA2, #64-1
|
216
|
-
vshl.u64 d4, d6, #18
|
217
|
-
veor.64 \argA2, d1, \argA4
|
218
|
-
veor.64 \argA3, d0
|
219
|
-
vsri.64 d4, d6, #64-18
|
220
|
-
vstr.64 \argA3, [r0, #\argA1]
|
221
|
-
veor.64 d5, \argA3
|
222
|
-
vbic.64 \argA5, d1, d0
|
223
|
-
vbic.64 \argA3, d4, d3
|
224
|
-
vbic.64 \argA4, d0, d4
|
225
|
-
veor.64 \argA3, d2
|
226
|
-
veor.64 \argA4, d3
|
227
|
-
veor.64 \argA5, d4
|
228
|
-
.endm
|
229
|
-
|
230
|
-
.macro KeccakS_ThetaRhoPiChi3 argA1, argA2, argA3, argA4, argA5
|
231
|
-
|
232
|
-
@ Be = ROL64((argA1^Da), 36)
|
233
|
-
@ Bi = ROL64((argA2^De), 10)
|
234
|
-
@ Bo = ROL64((argA3^Di), 15)
|
235
|
-
@ Bu = ROL64((argA4^Do), 56)
|
236
|
-
@ Ba = ROL64((argA5^Du), 27)
|
237
|
-
@ argA1 = Ba ^((~Be)& Bi )
|
238
|
-
@ Ca ^= argA1
|
239
|
-
@ argA2 = Be ^((~Bi)& Bo )
|
240
|
-
@ argA3 = Bi ^((~Bo)& Bu )
|
241
|
-
@ argA4 = Bo ^((~Bu)& Ba )
|
242
|
-
@ argA5 = Bu ^((~Ba)& Be )
|
243
|
-
veor.64 \argA2, \argA2, d8
|
244
|
-
veor.64 \argA3, \argA3, d9
|
245
|
-
vshl.u64 d2, \argA2, #10
|
246
|
-
vldr.64 d6, [r0, #\argA1]
|
247
|
-
vshl.u64 d3, \argA3, #15
|
248
|
-
veor.64 \argA4, \argA4, d10
|
249
|
-
vsri.64 d2, \argA2, #64-10
|
250
|
-
vsri.64 d3, \argA3, #64-15
|
251
|
-
veor.64 \argA5, \argA5, d11
|
252
|
-
vext.8 d4, \argA4, \argA4, #1
|
253
|
-
vbic.64 \argA2, d3, d2
|
254
|
-
vshl.u64 d0, \argA5, #27
|
255
|
-
veor.64 d6, d6, d7
|
256
|
-
vbic.64 \argA3, d4, d3
|
257
|
-
vsri.64 d0, \argA5, #64-27
|
258
|
-
vshl.u64 d1, d6, #36
|
259
|
-
veor.64 \argA3, d2
|
260
|
-
vbic.64 \argA4, d0, d4
|
261
|
-
vsri.64 d1, d6, #64-36
|
262
|
-
veor.64 \argA4, d3
|
263
|
-
vbic.64 d6, d2, d1
|
264
|
-
vbic.64 \argA5, d1, d0
|
265
|
-
veor.64 d6, d0
|
266
|
-
veor.64 \argA2, d1
|
267
|
-
vstr.64 d6, [r0, #\argA1]
|
268
|
-
veor.64 d5, d6
|
269
|
-
veor.64 \argA5, d4
|
270
|
-
.endm
|
271
|
-
|
272
|
-
.macro KeccakS_ThetaRhoPiChi4 argA1, argA2, argA3, argA4, argA5
|
273
|
-
|
274
|
-
@ Bo = ROL64((argA1^Da), 41)
|
275
|
-
@ Bu = ROL64((argA2^De), 2)
|
276
|
-
@ Ba = ROL64((argA3^Di), 62)
|
277
|
-
@ Be = ROL64((argA4^Do), 55)
|
278
|
-
@ Bi = ROL64((argA5^Du), 39)
|
279
|
-
@ argA1 = Ba ^((~Be)& Bi )
|
280
|
-
@ Ca ^= argA1
|
281
|
-
@ argA2 = Be ^((~Bi)& Bo )
|
282
|
-
@ argA3 = Bi ^((~Bo)& Bu )
|
283
|
-
@ argA4 = Bo ^((~Bu)& Ba )
|
284
|
-
@ argA5 = Bu ^((~Ba)& Be )
|
285
|
-
veor.64 \argA2, \argA2, d8
|
286
|
-
veor.64 \argA3, \argA3, d9
|
287
|
-
vshl.u64 d4, \argA2, #2
|
288
|
-
veor.64 \argA5, \argA5, d11
|
289
|
-
vshl.u64 d0, \argA3, #62
|
290
|
-
vldr.64 d6, [r0, #\argA1]
|
291
|
-
vsri.64 d4, \argA2, #64-2
|
292
|
-
veor.64 \argA4, \argA4, d10
|
293
|
-
vsri.64 d0, \argA3, #64-62
|
294
|
-
vshl.u64 d1, \argA4, #55
|
295
|
-
veor.64 d6, d6, d7
|
296
|
-
vshl.u64 d2, \argA5, #39
|
297
|
-
vsri.64 d1, \argA4, #64-55
|
298
|
-
vbic.64 \argA4, d0, d4
|
299
|
-
vsri.64 d2, \argA5, #64-39
|
300
|
-
vbic.64 \argA2, d1, d0
|
301
|
-
vshl.u64 d3, d6, #41
|
302
|
-
veor.64 \argA5, d4, \argA2
|
303
|
-
vbic.64 \argA2, d2, d1
|
304
|
-
vsri.64 d3, d6, #64-41
|
305
|
-
veor.64 d6, d0, \argA2
|
306
|
-
vbic.64 \argA2, d3, d2
|
307
|
-
vbic.64 \argA3, d4, d3
|
308
|
-
veor.64 \argA2, d1
|
309
|
-
vstr.64 d6, [r0, #\argA1]
|
310
|
-
veor.64 d5, d6
|
311
|
-
veor.64 \argA3, d2
|
312
|
-
veor.64 \argA4, d3
|
313
|
-
.endm
|
314
|
-
|
315
|
-
@ --- macros for Parallel permutation
|
316
|
-
|
317
|
-
.macro m_pls start
|
318
|
-
.if \start != -1
|
319
|
-
add r3, r0, #\start
|
320
|
-
.endif
|
321
|
-
.endm
|
322
|
-
|
323
|
-
.macro m_ld qreg, next
|
324
|
-
.if \next == 16
|
325
|
-
vld1.64 { \qreg }, [r3:128]!
|
326
|
-
.else
|
327
|
-
vld1.64 { \qreg }, [r3:128], r4
|
328
|
-
.endif
|
329
|
-
.endm
|
330
|
-
|
331
|
-
.macro m_st qreg, next
|
332
|
-
.if \next == 16
|
333
|
-
vst1.64 { \qreg }, [r3:128]!
|
334
|
-
.else
|
335
|
-
vst1.64 { \qreg }, [r3:128], r4
|
336
|
-
.endif
|
337
|
-
.endm
|
338
|
-
|
339
|
-
.macro KeccakP_ThetaRhoPiChiIota ofs1, ofs2, ofs3, ofs4, ofs5, next, ofsn1
|
340
|
-
|
341
|
-
@ De = Ca ^ ROL64(Ci, 1)
|
342
|
-
@ Di = Ce ^ ROL64(Co, 1)
|
343
|
-
@ Do = Ci ^ ROL64(Cu, 1)
|
344
|
-
@ Du = Co ^ ROL64(Ca, 1)
|
345
|
-
@ Da = Cu ^ ROL64(Ce, 1)
|
346
|
-
vadd.u64 q6, q2, q2
|
347
|
-
vadd.u64 q7, q3, q3
|
348
|
-
vadd.u64 q8, q4, q4
|
349
|
-
vadd.u64 q9, q0, q0
|
350
|
-
vadd.u64 q5, q1, q1
|
351
|
-
|
352
|
-
vsri.64 q6, q2, #63
|
353
|
-
vsri.64 q7, q3, #63
|
354
|
-
vsri.64 q8, q4, #63
|
355
|
-
vsri.64 q9, q0, #63
|
356
|
-
vsri.64 q5, q1, #63
|
357
|
-
|
358
|
-
veor.64 q6, q6, q0
|
359
|
-
veor.64 q7, q7, q1
|
360
|
-
veor.64 q8, q8, q2
|
361
|
-
.if \next != 16
|
362
|
-
mov r4, #\next
|
363
|
-
.endif
|
364
|
-
veor.64 q9, q9, q3
|
365
|
-
veor.64 q5, q5, q4
|
366
|
-
|
367
|
-
@ Ba = argA1^Da
|
368
|
-
@ Be = ROL64(argA2^De, 44)
|
369
|
-
@ Bi = ROL64(argA3^Di, 43)
|
370
|
-
@ Bo = ROL64(argA4^Do, 21)
|
371
|
-
@ Bu = ROL64(argA5^Du, 14)
|
372
|
-
m_ld q10, \next
|
373
|
-
m_pls \ofs2
|
374
|
-
m_ld q1, \next
|
375
|
-
m_pls \ofs3
|
376
|
-
veor.64 q10, q10, q5
|
377
|
-
m_ld q2, \next
|
378
|
-
m_pls \ofs4
|
379
|
-
veor.64 q1, q1, q6
|
380
|
-
m_ld q3, \next
|
381
|
-
m_pls \ofs5
|
382
|
-
veor.64 q2, q2, q7
|
383
|
-
m_ld q4, \next
|
384
|
-
veor.64 q3, q3, q8
|
385
|
-
mov r6, r5
|
386
|
-
veor.64 q4, q4, q9
|
387
|
-
|
388
|
-
vst1.64 { q6 }, [r6:128]!
|
389
|
-
vshl.u64 q11, q1, #44
|
390
|
-
vshl.u64 q12, q2, #43
|
391
|
-
vst1.64 { q7 }, [r6:128]!
|
392
|
-
vshl.u64 q13, q3, #21
|
393
|
-
vshl.u64 q14, q4, #14
|
394
|
-
vst1.64 { q8 }, [r6:128]!
|
395
|
-
vsri.64 q11, q1, #64-44
|
396
|
-
vsri.64 q12, q2, #64-43
|
397
|
-
vst1.64 { q9 }, [r6:128]!
|
398
|
-
vsri.64 q13, q3, #64-21
|
399
|
-
vsri.64 q14, q4, #64-14
|
400
|
-
|
401
|
-
@ argA1 = Ba ^(~Be & Bi) ^ KeccakP1600RoundConstants[round]
|
402
|
-
@ argA2 = Be ^(~Bi & Bo)
|
403
|
-
@ argA3 = Bi ^(~Bo & Bu)
|
404
|
-
@ argA4 = Bo ^(~Bu & Ba)
|
405
|
-
@ argA5 = Bu ^(~Ba & Be)
|
406
|
-
vld1.64 { d30 }, [r1:64]
|
407
|
-
vbic.64 q0, q12, q11
|
408
|
-
vbic.64 q1, q13, q12
|
409
|
-
vld1.64 { d31 }, [r1:64]!
|
410
|
-
veor.64 q0, q10
|
411
|
-
vbic.64 q4, q11, q10
|
412
|
-
veor.64 q0, q15
|
413
|
-
vbic.64 q2, q14, q13
|
414
|
-
vbic.64 q3, q10, q14
|
415
|
-
|
416
|
-
m_pls \ofs1
|
417
|
-
veor.64 q1, q11
|
418
|
-
m_st q0, \next
|
419
|
-
m_pls \ofs2
|
420
|
-
veor.64 q2, q12
|
421
|
-
m_st q1, \next
|
422
|
-
m_pls \ofs3
|
423
|
-
veor.64 q3, q13
|
424
|
-
m_st q2, \next
|
425
|
-
m_pls \ofs4
|
426
|
-
veor.64 q4, q14
|
427
|
-
m_st q3, \next
|
428
|
-
m_pls \ofs5
|
429
|
-
m_st q4, \next
|
430
|
-
m_pls \ofsn1
|
431
|
-
.endm
|
432
|
-
|
433
|
-
.macro KeccakP_ThetaRhoPiChi ofs1, ofs2, ofs3, ofs4, ofs5, next, ofsn1, Bb1, Bb2, Bb3, Bb4, Bb5, Rr1, Rr2, Rr3, Rr4, Rr5
|
434
|
-
|
435
|
-
@ Bb1 = ROL64((argA1^Da), Rr1)
|
436
|
-
@ Bb2 = ROL64((argA2^De), Rr2)
|
437
|
-
@ Bb3 = ROL64((argA3^Di), Rr3)
|
438
|
-
@ Bb4 = ROL64((argA4^Do), Rr4)
|
439
|
-
@ Bb5 = ROL64((argA5^Du), Rr5)
|
440
|
-
|
441
|
-
.if \next != 16
|
442
|
-
mov r4, #\next
|
443
|
-
.endif
|
444
|
-
|
445
|
-
m_ld \Bb1, \next
|
446
|
-
m_pls \ofs2
|
447
|
-
m_ld \Bb2, \next
|
448
|
-
m_pls \ofs3
|
449
|
-
veor.64 q15, q5, \Bb1
|
450
|
-
m_ld \Bb3, \next
|
451
|
-
m_pls \ofs4
|
452
|
-
veor.64 q6, q6, \Bb2
|
453
|
-
m_ld \Bb4, \next
|
454
|
-
m_pls \ofs5
|
455
|
-
veor.64 q7, q7, \Bb3
|
456
|
-
m_ld \Bb5, \next
|
457
|
-
veor.64 q8, q8, \Bb4
|
458
|
-
veor.64 q9, q9, \Bb5
|
459
|
-
|
460
|
-
vshl.u64 \Bb1, q15, #\Rr1
|
461
|
-
vshl.u64 \Bb2, q6, #\Rr2
|
462
|
-
vshl.u64 \Bb3, q7, #\Rr3
|
463
|
-
vshl.u64 \Bb4, q8, #\Rr4
|
464
|
-
vshl.u64 \Bb5, q9, #\Rr5
|
465
|
-
|
466
|
-
vsri.64 \Bb1, q15, #64-\Rr1
|
467
|
-
vsri.64 \Bb2, q6, #64-\Rr2
|
468
|
-
vsri.64 \Bb3, q7, #64-\Rr3
|
469
|
-
vsri.64 \Bb4, q8, #64-\Rr4
|
470
|
-
vsri.64 \Bb5, q9, #64-\Rr5
|
471
|
-
|
472
|
-
@ argA1 = Ba ^((~Be)& Bi ), Ca ^= argA1
|
473
|
-
@ argA2 = Be ^((~Bi)& Bo ), Ce ^= argA2
|
474
|
-
@ argA3 = Bi ^((~Bo)& Bu ), Ci ^= argA3
|
475
|
-
@ argA4 = Bo ^((~Bu)& Ba ), Co ^= argA4
|
476
|
-
@ argA5 = Bu ^((~Ba)& Be ), Cu ^= argA5
|
477
|
-
vbic.64 q15, q12, q11
|
478
|
-
mov r6, r5
|
479
|
-
vbic.64 q6, q13, q12
|
480
|
-
m_pls \ofs1
|
481
|
-
vbic.64 q7, q14, q13
|
482
|
-
vbic.64 q8, q10, q14
|
483
|
-
vbic.64 q9, q11, q10
|
484
|
-
|
485
|
-
veor.64 q15, q15, q10
|
486
|
-
veor.64 q6, q6, q11
|
487
|
-
|
488
|
-
m_st q15, \next
|
489
|
-
m_pls \ofs2
|
490
|
-
veor.64 q7, q7, q12
|
491
|
-
|
492
|
-
m_st q6, \next
|
493
|
-
m_pls \ofs3
|
494
|
-
veor.64 q1, q1, q6
|
495
|
-
vld1.64 { q6 }, [r6:128]!
|
496
|
-
veor.64 q8, q8, q13
|
497
|
-
|
498
|
-
m_st q7, \next
|
499
|
-
m_pls \ofs4
|
500
|
-
veor.64 q2, q2, q7
|
501
|
-
vld1.64 { q7 }, [r6:128]!
|
502
|
-
veor.64 q9, q9, q14
|
503
|
-
|
504
|
-
m_st q8, \next
|
505
|
-
m_pls \ofs5
|
506
|
-
veor.64 q3, q3, q8
|
507
|
-
|
508
|
-
m_st q9, \next
|
509
|
-
|
510
|
-
vld1.64 { q8 }, [r6:128]!
|
511
|
-
veor.64 q4, q4, q9
|
512
|
-
m_pls \ofsn1
|
513
|
-
vld1.64 { q9 }, [r6:128]!
|
514
|
-
veor.64 q0, q0, q15
|
515
|
-
.endm
|
516
|
-
|
517
|
-
.macro KeccakP_ThetaRhoPiChi1 ofs1, ofs2, ofs3, ofs4, ofs5, next, ofsn1
|
518
|
-
KeccakP_ThetaRhoPiChi \ofs1, \ofs2, \ofs3, \ofs4, \ofs5, \next, \ofsn1, q12, q13, q14, q10, q11, 3, 45, 61, 28, 20
|
519
|
-
.endm
|
520
|
-
|
521
|
-
.macro KeccakP_ThetaRhoPiChi2 ofs1, ofs2, ofs3, ofs4, ofs5, next, ofsn1
|
522
|
-
KeccakP_ThetaRhoPiChi \ofs1, \ofs2, \ofs3, \ofs4, \ofs5, \next, \ofsn1, q14, q10, q11, q12, q13, 18, 1, 6, 25, 8
|
523
|
-
.endm
|
524
|
-
|
525
|
-
.macro KeccakP_ThetaRhoPiChi3 ofs1, ofs2, ofs3, ofs4, ofs5, next, ofsn1
|
526
|
-
KeccakP_ThetaRhoPiChi \ofs1, \ofs2, \ofs3, \ofs4, \ofs5, \next, \ofsn1, q11, q12, q13, q14, q10, 36, 10, 15, 56, 27
|
527
|
-
.endm
|
528
|
-
|
529
|
-
.macro KeccakP_ThetaRhoPiChi4 ofs1, ofs2, ofs3, ofs4, ofs5, next, ofsn1
|
530
|
-
|
531
|
-
@ Bo = ROL64((argA1^Da), 41)
|
532
|
-
@ Bu = ROL64((argA2^De), 2)
|
533
|
-
@ Ba = ROL64((argA3^Di), 62)
|
534
|
-
@ Be = ROL64((argA4^Do), 55)
|
535
|
-
@ Bi = ROL64((argA5^Du), 39)
|
536
|
-
@ KeccakChi
|
537
|
-
|
538
|
-
.if \next != 16
|
539
|
-
mov r4, #\next
|
540
|
-
.endif
|
541
|
-
|
542
|
-
m_ld q13, \next
|
543
|
-
m_pls \ofs2
|
544
|
-
m_ld q14, \next
|
545
|
-
m_pls \ofs3
|
546
|
-
veor.64 q5, q5, q13
|
547
|
-
m_ld q10, \next
|
548
|
-
m_pls \ofs4
|
549
|
-
veor.64 q6, q6, q14
|
550
|
-
m_ld q11, \next
|
551
|
-
m_pls \ofs5
|
552
|
-
veor.64 q7, q7, q10
|
553
|
-
m_ld q12, \next
|
554
|
-
veor.64 q8, q8, q11
|
555
|
-
veor.64 q9, q9, q12
|
556
|
-
|
557
|
-
vshl.u64 q13, q5, #41
|
558
|
-
vshl.u64 q14, q6, #2
|
559
|
-
vshl.u64 q10, q7, #62
|
560
|
-
vshl.u64 q11, q8, #55
|
561
|
-
vshl.u64 q12, q9, #39
|
562
|
-
|
563
|
-
vsri.64 q13, q5, #64-41
|
564
|
-
vsri.64 q14, q6, #64-2
|
565
|
-
vsri.64 q11, q8, #64-55
|
566
|
-
vsri.64 q12, q9, #64-39
|
567
|
-
vsri.64 q10, q7, #64-62
|
568
|
-
|
569
|
-
vbic.64 q5, q12, q11
|
570
|
-
vbic.64 q6, q13, q12
|
571
|
-
vbic.64 q7, q14, q13
|
572
|
-
vbic.64 q8, q10, q14
|
573
|
-
vbic.64 q9, q11, q10
|
574
|
-
veor.64 q5, q5, q10
|
575
|
-
veor.64 q6, q6, q11
|
576
|
-
veor.64 q7, q7, q12
|
577
|
-
veor.64 q8, q8, q13
|
578
|
-
m_pls \ofs1
|
579
|
-
veor.64 q9, q9, q14
|
580
|
-
m_st q5, \next
|
581
|
-
m_pls \ofs2
|
582
|
-
veor.64 q0, q0, q5
|
583
|
-
m_st q6, \next
|
584
|
-
m_pls \ofs3
|
585
|
-
veor.64 q1, q1, q6
|
586
|
-
m_st q7, \next
|
587
|
-
m_pls \ofs4
|
588
|
-
veor.64 q2, q2, q7
|
589
|
-
m_st q8, \next
|
590
|
-
m_pls \ofs5
|
591
|
-
veor.64 q3, q3, q8
|
592
|
-
m_st q9, \next
|
593
|
-
m_pls \ofsn1
|
594
|
-
veor.64 q4, q4, q9
|
595
|
-
.endm
|
596
|
-
|
597
|
-
@----------------------------------------------------------------------------
|
598
|
-
@
|
599
|
-
@ void KeccakP1600times2_StaticInitialize( void )
|
600
|
-
@
|
601
|
-
.align 8
|
602
|
-
.global KeccakP1600times2_StaticInitialize
|
603
|
-
.type KeccakP1600times2_StaticInitialize, %function;
|
604
|
-
KeccakP1600times2_StaticInitialize:
|
605
|
-
bx lr
|
606
|
-
|
607
|
-
|
608
|
-
@----------------------------------------------------------------------------
|
609
|
-
@
|
610
|
-
@ void KeccakP1600times2_InitializeAll( void *states )
|
611
|
-
@
|
612
|
-
.align 8
|
613
|
-
.global KeccakP1600times2_InitializeAll
|
614
|
-
.type KeccakP1600times2_InitializeAll, %function;
|
615
|
-
KeccakP1600times2_InitializeAll:
|
616
|
-
vmov.i64 q0, #0
|
617
|
-
vmov.i64 q1, #0
|
618
|
-
vmov.i64 q2, #0
|
619
|
-
vmov.i64 q3, #0
|
620
|
-
vstm r0!, { d0 - d7 } @ 8 (clear 8 lanes at a time)
|
621
|
-
vstm r0!, { d0 - d7 } @ 16
|
622
|
-
vstm r0!, { d0 - d7 } @ 24
|
623
|
-
vstm r0!, { d0 - d7 } @ 32
|
624
|
-
vstm r0!, { d0 - d7 } @ 40
|
625
|
-
vstm r0!, { d0 - d7 } @ 48
|
626
|
-
vstm r0!, { d0 - d1} @ 50
|
627
|
-
bx lr
|
628
|
-
|
629
|
-
|
630
|
-
|
631
|
-
@----------------------------------------------------------------------------
|
632
|
-
@
|
633
|
-
@ void KeccakP1600times2_AddByte( void *states, unsigned int instanceIndex, unsigned char byte, unsigned int offset )
|
634
|
-
@
|
635
|
-
.align 8
|
636
|
-
.global KeccakP1600times2_AddByte
|
637
|
-
.type KeccakP1600times2_AddByte, %function;
|
638
|
-
KeccakP1600times2_AddByte:
|
639
|
-
add r0, r0, r1, LSL #3 @ states += 8 * instanceIndex
|
640
|
-
lsr r1, r3, #3 @ states += (offset & ~7) * 2
|
641
|
-
add r0, r0, r1, LSL #4
|
642
|
-
and r3, r3, #7
|
643
|
-
add r0, r0, r3 @ states += offset & 7
|
644
|
-
ldrb r1, [r0]
|
645
|
-
eor r1, r1, r2
|
646
|
-
strb r1, [r0]
|
647
|
-
bx lr
|
648
|
-
|
649
|
-
|
650
|
-
@----------------------------------------------------------------------------
|
651
|
-
@
|
652
|
-
@ void KeccakP1600times2_AddBytes( void *states, unsigned int instanceIndex, const unsigned char *data,
|
653
|
-
@ unsigned int offset, unsigned int length )
|
654
|
-
@
|
655
|
-
.align 8
|
656
|
-
.global KeccakP1600times2_AddBytes
|
657
|
-
.type KeccakP1600times2_AddBytes, %function;
|
658
|
-
KeccakP1600times2_AddBytes:
|
659
|
-
add r0, r0, r1, LSL #3 @ states += 8 * instanceIndex
|
660
|
-
ldr r1, [sp, #0*4] @ r1 = length
|
661
|
-
cmp r1, #0
|
662
|
-
beq KeccakP1600times2_AddBytes_Exit
|
663
|
-
push { r4- r7 }
|
664
|
-
lsr r4, r3, #3 @ states += (offset & ~7) * 2
|
665
|
-
add r0, r0, r4, LSL #4
|
666
|
-
ands r3, r3, #7 @ .if (offset & 7) != 0
|
667
|
-
beq KeccakP1600times2_AddBytes_CheckLanes
|
668
|
-
add r0, r0, r3 @ states += offset & 7
|
669
|
-
rsb r3, r3, #8 @ lenInLane = 8 - (offset & 7)
|
670
|
-
KeccakP1600times2_AddBytes_LoopBytesFirst:
|
671
|
-
ldrb r4, [r0]
|
672
|
-
ldrb r5, [r2], #1
|
673
|
-
eor r4, r4, r5
|
674
|
-
subs r1, r1, #1
|
675
|
-
strb r4, [r0], #1
|
676
|
-
beq KeccakP1600times2_AddBytes_Done
|
677
|
-
subs r3, r3, #1
|
678
|
-
bne KeccakP1600times2_AddBytes_LoopBytesFirst
|
679
|
-
add r0, r0, #8 @ states += 8 (next lane of current state part)
|
680
|
-
KeccakP1600times2_AddBytes_CheckLanes:
|
681
|
-
lsrs r3, r1, #3
|
682
|
-
beq KeccakP1600times2_AddBytes_CheckBytesLast
|
683
|
-
KeccakP1600times2_AddBytes_LoopLanes:
|
684
|
-
ldr r4, [r0]
|
685
|
-
ldr r5, [r0, #4]
|
686
|
-
ldr r6, [r2], #4
|
687
|
-
ldr r7, [r2], #4
|
688
|
-
eor r4, r4, r6
|
689
|
-
eor r5, r5, r7
|
690
|
-
subs r3, r3, #1
|
691
|
-
str r4, [r0], #4
|
692
|
-
str r5, [r0], #12 @ states += 8 (next lane of current state part)
|
693
|
-
bne KeccakP1600times2_AddBytes_LoopLanes
|
694
|
-
KeccakP1600times2_AddBytes_CheckBytesLast:
|
695
|
-
ands r1, r1, #7
|
696
|
-
beq KeccakP1600times2_AddBytes_Done
|
697
|
-
KeccakP1600times2_AddBytes_LoopBytesLast:
|
698
|
-
ldrb r4, [r0]
|
699
|
-
ldrb r5, [r2], #1
|
700
|
-
eor r4, r4, r5
|
701
|
-
subs r1, r1, #1
|
702
|
-
strb r4, [r0], #1
|
703
|
-
bne KeccakP1600times2_AddBytes_LoopBytesLast
|
704
|
-
KeccakP1600times2_AddBytes_Done:
|
705
|
-
pop { r4- r7 }
|
706
|
-
KeccakP1600times2_AddBytes_Exit:
|
707
|
-
bx lr
|
708
|
-
|
709
|
-
|
710
|
-
@----------------------------------------------------------------------------
|
711
|
-
@
|
712
|
-
@ void KeccakP1600times2_AddLanesAll( void *states, const unsigned char *data, unsigned int laneCount, unsigned int laneOffset )
|
713
|
-
@
|
714
|
-
.align 8
|
715
|
-
.global KeccakP1600times2_AddLanesAll
|
716
|
-
.type KeccakP1600times2_AddLanesAll, %function;
|
717
|
-
KeccakP1600times2_AddLanesAll:
|
718
|
-
cmp r2, #0
|
719
|
-
beq KeccakP1600times2_AddLanesAll_Exit
|
720
|
-
add r3, r1, r3, LSL #3 @ r3: data + 8 * laneOffset
|
721
|
-
push {r4 - r7}
|
722
|
-
KeccakP1600times2_AddLanesAll_Loop:
|
723
|
-
ldr r4, [r1], #4 @ index 0
|
724
|
-
ldr r5, [r1], #4
|
725
|
-
ldrd r6, r7, [r0]
|
726
|
-
eor r6, r6, r4
|
727
|
-
eor r7, r7, r5
|
728
|
-
strd r6, r7, [r0], #8
|
729
|
-
ldr r4, [r3], #4 @ index 1
|
730
|
-
ldr r5, [r3], #4
|
731
|
-
ldrd r6, r7, [r0]
|
732
|
-
eor r6, r6, r4
|
733
|
-
eor r7, r7, r5
|
734
|
-
strd r6, r7, [r0], #8
|
735
|
-
subs r2, r2, #1
|
736
|
-
bne KeccakP1600times2_AddLanesAll_Loop
|
737
|
-
pop {r4 - r7}
|
738
|
-
KeccakP1600times2_AddLanesAll_Exit:
|
739
|
-
bx lr
|
740
|
-
|
741
|
-
|
742
|
-
@----------------------------------------------------------------------------
|
743
|
-
@
|
744
|
-
@ void KeccakP1600times2_OverwriteBytes( void *states, unsigned int instanceIndex, const unsigned char *data,
|
745
|
-
@ unsigned int offset, unsigned int length )
|
746
|
-
@
|
747
|
-
.align 8
|
748
|
-
.global KeccakP1600times2_OverwriteBytes
|
749
|
-
.type KeccakP1600times2_OverwriteBytes, %function;
|
750
|
-
KeccakP1600times2_OverwriteBytes:
|
751
|
-
add r0, r0, r1, LSL #3 @ states += 8 * instanceIndex
|
752
|
-
ldr r1, [sp, #0*4] @ r1 = length
|
753
|
-
cmp r1, #0
|
754
|
-
beq KeccakP1600times2_OverwriteBytes_Exit
|
755
|
-
push { r4-r5 }
|
756
|
-
lsr r4, r3, #3 @ states += (offset & ~7) * 2
|
757
|
-
add r0, r0, r4, LSL #4
|
758
|
-
ands r3, r3, #7 @ .if (offset & 7) != 0
|
759
|
-
beq KeccakP1600times2_OverwriteBytes_CheckLanes
|
760
|
-
add r0, r0, r3 @ states += offset & 7
|
761
|
-
rsb r3, r3, #8 @ lenInLane = 8 - (offset & 7)
|
762
|
-
KeccakP1600times2_OverwriteBytes_LoopBytesFirst:
|
763
|
-
ldrb r4, [r2], #1
|
764
|
-
strb r4, [r0], #1
|
765
|
-
subs r1, r1, #1
|
766
|
-
beq KeccakP1600times2_OverwriteBytes_Done
|
767
|
-
subs r3, r3, #1
|
768
|
-
bne KeccakP1600times2_OverwriteBytes_LoopBytesFirst
|
769
|
-
add r0, r0, #8 @ states += 8 (next lane of current state part)
|
770
|
-
KeccakP1600times2_OverwriteBytes_CheckLanes:
|
771
|
-
lsrs r3, r1, #3
|
772
|
-
beq KeccakP1600times2_OverwriteBytes_CheckBytesLast
|
773
|
-
KeccakP1600times2_OverwriteBytes_LoopLanes:
|
774
|
-
ldr r4, [r2], #4
|
775
|
-
ldr r5, [r2], #4
|
776
|
-
str r4, [r0], #4
|
777
|
-
str r5, [r0], #12 @ states += 8 (next lane of current state part)
|
778
|
-
subs r3, r3, #1
|
779
|
-
bne KeccakP1600times2_OverwriteBytes_LoopLanes
|
780
|
-
KeccakP1600times2_OverwriteBytes_CheckBytesLast:
|
781
|
-
ands r1, r1, #7
|
782
|
-
beq KeccakP1600times2_OverwriteBytes_Done
|
783
|
-
KeccakP1600times2_OverwriteBytes_LoopBytesLast:
|
784
|
-
ldrb r4, [r2], #1
|
785
|
-
subs r1, r1, #1
|
786
|
-
strb r4, [r0], #1
|
787
|
-
bne KeccakP1600times2_OverwriteBytes_LoopBytesLast
|
788
|
-
KeccakP1600times2_OverwriteBytes_Done:
|
789
|
-
pop { r4- r5 }
|
790
|
-
KeccakP1600times2_OverwriteBytes_Exit:
|
791
|
-
bx lr
|
792
|
-
|
793
|
-
|
794
|
-
@----------------------------------------------------------------------------
|
795
|
-
@
|
796
|
-
@ KeccakP1600times2_OverwriteLanesAll( void *states, const unsigned char *data, unsigned int laneCount, unsigned int laneOffset )
|
797
|
-
@
|
798
|
-
.align 8
|
799
|
-
.global KeccakP1600times2_OverwriteLanesAll
|
800
|
-
.type KeccakP1600times2_OverwriteLanesAll, %function;
|
801
|
-
KeccakP1600times2_OverwriteLanesAll:
|
802
|
-
cmp r2, #0
|
803
|
-
beq KeccakP1600times2_OverwriteLanesAll_Exit
|
804
|
-
lsls r12, r1, #32-3
|
805
|
-
bne KeccakP1600times2_OverwriteLanesAll_Unaligned
|
806
|
-
add r3, r1, r3, LSL #3 @ r3(pointer instance 1): data + 8 * laneOffset
|
807
|
-
lsrs r2, r2, #1
|
808
|
-
bcc KeccakP1600times2_OverwriteLanesAll_LoopAligned
|
809
|
-
vldm r1!, { d0 }
|
810
|
-
vldm r3!, { d1 }
|
811
|
-
vstm r0!, { d0 - d1 }
|
812
|
-
beq KeccakP1600times2_OverwriteLanesAll_Exit
|
813
|
-
KeccakP1600times2_OverwriteLanesAll_LoopAligned:
|
814
|
-
vldm r1!, { d0 }
|
815
|
-
vldm r1!, { d2 }
|
816
|
-
vldm r3!, { d1 }
|
817
|
-
vldm r3!, { d3 }
|
818
|
-
subs r2, r2, #1
|
819
|
-
vstm r0!, { d0 - d3 }
|
820
|
-
bne KeccakP1600times2_OverwriteLanesAll_LoopAligned
|
821
|
-
bx lr
|
822
|
-
KeccakP1600times2_OverwriteLanesAll_Unaligned:
|
823
|
-
add r3, r1, r3, LSL #3 @ r3(pointer instance 1): data + 8 * laneOffset
|
824
|
-
push { r4, r5 }
|
825
|
-
KeccakP1600times2_OverwriteLanesAll_LoopUnaligned:
|
826
|
-
ldr r4, [r1], #4
|
827
|
-
ldr r5, [r1], #4
|
828
|
-
strd r4, r5, [r0], #8
|
829
|
-
ldr r4, [r3], #4
|
830
|
-
ldr r5, [r3], #4
|
831
|
-
subs r2, r2, #1
|
832
|
-
strd r4, r5, [r0], #8
|
833
|
-
bne KeccakP1600times2_OverwriteLanesAll_LoopUnaligned
|
834
|
-
pop { r4, r5 }
|
835
|
-
KeccakP1600times2_OverwriteLanesAll_Exit:
|
836
|
-
bx lr
|
837
|
-
|
838
|
-
|
839
|
-
@----------------------------------------------------------------------------
|
840
|
-
@
|
841
|
-
@ void KeccakP1600times2_OverwriteWithZeroes( void *states, unsigned int instanceIndex, unsigned int byteCount )
|
842
|
-
@
|
843
|
-
.align 8
|
844
|
-
.global KeccakP1600times2_OverwriteWithZeroes
|
845
|
-
.type KeccakP1600times2_OverwriteWithZeroes, %function;
|
846
|
-
KeccakP1600times2_OverwriteWithZeroes:
|
847
|
-
add r0, r0, r1, LSL #3 @ states += 8 * instanceIndex
|
848
|
-
lsrs r1, r2, #3 @ r1: laneCount
|
849
|
-
beq KeccakP1600times2_OverwriteWithZeroes_Bytes
|
850
|
-
vmov.i64 d0, #0
|
851
|
-
KeccakP1600times2_OverwriteWithZeroes_LoopLanes:
|
852
|
-
subs r1, r1, #1
|
853
|
-
vstm r0!, { d0 }
|
854
|
-
add r0, r0, #8
|
855
|
-
bne KeccakP1600times2_OverwriteWithZeroes_LoopLanes
|
856
|
-
KeccakP1600times2_OverwriteWithZeroes_Bytes:
|
857
|
-
ands r2, r2, #7 @ r2: byteCount remaining
|
858
|
-
beq KeccakP1600times2_OverwriteWithZeroes_Exit
|
859
|
-
movs r3, #0
|
860
|
-
KeccakP1600times2_OverwriteWithZeroes_LoopBytes:
|
861
|
-
subs r2, r2, #1
|
862
|
-
strb r3, [r0], #1
|
863
|
-
bne KeccakP1600times2_OverwriteWithZeroes_LoopBytes
|
864
|
-
KeccakP1600times2_OverwriteWithZeroes_Exit:
|
865
|
-
bx lr
|
866
|
-
|
867
|
-
|
868
|
-
@----------------------------------------------------------------------------
|
869
|
-
@
|
870
|
-
@ void KeccakP1600times2_ExtractBytes( void *states, unsigned int instanceIndex, const unsigned char *data,
|
871
|
-
@ unsigned int offset, unsigned int length )
|
872
|
-
@
|
873
|
-
.align 8
|
874
|
-
.global KeccakP1600times2_ExtractBytes
|
875
|
-
.type KeccakP1600times2_ExtractBytes, %function;
|
876
|
-
KeccakP1600times2_ExtractBytes:
|
877
|
-
add r0, r0, r1, LSL #3 @ states += 8 * instanceIndex
|
878
|
-
ldr r1, [sp, #0*4] @ r1 = length
|
879
|
-
cmp r1, #0
|
880
|
-
beq KeccakP1600times2_ExtractBytes_Exit
|
881
|
-
push { r4-r5 }
|
882
|
-
lsr r4, r3, #3 @ states += (offset & ~7) * 2
|
883
|
-
add r0, r0, r4, LSL #4
|
884
|
-
ands r3, r3, #7 @ .if (offset & 7) != 0
|
885
|
-
beq KeccakP1600times2_ExtractBytes_CheckLanes
|
886
|
-
add r0, r0, r3 @ states += offset & 7
|
887
|
-
rsb r3, r3, #8 @ lenInLane = 8 - (offset & 7)
|
888
|
-
KeccakP1600times2_ExtractBytes_LoopBytesFirst:
|
889
|
-
ldrb r4, [r0], #1
|
890
|
-
strb r4, [r2], #1
|
891
|
-
subs r1, r1, #1
|
892
|
-
beq KeccakP1600times2_ExtractBytes_Done
|
893
|
-
subs r3, r3, #1
|
894
|
-
bne KeccakP1600times2_ExtractBytes_LoopBytesFirst
|
895
|
-
add r0, r0, #8 @ states += 8 (next lane of current state part)
|
896
|
-
KeccakP1600times2_ExtractBytes_CheckLanes:
|
897
|
-
lsrs r3, r1, #3
|
898
|
-
beq KeccakP1600times2_ExtractBytes_CheckBytesLast
|
899
|
-
KeccakP1600times2_ExtractBytes_LoopLanes:
|
900
|
-
ldr r4, [r0], #4
|
901
|
-
ldr r5, [r0], #12 @ states += 8 (next lane of current state part)
|
902
|
-
str r4, [r2], #4
|
903
|
-
str r5, [r2], #4
|
904
|
-
subs r3, r3, #1
|
905
|
-
bne KeccakP1600times2_ExtractBytes_LoopLanes
|
906
|
-
KeccakP1600times2_ExtractBytes_CheckBytesLast:
|
907
|
-
ands r1, r1, #7
|
908
|
-
beq KeccakP1600times2_ExtractBytes_Done
|
909
|
-
KeccakP1600times2_ExtractBytes_LoopBytesLast:
|
910
|
-
ldrb r4, [r0], #1
|
911
|
-
subs r1, r1, #1
|
912
|
-
strb r4, [r2], #1
|
913
|
-
bne KeccakP1600times2_ExtractBytes_LoopBytesLast
|
914
|
-
KeccakP1600times2_ExtractBytes_Done:
|
915
|
-
pop { r4-r5 }
|
916
|
-
KeccakP1600times2_ExtractBytes_Exit:
|
917
|
-
bx lr
|
918
|
-
|
919
|
-
|
920
|
-
@----------------------------------------------------------------------------
|
921
|
-
@
|
922
|
-
@ void KeccakP1600times2_ExtractLanesAll( const void *states, unsigned char *data, unsigned int laneCount, unsigned int laneOffset )
|
923
|
-
@
|
924
|
-
.align 8
|
925
|
-
.global KeccakP1600times2_ExtractLanesAll
|
926
|
-
.type KeccakP1600times2_ExtractLanesAll, %function;
|
927
|
-
KeccakP1600times2_ExtractLanesAll:
|
928
|
-
cmp r2, #0
|
929
|
-
beq KeccakP1600times2_ExtractLanesAll_Exit
|
930
|
-
lsls r12, r1, #32-3
|
931
|
-
bne KeccakP1600times2_ExtractLanesAll_Unaligned
|
932
|
-
add r3, r1, r3, LSL #3 @ r3(pointer instance 1): data + 8 * laneOffset
|
933
|
-
lsrs r2, r2, #1
|
934
|
-
bcc KeccakP1600times2_ExtractLanesAll_LoopAligned
|
935
|
-
vldm r0!, { d0 - d1 }
|
936
|
-
vstm r1!, { d0 }
|
937
|
-
vstm r3!, { d1 }
|
938
|
-
beq KeccakP1600times2_ExtractLanesAll_Exit
|
939
|
-
KeccakP1600times2_ExtractLanesAll_LoopAligned:
|
940
|
-
vldm r0!, { d0 - d3 }
|
941
|
-
subs r2, r2, #1
|
942
|
-
vstm r1!, { d0 }
|
943
|
-
vstm r1!, { d2 }
|
944
|
-
vstm r3!, { d1 }
|
945
|
-
vstm r3!, { d3 }
|
946
|
-
bne KeccakP1600times2_ExtractLanesAll_LoopAligned
|
947
|
-
bx lr
|
948
|
-
KeccakP1600times2_ExtractLanesAll_Unaligned:
|
949
|
-
add r3, r1, r3, LSL #3 @ r3(pointer instance 1): data + 8 * laneOffset
|
950
|
-
push { r4, r5 }
|
951
|
-
KeccakP1600times2_ExtractLanesAll_LoopUnaligned:
|
952
|
-
ldrd r4, r5, [r0], #8
|
953
|
-
str r4, [r1], #4
|
954
|
-
str r5, [r1], #4
|
955
|
-
ldrd r4, r5, [r0], #8
|
956
|
-
subs r2, r2, #1
|
957
|
-
str r4, [r3], #4
|
958
|
-
str r5, [r3], #4
|
959
|
-
bne KeccakP1600times2_ExtractLanesAll_LoopUnaligned
|
960
|
-
pop { r4, r5 }
|
961
|
-
KeccakP1600times2_ExtractLanesAll_Exit:
|
962
|
-
bx lr
|
963
|
-
|
964
|
-
|
965
|
-
@----------------------------------------------------------------------------
|
966
|
-
@
|
967
|
-
@ void KeccakP1600times2_ExtractAndAddBytes( void *states, unsigned int instanceIndex,
|
968
|
-
@ const unsigned char *input, unsigned char *output,
|
969
|
-
@ unsigned int offset, unsigned int length )
|
970
|
-
@
|
971
|
-
.align 8
|
972
|
-
.global KeccakP1600times2_ExtractAndAddBytes
|
973
|
-
.type KeccakP1600times2_ExtractAndAddBytes, %function;
|
974
|
-
KeccakP1600times2_ExtractAndAddBytes:
|
975
|
-
add r0, r0, r1, LSL #3 @ states += 8 * instanceIndex
|
976
|
-
ldr r1, [sp, #1*4] @ r1 = length
|
977
|
-
cmp r1, #0
|
978
|
-
beq KeccakP1600times2_ExtractAndAddBytes_Exit
|
979
|
-
push { r4 - r9 }
|
980
|
-
ldr r8, [sp, #6*4] @ r8 = offset
|
981
|
-
lsr r4, r8, #3 @ states += (offset & ~7) * 2
|
982
|
-
add r0, r0, r4, LSL #4
|
983
|
-
ands r8, r8, #7 @ .if (offset & 7) != 0
|
984
|
-
beq KeccakP1600times2_ExtractAndAddBytes_CheckLanes
|
985
|
-
add r0, r0, r8 @ states += offset & 7
|
986
|
-
rsb r8, r8, #8 @ lenInLane = 8 - (offset & 7)
|
987
|
-
KeccakP1600times2_ExtractAndAddBytes_LoopBytesFirst:
|
988
|
-
ldrb r4, [r0], #1
|
989
|
-
ldrb r5, [r2], #1
|
990
|
-
eor r4, r4, r5
|
991
|
-
strb r4, [r3], #1
|
992
|
-
subs r1, r1, #1
|
993
|
-
beq KeccakP1600times2_ExtractAndAddBytes_Done
|
994
|
-
subs r8, r8, #1
|
995
|
-
bne KeccakP1600times2_ExtractAndAddBytes_LoopBytesFirst
|
996
|
-
add r0, r0, #8 @ states += 8 (next lane of current state part)
|
997
|
-
KeccakP1600times2_ExtractAndAddBytes_CheckLanes:
|
998
|
-
lsrs r8, r1, #3
|
999
|
-
beq KeccakP1600times2_ExtractAndAddBytes_CheckBytesLast
|
1000
|
-
KeccakP1600times2_ExtractAndAddBytes_LoopLanes:
|
1001
|
-
ldr r4, [r0], #4
|
1002
|
-
ldr r5, [r0], #12
|
1003
|
-
ldr r6, [r2], #4
|
1004
|
-
ldr r7, [r2], #4
|
1005
|
-
eor r4, r4, r6
|
1006
|
-
eor r5, r5, r7
|
1007
|
-
str r4, [r3], #4
|
1008
|
-
str r5, [r3], #4 @ states += 8 (next lane of current state part)
|
1009
|
-
subs r8, r8, #1
|
1010
|
-
bne KeccakP1600times2_ExtractAndAddBytes_LoopLanes
|
1011
|
-
KeccakP1600times2_ExtractAndAddBytes_CheckBytesLast:
|
1012
|
-
ands r1, r1, #7
|
1013
|
-
beq KeccakP1600times2_ExtractAndAddBytes_Done
|
1014
|
-
KeccakP1600times2_ExtractAndAddBytes_LoopBytesLast:
|
1015
|
-
ldrb r4, [r0], #1
|
1016
|
-
ldrb r5, [r2], #1
|
1017
|
-
eor r4, r4, r5
|
1018
|
-
strb r4, [r3], #1
|
1019
|
-
subs r1, r1, #1
|
1020
|
-
bne KeccakP1600times2_ExtractAndAddBytes_LoopBytesLast
|
1021
|
-
KeccakP1600times2_ExtractAndAddBytes_Done:
|
1022
|
-
pop { r4 - r9 }
|
1023
|
-
KeccakP1600times2_ExtractAndAddBytes_Exit:
|
1024
|
-
bx lr
|
1025
|
-
|
1026
|
-
|
1027
|
-
@----------------------------------------------------------------------------
|
1028
|
-
@
|
1029
|
-
@ void KeccakP1600times2_ExtractAndAddLanesAll( const void *states,
|
1030
|
-
@ const unsigned char *input, unsigned char *output,
|
1031
|
-
@ unsigned int laneCount, unsigned int laneOffset )
|
1032
|
-
@
|
1033
|
-
.align 8
|
1034
|
-
.global KeccakP1600times2_ExtractAndAddLanesAll
|
1035
|
-
.type KeccakP1600times2_ExtractAndAddLanesAll, %function;
|
1036
|
-
KeccakP1600times2_ExtractAndAddLanesAll:
|
1037
|
-
cmp r3, #0
|
1038
|
-
beq KeccakP1600times2_ExtractAndAddLanesAll_Exit
|
1039
|
-
orr r12, r1, r2
|
1040
|
-
lsls r12, r12, #32-3 @ unaligned access .if input or output unaligned
|
1041
|
-
bne KeccakP1600times2_ExtractAndAddLanesAll_Unaligned
|
1042
|
-
push {r4,r5}
|
1043
|
-
ldr r12, [sp, #2*4] @ r12 = laneOffset
|
1044
|
-
lsrs r3, r3, #1
|
1045
|
-
add r4, r1, r12, LSL #3 @ r4(input instance 1): input + 8 * laneOffset
|
1046
|
-
add r5, r2, r12, LSL #3 @ r5(output instance 1): output + 8 * laneOffset
|
1047
|
-
bcc KeccakP1600times2_ExtractAndAddLanesAll_LoopAligned
|
1048
|
-
vldm r0!, { d0 - d1 }
|
1049
|
-
vldm r1!, { d2 }
|
1050
|
-
vldm r4!, { d3 }
|
1051
|
-
veor q0, q0, q1
|
1052
|
-
vstm r2!, { d0 }
|
1053
|
-
vstm r5!, { d1 }
|
1054
|
-
beq KeccakP1600times2_ExtractAndAddLanesAll_AlignedDone
|
1055
|
-
KeccakP1600times2_ExtractAndAddLanesAll_LoopAligned:
|
1056
|
-
vldm r0!, { d0 - d3 }
|
1057
|
-
vldm r1!, { d4 }
|
1058
|
-
vldm r1!, { d6 }
|
1059
|
-
vldm r4!, { d5 }
|
1060
|
-
vldm r4!, { d7 }
|
1061
|
-
subs r3, r3, #1
|
1062
|
-
veor q0, q0, q2
|
1063
|
-
veor q1, q1, q3
|
1064
|
-
vstm r2!, { d0 }
|
1065
|
-
vstm r2!, { d2 }
|
1066
|
-
vstm r5!, { d1 }
|
1067
|
-
vstm r5!, { d3 }
|
1068
|
-
bne KeccakP1600times2_ExtractAndAddLanesAll_LoopAligned
|
1069
|
-
KeccakP1600times2_ExtractAndAddLanesAll_AlignedDone:
|
1070
|
-
pop {r4,r5}
|
1071
|
-
bx lr
|
1072
|
-
KeccakP1600times2_ExtractAndAddLanesAll_Unaligned:
|
1073
|
-
push {r4-r9}
|
1074
|
-
ldr r12, [sp, #6*4] @ r12 = laneOffset
|
1075
|
-
add r4, r1, r12, LSL #3 @ r4(input instance 1): input + 8 * laneOffset
|
1076
|
-
add r5, r2, r12, LSL #3 @ r5(output instance 1): output + 8 * laneOffset
|
1077
|
-
KeccakP1600times2_ExtractAndAddLanesAll_LoopUnaligned:
|
1078
|
-
ldrd r8, r9, [r0], #8
|
1079
|
-
ldr r6, [r1], #4
|
1080
|
-
ldr r7, [r1], #4
|
1081
|
-
eor r8, r8, r6
|
1082
|
-
eor r9, r9, r7
|
1083
|
-
str r8, [r2], #4
|
1084
|
-
str r9, [r2], #4
|
1085
|
-
ldrd r8, r9, [r0], #8
|
1086
|
-
ldr r6, [r4], #4
|
1087
|
-
ldr r7, [r4], #4
|
1088
|
-
eor r8, r8, r6
|
1089
|
-
eor r9, r9, r7
|
1090
|
-
str r8, [r5], #4
|
1091
|
-
subs r3, r3, #1
|
1092
|
-
str r9, [r5], #4
|
1093
|
-
bne KeccakP1600times2_ExtractAndAddLanesAll_LoopUnaligned
|
1094
|
-
pop { r4 - r9 }
|
1095
|
-
KeccakP1600times2_ExtractAndAddLanesAll_Exit:
|
1096
|
-
bx lr
|
1097
|
-
|
1098
|
-
|
1099
|
-
@----------------------------------------------------------------------------
|
1100
|
-
@
|
1101
|
-
@ void KeccakP1600times2_PermuteAll_6rounds( void *states )
|
1102
|
-
@
|
1103
|
-
.align 8
|
1104
|
-
.global KeccakP1600times2_PermuteAll_6rounds
|
1105
|
-
.type KeccakP1600times2_PermuteAll_6rounds, %function;
|
1106
|
-
KeccakP1600times2_PermuteAll_6rounds:
|
1107
|
-
adr r1, KeccakP1600times2_Permute_RoundConstants6
|
1108
|
-
movs r2, #6+2
|
1109
|
-
vpush {q4-q7}
|
1110
|
-
push {r4-r7}
|
1111
|
-
sub sp, #4*2*8+8 @allocate 4 D double lanes (plus 8bytes to allow alignment on 16 bytes)
|
1112
|
-
add r5, sp, #8
|
1113
|
-
|
1114
|
-
@ ba
|
1115
|
-
@ be = me, me = be
|
1116
|
-
@ bi = gi, gi = bi
|
1117
|
-
@ bo = so, so = bo
|
1118
|
-
@ bu = ku, ku = bu
|
1119
|
-
|
1120
|
-
@ ga = sa, sa = ga
|
1121
|
-
@ ge = ke, ke = ge
|
1122
|
-
@ go = mo, mo = go
|
1123
|
-
@ gu
|
1124
|
-
|
1125
|
-
@ ka = ma, ma = ka
|
1126
|
-
@ ki = si, si = ki
|
1127
|
-
@ ko
|
1128
|
-
|
1129
|
-
@ mu = su, su = mu
|
1130
|
-
@ mi
|
1131
|
-
@ se
|
1132
|
-
|
1133
|
-
@PrepareTheta
|
1134
|
-
@ Ca = ba ^ ga ^ ka ^ ma ^ sa
|
1135
|
-
@ Ce = be ^ ge ^ ke ^ me ^ se
|
1136
|
-
@ Ci = bi ^ gi ^ ki ^ mi ^ si
|
1137
|
-
@ Co = bo ^ go ^ ko ^ mo ^ so
|
1138
|
-
@ Cu = bu ^ gu ^ ku ^ mu ^ su
|
1139
|
-
vldm r0, { q0 - q4 } @ ba be bi bo bu
|
1140
|
-
bic r5, #15
|
1141
|
-
add r3, r0, #_me
|
1142
|
-
vldm r3, { q6 } @ me
|
1143
|
-
vstm r3, { q1 }
|
1144
|
-
veor.64 q1, q1, q6
|
1145
|
-
add r4, r0, #_be
|
1146
|
-
vstm r4!, { q6 } @ be
|
1147
|
-
|
1148
|
-
add r3, r0, #_ga
|
1149
|
-
vldm r3, { q10 - q14 } @ ga ge gi go gu
|
1150
|
-
add r3, r0, #_gi
|
1151
|
-
vstm r3, { q2 }
|
1152
|
-
veor.64 q2, q2, q12
|
1153
|
-
vstm r4!, { q12 } @ bi
|
1154
|
-
|
1155
|
-
add r3, r0, #_so
|
1156
|
-
vldm r3, { q8 } @ so
|
1157
|
-
vstm r3, { q3 }
|
1158
|
-
veor.64 q3, q3, q8
|
1159
|
-
vstm r4!, { q8 } @ bo
|
1160
|
-
|
1161
|
-
add r3, r0, #_ku
|
1162
|
-
vldm r3, { q9 } @ ku
|
1163
|
-
vstm r3, { q4 }
|
1164
|
-
veor.64 q4, q4, q9
|
1165
|
-
vstm r4!, { q9 } @ bu
|
1166
|
-
|
1167
|
-
add r3, r0, #_sa
|
1168
|
-
vldm r3, { q5 } @ sa
|
1169
|
-
vstm r3, { q10 }
|
1170
|
-
add r4, r0, #_ga
|
1171
|
-
veor.64 q0, q0, q5
|
1172
|
-
veor.64 q0, q0, q10
|
1173
|
-
vstm r4!, { q5 } @ ga
|
1174
|
-
|
1175
|
-
add r3, r0, #_ke
|
1176
|
-
vldm r3, { q6 } @ ke
|
1177
|
-
vstm r3, { q11 }
|
1178
|
-
veor.64 q1, q1, q6
|
1179
|
-
veor.64 q1, q1, q11
|
1180
|
-
vstm r4!, { q6 } @ ge
|
1181
|
-
|
1182
|
-
add r3, r0, #_mo
|
1183
|
-
vldm r3, { q8 } @ mo
|
1184
|
-
vstm r3, { q13 }
|
1185
|
-
add r4, r0, #_go
|
1186
|
-
veor.64 q3, q3, q8
|
1187
|
-
veor.64 q3, q3, q13
|
1188
|
-
vstm r4!, { q8 } @ go
|
1189
|
-
veor.64 q4, q4, q14 @ gu
|
1190
|
-
|
1191
|
-
add r4, r0, #_ka @ ka
|
1192
|
-
vldm r4, { q10 }
|
1193
|
-
add r3, r0, #_ma
|
1194
|
-
vldm r3, { q5 } @ ma
|
1195
|
-
vstm r3, { q10 }
|
1196
|
-
veor.64 q0, q0, q5
|
1197
|
-
veor.64 q0, q0, q10
|
1198
|
-
vstm r4!, { q5 } @ ka
|
1199
|
-
|
1200
|
-
add r4, r0, #_ki @ ki ko
|
1201
|
-
vldm r4, { q12, q13 }
|
1202
|
-
add r3, r0, #_si
|
1203
|
-
vldm r3, { q7 } @ si
|
1204
|
-
vstm r3, { q12 }
|
1205
|
-
veor.64 q2, q2, q7
|
1206
|
-
veor.64 q2, q2, q12
|
1207
|
-
vstm r4, { q7 } @ ki
|
1208
|
-
veor.64 q3, q3, q13 @ ko
|
1209
|
-
|
1210
|
-
add r4, r0, #_mu @ mu
|
1211
|
-
vldm r4, { q14 }
|
1212
|
-
add r3, r0, #_su
|
1213
|
-
vldm r3, { q9 } @ su
|
1214
|
-
vstm r3, { q14 }
|
1215
|
-
veor.64 q4, q4, q9
|
1216
|
-
veor.64 q4, q4, q14
|
1217
|
-
vstm r4, { q9 } @ mu
|
1218
|
-
|
1219
|
-
add r4, r0, #_mi @ mi
|
1220
|
-
vldm r4, { q12 }
|
1221
|
-
veor.64 q2, q2, q12
|
1222
|
-
add r3, r0, #_se @ se
|
1223
|
-
vldm r3, { q6 }
|
1224
|
-
veor.64 q1, q1, q6
|
1225
|
-
|
1226
|
-
mov r3, r0
|
1227
|
-
b KeccakP1600times2_PermuteAll_Round2
|
1228
|
-
|
1229
|
-
|
1230
|
-
.align 8
|
1231
|
-
KeccakP1600times2_Permute_RoundConstants24:
|
1232
|
-
.quad 0x0000000000000001
|
1233
|
-
.quad 0x0000000000008082
|
1234
|
-
.quad 0x800000000000808a
|
1235
|
-
.quad 0x8000000080008000
|
1236
|
-
.quad 0x000000000000808b
|
1237
|
-
.quad 0x0000000080000001
|
1238
|
-
.quad 0x8000000080008081
|
1239
|
-
.quad 0x8000000000008009
|
1240
|
-
.quad 0x000000000000008a
|
1241
|
-
.quad 0x0000000000000088
|
1242
|
-
.quad 0x0000000080008009
|
1243
|
-
.quad 0x000000008000000a
|
1244
|
-
KeccakP1600times2_Permute_RoundConstants12:
|
1245
|
-
.quad 0x000000008000808b
|
1246
|
-
.quad 0x800000000000008b
|
1247
|
-
.quad 0x8000000000008089
|
1248
|
-
.quad 0x8000000000008003
|
1249
|
-
.quad 0x8000000000008002
|
1250
|
-
.quad 0x8000000000000080
|
1251
|
-
KeccakP1600times2_Permute_RoundConstants6:
|
1252
|
-
.quad 0x000000000000800a
|
1253
|
-
.quad 0x800000008000000a
|
1254
|
-
KeccakP1600times2_Permute_RoundConstants4:
|
1255
|
-
.quad 0x8000000080008081
|
1256
|
-
.quad 0x8000000000008080
|
1257
|
-
.quad 0x0000000080000001
|
1258
|
-
.quad 0x8000000080008008
|
1259
|
-
|
1260
|
-
@----------------------------------------------------------------------------
|
1261
|
-
@
|
1262
|
-
@ void KeccakP1600times2_PermuteAll_24rounds( void *states )
|
1263
|
-
@
|
1264
|
-
.align 8
|
1265
|
-
.global KeccakP1600times2_PermuteAll_24rounds
|
1266
|
-
.type KeccakP1600times2_PermuteAll_24rounds, %function;
|
1267
|
-
KeccakP1600times2_PermuteAll_24rounds:
|
1268
|
-
adr r1, KeccakP1600times2_Permute_RoundConstants24
|
1269
|
-
movs r2, #24
|
1270
|
-
b KeccakP1600times2_PermuteAll
|
1271
|
-
|
1272
|
-
|
1273
|
-
@----------------------------------------------------------------------------
|
1274
|
-
@
|
1275
|
-
@ void KeccakP1600times2_PermuteAll_12rounds( void *states )
|
1276
|
-
@
|
1277
|
-
.align 8
|
1278
|
-
.global KeccakP1600times2_PermuteAll_12rounds
|
1279
|
-
.type KeccakP1600times2_PermuteAll_12rounds, %function;
|
1280
|
-
KeccakP1600times2_PermuteAll_12rounds:
|
1281
|
-
adr r1, KeccakP1600times2_Permute_RoundConstants12
|
1282
|
-
movs r2, #12
|
1283
|
-
b KeccakP1600times2_PermuteAll
|
1284
|
-
|
1285
|
-
|
1286
|
-
@----------------------------------------------------------------------------
|
1287
|
-
@
|
1288
|
-
@ void KeccakP1600times2_PermuteAll_4rounds( void *states )
|
1289
|
-
@
|
1290
|
-
.align 8
|
1291
|
-
.global KeccakP1600times2_PermuteAll_4rounds
|
1292
|
-
.type KeccakP1600times2_PermuteAll_4rounds, %function;
|
1293
|
-
KeccakP1600times2_PermuteAll_4rounds:
|
1294
|
-
adr r1, KeccakP1600times2_Permute_RoundConstants4
|
1295
|
-
movs r2, #4
|
1296
|
-
b KeccakP1600times2_PermuteAll
|
1297
|
-
|
1298
|
-
|
1299
|
-
@----------------------------------------------------------------------------
|
1300
|
-
@
|
1301
|
-
@ void KeccakP1600times2_PermuteAll( void *states, void *rc, unsigned int nr )
|
1302
|
-
@
|
1303
|
-
.align 8
|
1304
|
-
.type KeccakP1600times2_PermuteAll, %function;
|
1305
|
-
KeccakP1600times2_PermuteAll:
|
1306
|
-
vpush {q4-q7}
|
1307
|
-
push {r4-r7}
|
1308
|
-
sub sp, #4*2*8+8 @allocate 4 D double lanes (plus 8bytes to allow alignment on 16 bytes)
|
1309
|
-
mov r3, r0
|
1310
|
-
add r5, sp, #8
|
1311
|
-
|
1312
|
-
@PrepareTheta
|
1313
|
-
@ Ca = ba ^ ga ^ ka ^ ma ^ sa
|
1314
|
-
@ Ce = be ^ ge ^ ke ^ me ^ se
|
1315
|
-
@ Ci = bi ^ gi ^ ki ^ mi ^ si
|
1316
|
-
@ Co = bo ^ go ^ ko ^ mo ^ so
|
1317
|
-
@ Cu = bu ^ gu ^ ku ^ mu ^ su
|
1318
|
-
vld1.64 { d0, d1, d2, d3 }, [r3:256]! @ _ba _be
|
1319
|
-
bic r5, #15
|
1320
|
-
vld1.64 { d4, d5, d6, d7 }, [r3:256]! @ _bi _bo
|
1321
|
-
vld1.64 { d8, d9, d10, d11 }, [r3:256]! @ _bu _ga
|
1322
|
-
vld1.64 { d12, d13 }, [r3:128]! @ _ge
|
1323
|
-
veor.64 q0, q0, q5
|
1324
|
-
vld1.64 { d14, d15 }, [r3:128]! @ _gi
|
1325
|
-
veor.64 q1, q1, q6
|
1326
|
-
vld1.64 { d16, d17 }, [r3:128]! @ _go
|
1327
|
-
veor.64 q2, q2, q7
|
1328
|
-
vld1.64 { d18, d19 }, [r3:128]! @ _gu
|
1329
|
-
veor.64 q3, q3, q8
|
1330
|
-
vld1.64 { d10, d11 }, [r3:128]! @ _ka
|
1331
|
-
veor.64 q4, q4, q9
|
1332
|
-
vld1.64 { d12, d13 }, [r3:128]! @ _ke
|
1333
|
-
veor.64 q0, q0, q5
|
1334
|
-
vld1.64 { d14, d15 }, [r3:128]! @ _ki
|
1335
|
-
veor.64 q1, q1, q6
|
1336
|
-
vld1.64 { d16, d17 }, [r3:128]! @ _ko
|
1337
|
-
veor.64 q2, q2, q7
|
1338
|
-
vld1.64 { d18, d19 }, [r3:128]! @ _ku
|
1339
|
-
veor.64 q3, q3, q8
|
1340
|
-
vld1.64 { d10, d11 }, [r3:128]! @ _ma
|
1341
|
-
veor.64 q4, q4, q9
|
1342
|
-
vld1.64 { d12, d13 }, [r3:128]! @ _me
|
1343
|
-
veor.64 q0, q0, q5
|
1344
|
-
vld1.64 { d14, d15 }, [r3:128]! @ _mi
|
1345
|
-
veor.64 q1, q1, q6
|
1346
|
-
vld1.64 { d16, d17 }, [r3:128]! @ _mo
|
1347
|
-
veor.64 q2, q2, q7
|
1348
|
-
vld1.64 { d18, d19 }, [r3:128]! @ _mu
|
1349
|
-
veor.64 q3, q3, q8
|
1350
|
-
vld1.64 { d10, d11 }, [r3:128]! @ _sa
|
1351
|
-
veor.64 q4, q4, q9
|
1352
|
-
vld1.64 { d12, d13 }, [r3:128]! @ _se
|
1353
|
-
veor.64 q0, q0, q5
|
1354
|
-
vld1.64 { d14, d15 }, [r3:128]! @ _si
|
1355
|
-
veor.64 q1, q1, q6
|
1356
|
-
vld1.64 { d16, d17 }, [r3:128]! @ _so
|
1357
|
-
veor.64 q2, q2, q7
|
1358
|
-
vld1.64 { d18, d19 }, [r3:128]! @ _su
|
1359
|
-
mov r3, r0
|
1360
|
-
veor.64 q3, q3, q8
|
1361
|
-
veor.64 q4, q4, q9
|
1362
|
-
|
1363
|
-
KeccakP1600times2_PermuteAll_RoundLoop:
|
1364
|
-
KeccakP_ThetaRhoPiChiIota _ba, -1, -1, -1, -1, _ge-_ba, _ka @ _ba, _ge, _ki, _mo, _su
|
1365
|
-
KeccakP_ThetaRhoPiChi1 _ka, -1, -1, _bo, -1, _me-_ka, _sa @ _ka, _me, _si, _bo, _gu
|
1366
|
-
KeccakP_ThetaRhoPiChi2 _sa, _be, -1, -1, -1, _gi-_be, _ga @ _sa, _be, _gi, _ko, _mu
|
1367
|
-
KeccakP_ThetaRhoPiChi3 _ga, -1, -1, -1, _bu, _ke-_ga, _ma @ _ga, _ke, _mi, _so, _bu
|
1368
|
-
KeccakP_ThetaRhoPiChi4 _ma, -1, _bi, -1, -1, _se-_ma, _ba @ _ma, _se, _bi, _go, _ku
|
1369
|
-
|
1370
|
-
KeccakP_ThetaRhoPiChiIota _ba, -1, _gi, -1, _ku, _me-_ba, _sa @ _ba, _me, _gi, _so, _ku
|
1371
|
-
KeccakP_ThetaRhoPiChi1 _sa, _ke, _bi, -1, _gu, _mo-_bi, _ma @ _sa, _ke, _bi, _mo, _gu
|
1372
|
-
KeccakP_ThetaRhoPiChi2 _ma, _ge, -1, _ko, _bu, _si-_ge, _ka @ _ma, _ge, _si, _ko, _bu
|
1373
|
-
KeccakP_ThetaRhoPiChi3 _ka, _be, -1, _go, -1, _mi-_be, _ga @ _ka, _be, _mi, _go, _su
|
1374
|
-
KeccakP_ThetaRhoPiChi4 _ga, -1, _ki, _bo, -1, _se-_ga, _ba @ _ga, _se, _ki, _bo, _mu
|
1375
|
-
KeccakP1600times2_PermuteAll_Round2:
|
1376
|
-
KeccakP_ThetaRhoPiChiIota _ba, -1, -1, _go, -1, _ke-_ba, _ma @ _ba, _ke, _si, _go, _mu
|
1377
|
-
KeccakP_ThetaRhoPiChi1 _ma, _be, -1, -1, _gu, _ki-_be, _ga @ _ma, _be, _ki, _so, _gu
|
1378
|
-
KeccakP_ThetaRhoPiChi2 _ga, -1, _bi, -1, -1, _me-_ga, _sa @ _ga, _me, _bi, _ko, _su
|
1379
|
-
KeccakP_ThetaRhoPiChi3 _sa, _ge, -1, _bo, -1, _mi-_ge, _ka @ _sa, _ge, _mi, _bo, _ku
|
1380
|
-
KeccakP_ThetaRhoPiChi4 _ka, -1, _gi, -1, _bu, _se-_ka, _ba @ _ka, _se, _gi, _mo, _bu
|
1381
|
-
|
1382
|
-
KeccakP_ThetaRhoPiChiIota _ba, -1, -1, -1, -1, _be-_ba, _ga @ _ba, _be, _bi, _bo, _bu
|
1383
|
-
KeccakP_ThetaRhoPiChi1 _ga, -1, -1, -1, -1, _ge-_ga, _ka @ _ga, _ge, _gi, _go, _gu
|
1384
|
-
KeccakP_ThetaRhoPiChi2 _ka, -1, -1, -1, -1, _ke-_ka, _ma @ _ka, _ke, _ki, _ko, _ku
|
1385
|
-
KeccakP_ThetaRhoPiChi3 _ma, -1, -1, -1, -1, _me-_ma, _sa @ _ma, _me, _mi, _mo, _mu
|
1386
|
-
subs r2, #4
|
1387
|
-
KeccakP_ThetaRhoPiChi4 _sa, -1, -1, -1, -1, _se-_sa, _ba @ _sa, _se, _si, _so, _su
|
1388
|
-
bne KeccakP1600times2_PermuteAll_RoundLoop
|
1389
|
-
add sp, #4*2*8+8 @ free 4.5 D lanes
|
1390
|
-
pop {r4-r7}
|
1391
|
-
vpop {q4-q7}
|
1392
|
-
bx lr
|
1393
|
-
|
1394
|
-
|