Add simon-simd.cpp to file list and nmake file

Filelist.txt

@@ -274,6 +274,7 @@ simple.cpp
 simple.h
 siphash.h
 simon.cpp
+simon-simd.cpp
 simon.h
 skipjack.cpp
 skipjack.h

cryptest.nmake

@@ -47,9 +47,9 @@
 
 # If you use 'make sources' from Linux makefile, then add 'winpipes.cpp' to the list below.
 
-LIB_SRCS = cryptlib.cpp cpu.cpp integer.cpp 3way.cpp adler32.cpp algebra.cpp algparam.cpp arc4.cpp aria-simd.cpp aria.cpp ariatab.cpp asn.cpp authenc.cpp base32.cpp base64.cpp basecode.cpp bfinit.cpp blake2-simd.cpp blake2.cpp blowfish.cpp blumshub.cpp camellia.cpp cast.cpp casts.cpp cbcmac.cpp ccm.cpp chacha.cpp channels.cpp cmac.cpp crc-simd.cpp crc.cpp default.cpp des.cpp dessp.cpp dh.cpp dh2.cpp dll.cpp dsa.cpp eax.cpp ec2n.cpp eccrypto.cpp ecp.cpp elgamal.cpp emsa2.cpp eprecomp.cpp esign.cpp files.cpp filters.cpp fips140.cpp fipstest.cpp gcm-simd.cpp gcm.cpp gf256.cpp gf2_32.cpp gf2n.cpp gfpcrypt.cpp gost.cpp gzip.cpp hex.cpp hmac.cpp hrtimer.cpp ida.cpp idea.cpp iterhash.cpp kalyna.cpp kalynatab.cpp keccak.cpp luc.cpp mars.cpp marss.cpp md2.cpp md4.cpp md5.cpp misc.cpp modes.cpp mqueue.cpp mqv.cpp nbtheory.cpp neon-simd.cpp network.cpp oaep.cpp osrng.cpp padlkrng.cpp panama.cpp pkcspad.cpp poly1305.cpp polynomi.cpp pssr.cpp pubkey.cpp queue.cpp rabin.cpp randpool.cpp rc2.cpp rc5.cpp rc6.cpp rdrand.cpp rdtables.cpp rijndael-simd.cpp rijndael.cpp ripemd.cpp rng.cpp rsa.cpp rw.cpp safer.cpp salsa.cpp seal.cpp seed.cpp serpent.cpp sha-simd.cpp sha.cpp sha3.cpp shacal2-simd.cpp shacal2.cpp shark.cpp sharkbox.cpp simon.cpp skipjack.cpp sm3.cpp sm4.cpp socketft.cpp sosemanuk.cpp speck.cpp speck-simd.cpp square.cpp squaretb.cpp sse-simd.cpp strciphr.cpp tea.cpp tftables.cpp threefish.cpp tiger.cpp tigertab.cpp trdlocal.cpp ttmac.cpp twofish.cpp vmac.cpp wait.cpp wake.cpp whrlpool.cpp winpipes.cpp xtr.cpp xtrcrypt.cpp zdeflate.cpp zinflate.cpp zlib.cpp
+LIB_SRCS = cryptlib.cpp cpu.cpp integer.cpp 3way.cpp adler32.cpp algebra.cpp algparam.cpp arc4.cpp aria-simd.cpp aria.cpp ariatab.cpp asn.cpp authenc.cpp base32.cpp base64.cpp basecode.cpp bfinit.cpp blake2-simd.cpp blake2.cpp blowfish.cpp blumshub.cpp camellia.cpp cast.cpp casts.cpp cbcmac.cpp ccm.cpp chacha.cpp channels.cpp cmac.cpp crc-simd.cpp crc.cpp default.cpp des.cpp dessp.cpp dh.cpp dh2.cpp dll.cpp dsa.cpp eax.cpp ec2n.cpp eccrypto.cpp ecp.cpp elgamal.cpp emsa2.cpp eprecomp.cpp esign.cpp files.cpp filters.cpp fips140.cpp fipstest.cpp gcm-simd.cpp gcm.cpp gf256.cpp gf2_32.cpp gf2n.cpp gfpcrypt.cpp gost.cpp gzip.cpp hex.cpp hmac.cpp hrtimer.cpp ida.cpp idea.cpp iterhash.cpp kalyna.cpp kalynatab.cpp keccak.cpp luc.cpp mars.cpp marss.cpp md2.cpp md4.cpp md5.cpp misc.cpp modes.cpp mqueue.cpp mqv.cpp nbtheory.cpp neon-simd.cpp network.cpp oaep.cpp osrng.cpp padlkrng.cpp panama.cpp pkcspad.cpp poly1305.cpp polynomi.cpp pssr.cpp pubkey.cpp queue.cpp rabin.cpp randpool.cpp rc2.cpp rc5.cpp rc6.cpp rdrand.cpp rdtables.cpp rijndael-simd.cpp rijndael.cpp ripemd.cpp rng.cpp rsa.cpp rw.cpp safer.cpp salsa.cpp seal.cpp seed.cpp serpent.cpp sha-simd.cpp sha.cpp sha3.cpp shacal2-simd.cpp shacal2.cpp shark.cpp sharkbox.cpp simon.cpp simon-simd.cpp skipjack.cpp sm3.cpp sm4.cpp socketft.cpp sosemanuk.cpp speck.cpp speck-simd.cpp square.cpp squaretb.cpp sse-simd.cpp strciphr.cpp tea.cpp tftables.cpp threefish.cpp tiger.cpp tigertab.cpp trdlocal.cpp ttmac.cpp twofish.cpp vmac.cpp wait.cpp wake.cpp whrlpool.cpp winpipes.cpp xtr.cpp xtrcrypt.cpp zdeflate.cpp zinflate.cpp zlib.cpp
 
-LIB_OBJS = cryptlib.obj cpu.obj integer.obj 3way.obj adler32.obj algebra.obj algparam.obj arc4.obj aria-simd.obj aria.obj ariatab.obj asn.obj authenc.obj base32.obj base64.obj basecode.obj bfinit.obj blake2-simd.obj blake2.obj blowfish.obj blumshub.obj camellia.obj cast.obj casts.obj cbcmac.obj ccm.obj chacha.obj channels.obj cmac.obj crc-simd.obj crc.obj default.obj des.obj dessp.obj dh.obj dh2.obj dll.obj dsa.obj eax.obj ec2n.obj eccrypto.obj ecp.obj elgamal.obj emsa2.obj eprecomp.obj esign.obj files.obj filters.obj fips140.obj fipstest.obj gcm-simd.obj gcm.obj gf256.obj gf2_32.obj gf2n.obj gfpcrypt.obj gost.obj gzip.obj hex.obj hmac.obj hrtimer.obj ida.obj idea.obj iterhash.obj kalyna.obj kalynatab.obj keccak.obj luc.obj mars.obj marss.obj md2.obj md4.obj md5.obj misc.obj modes.obj mqueue.obj mqv.obj nbtheory.obj neon-simd.obj network.obj oaep.obj osrng.obj padlkrng.obj panama.obj pkcspad.obj poly1305.obj polynomi.obj pssr.obj pubkey.obj queue.obj rabin.obj randpool.obj rc2.obj rc5.obj rc6.obj rdrand.obj rdtables.obj rijndael-simd.obj rijndael.obj ripemd.obj rng.obj rsa.obj rw.obj safer.obj salsa.obj seal.obj seed.obj serpent.obj sha-simd.obj sha.obj sha3.obj shacal2-simd.obj shacal2.obj shark.obj sharkbox.obj simon.obj skipjack.obj sm3.obj sm4.obj socketft.obj sosemanuk.obj speck.obj speck-simd.obj square.obj squaretb.obj sse-simd.obj strciphr.obj tea.obj tftables.obj threefish.obj tiger.obj tigertab.obj trdlocal.obj ttmac.obj twofish.obj vmac.obj wait.obj wake.obj whrlpool.obj winpipes.obj xtr.obj xtrcrypt.obj zdeflate.obj zinflate.obj zlib.obj
+LIB_OBJS = cryptlib.obj cpu.obj integer.obj 3way.obj adler32.obj algebra.obj algparam.obj arc4.obj aria-simd.obj aria.obj ariatab.obj asn.obj authenc.obj base32.obj base64.obj basecode.obj bfinit.obj blake2-simd.obj blake2.obj blowfish.obj blumshub.obj camellia.obj cast.obj casts.obj cbcmac.obj ccm.obj chacha.obj channels.obj cmac.obj crc-simd.obj crc.obj default.obj des.obj dessp.obj dh.obj dh2.obj dll.obj dsa.obj eax.obj ec2n.obj eccrypto.obj ecp.obj elgamal.obj emsa2.obj eprecomp.obj esign.obj files.obj filters.obj fips140.obj fipstest.obj gcm-simd.obj gcm.obj gf256.obj gf2_32.obj gf2n.obj gfpcrypt.obj gost.obj gzip.obj hex.obj hmac.obj hrtimer.obj ida.obj idea.obj iterhash.obj kalyna.obj kalynatab.obj keccak.obj luc.obj mars.obj marss.obj md2.obj md4.obj md5.obj misc.obj modes.obj mqueue.obj mqv.obj nbtheory.obj neon-simd.obj network.obj oaep.obj osrng.obj padlkrng.obj panama.obj pkcspad.obj poly1305.obj polynomi.obj pssr.obj pubkey.obj queue.obj rabin.obj randpool.obj rc2.obj rc5.obj rc6.obj rdrand.obj rdtables.obj rijndael-simd.obj rijndael.obj ripemd.obj rng.obj rsa.obj rw.obj safer.obj salsa.obj seal.obj seed.obj serpent.obj sha-simd.obj sha.obj sha3.obj shacal2-simd.obj shacal2.obj shark.obj sharkbox.obj simon.obj simon-simd.obj skipjack.obj sm3.obj sm4.obj socketft.obj sosemanuk.obj speck.obj speck-simd.obj square.obj squaretb.obj sse-simd.obj strciphr.obj tea.obj tftables.obj threefish.obj tiger.obj tigertab.obj trdlocal.obj ttmac.obj twofish.obj vmac.obj wait.obj wake.obj whrlpool.obj winpipes.obj xtr.obj xtrcrypt.obj zdeflate.obj zinflate.obj zlib.obj
 
 TEST_SRCS = bench1.cpp bench2.cpp test.cpp validat0.cpp validat1.cpp validat2.cpp validat3.cpp datatest.cpp regtest1.cpp regtest2.cpp regtest3.cpp fipsalgt.cpp dlltest.cpp fipstest.cpp
 

cryptlib.vcxproj

@@ -1,4 +1,4 @@
-<?xml version="1.0" encoding="utf-8"?>
+<?xml version="1.0" encoding="utf-8"?>
 <Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
   <!-- Microsoft documentation for VCXPROJ file format is located at -->
   <!-- the following URL. The documentation leaves a lot to be desired. -->

cryptlib.vcxproj.filters

@@ -1,4 +1,4 @@
-<?xml version="1.0" encoding="utf-8"?>
+<?xml version="1.0" encoding="utf-8"?>
 <Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
   <ItemGroup>
     <Filter Include="Header Files">

speck-simd.cpp

@@ -103,7 +103,7 @@ inline uint64x2_t Shuffle64(const uint64x2_t& val)
 inline void SPECK128_Enc_Block(uint8x16_t &block0, const word64 *subkeys, unsigned int rounds)
 {
     // Hack ahead... Rearrange the data for vectorization. It is easier to permute
-    // the data in SPECK128_Enc_Blocks then SPECK128_AdvancedProcessBlocks_SSSE3.
+    // the data in SPECK128_Enc_Blocks then SPECK128_AdvancedProcessBlocks_NEON.
     // The zero block below is a "don't care". It is present so we can vectorize.
     uint8x16_t block1 = {0};
     uint64x2_t x1 = UnpackLow64<uint64x2_t>(block0, block1);
@@ -135,7 +135,7 @@ inline void SPECK128_Enc_6_Blocks(uint8x16_t &block0, uint8x16_t &block1,
             uint8x16_t &block5, const word64 *subkeys, unsigned int rounds)
 {
     // Hack ahead... Rearrange the data for vectorization. It is easier to permute
-    // the data in SPECK128_Enc_Blocks then SPECK128_AdvancedProcessBlocks_SSSE3.
+    // the data in SPECK128_Enc_Blocks then SPECK128_AdvancedProcessBlocks_NEON.
     uint64x2_t x1 = UnpackLow64<uint64x2_t>(block0, block1);
     uint64x2_t y1 = UnpackHigh64<uint64x2_t>(block0, block1);
     uint64x2_t x2 = UnpackLow64<uint64x2_t>(block2, block3);
@@ -189,7 +189,7 @@ inline void SPECK128_Enc_6_Blocks(uint8x16_t &block0, uint8x16_t &block1,
 inline void SPECK128_Dec_Block(uint8x16_t &block0, const word64 *subkeys, unsigned int rounds)
 {
     // Hack ahead... Rearrange the data for vectorization. It is easier to permute
-    // the data in SPECK128_Dec_Blocks then SPECK128_AdvancedProcessBlocks_SSSE3.
+    // the data in SPECK128_Dec_Blocks then SPECK128_AdvancedProcessBlocks_NEON.
     // The zero block below is a "don't care". It is present so we can vectorize.
     uint8x16_t block1 = {0};
     uint64x2_t x1 = UnpackLow64<uint64x2_t>(block0, block1);
@@ -221,7 +221,7 @@ inline void SPECK128_Dec_6_Blocks(uint8x16_t &block0, uint8x16_t &block1,
             uint8x16_t &block5, const word64 *subkeys, unsigned int rounds)
 {
     // Hack ahead... Rearrange the data for vectorization. It is easier to permute
-    // the data in SPECK128_Dec_Blocks then SPECK128_AdvancedProcessBlocks_SSSE3.
+    // the data in SPECK128_Dec_Blocks then SPECK128_AdvancedProcessBlocks_NEON.
     uint64x2_t x1 = UnpackLow64<uint64x2_t>(block0, block1);
     uint64x2_t y1 = UnpackHigh64<uint64x2_t>(block0, block1);
     uint64x2_t x2 = UnpackLow64<uint64x2_t>(block2, block3);