[DYNAREC] Optimized scalar AES impl in DynaRec (#3041)

* [DYNAREC] Optimized scalar AES impl

* [RV64_DYNAREC] Optimized AES with RVV

* [CI] Bump RISC-V toolchains

* [RV64_DYNAREC] Switch to scalar impl when xtheadvector is present

* [RV64_DYNAREC] Try to disable rvv aes kernels

* [RV64_DYNAREC] Reverted assembly aes functions

1 files changed, 179 insertions, 20 deletions

diff --git a/src/dynarec/dynarec_native_functions.c b/src/dynarec/dynarec_native_functions.c
index 0f8f5a39..d0a20b1c 100644
--- a/src/dynarec/dynarec_native_functions.c
+++ b/src/dynarec/dynarec_native_functions.c
@@ -303,6 +303,147 @@ void native_fprem1(x64emu_t* emu)
     }
 }
 
+const uint8_t ff_mult2[4][256] = {
+    // a = 0x0e
+    0x00, 0x0e, 0x1c, 0x12, 0x38, 0x36, 0x24, 0x2a, 0x70, 0x7e, 0x6c, 0x62, 0x48, 0x46, 0x54, 0x5a,
+    0xe0, 0xee, 0xfc, 0xf2, 0xd8, 0xd6, 0xc4, 0xca, 0x90, 0x9e, 0x8c, 0x82, 0xa8, 0xa6, 0xb4, 0xba,
+    0xdb, 0xd5, 0xc7, 0xc9, 0xe3, 0xed, 0xff, 0xf1, 0xab, 0xa5, 0xb7, 0xb9, 0x93, 0x9d, 0x8f, 0x81,
+    0x3b, 0x35, 0x27, 0x29, 0x03, 0x0d, 0x1f, 0x11, 0x4b, 0x45, 0x57, 0x59, 0x73, 0x7d, 0x6f, 0x61,
+    0xad, 0xa3, 0xb1, 0xbf, 0x95, 0x9b, 0x89, 0x87, 0xdd, 0xd3, 0xc1, 0xcf, 0xe5, 0xeb, 0xf9, 0xf7,
+    0x4d, 0x43, 0x51, 0x5f, 0x75, 0x7b, 0x69, 0x67, 0x3d, 0x33, 0x21, 0x2f, 0x05, 0x0b, 0x19, 0x17,
+    0x76, 0x78, 0x6a, 0x64, 0x4e, 0x40, 0x52, 0x5c, 0x06, 0x08, 0x1a, 0x14, 0x3e, 0x30, 0x22, 0x2c,
+    0x96, 0x98, 0x8a, 0x84, 0xae, 0xa0, 0xb2, 0xbc, 0xe6, 0xe8, 0xfa, 0xf4, 0xde, 0xd0, 0xc2, 0xcc,
+    0x41, 0x4f, 0x5d, 0x53, 0x79, 0x77, 0x65, 0x6b, 0x31, 0x3f, 0x2d, 0x23, 0x09, 0x07, 0x15, 0x1b,
+    0xa1, 0xaf, 0xbd, 0xb3, 0x99, 0x97, 0x85, 0x8b, 0xd1, 0xdf, 0xcd, 0xc3, 0xe9, 0xe7, 0xf5, 0xfb,
+    0x9a, 0x94, 0x86, 0x88, 0xa2, 0xac, 0xbe, 0xb0, 0xea, 0xe4, 0xf6, 0xf8, 0xd2, 0xdc, 0xce, 0xc0,
+    0x7a, 0x74, 0x66, 0x68, 0x42, 0x4c, 0x5e, 0x50, 0x0a, 0x04, 0x16, 0x18, 0x32, 0x3c, 0x2e, 0x20,
+    0xec, 0xe2, 0xf0, 0xfe, 0xd4, 0xda, 0xc8, 0xc6, 0x9c, 0x92, 0x80, 0x8e, 0xa4, 0xaa, 0xb8, 0xb6,
+    0x0c, 0x02, 0x10, 0x1e, 0x34, 0x3a, 0x28, 0x26, 0x7c, 0x72, 0x60, 0x6e, 0x44, 0x4a, 0x58, 0x56,
+    0x37, 0x39, 0x2b, 0x25, 0x0f, 0x01, 0x13, 0x1d, 0x47, 0x49, 0x5b, 0x55, 0x7f, 0x71, 0x63, 0x6d,
+    0xd7, 0xd9, 0xcb, 0xc5, 0xef, 0xe1, 0xf3, 0xfd, 0xa7, 0xa9, 0xbb, 0xb5, 0x9f, 0x91, 0x83, 0x8d,
+    // a = 0x09
+    0x00, 0x09, 0x12, 0x1b, 0x24, 0x2d, 0x36, 0x3f, 0x48, 0x41, 0x5a, 0x53, 0x6c, 0x65, 0x7e, 0x77,
+    0x90, 0x99, 0x82, 0x8b, 0xb4, 0xbd, 0xa6, 0xaf, 0xd8, 0xd1, 0xca, 0xc3, 0xfc, 0xf5, 0xee, 0xe7,
+    0x3b, 0x32, 0x29, 0x20, 0x1f, 0x16, 0x0d, 0x04, 0x73, 0x7a, 0x61, 0x68, 0x57, 0x5e, 0x45, 0x4c,
+    0xab, 0xa2, 0xb9, 0xb0, 0x8f, 0x86, 0x9d, 0x94, 0xe3, 0xea, 0xf1, 0xf8, 0xc7, 0xce, 0xd5, 0xdc,
+    0x76, 0x7f, 0x64, 0x6d, 0x52, 0x5b, 0x40, 0x49, 0x3e, 0x37, 0x2c, 0x25, 0x1a, 0x13, 0x08, 0x01,
+    0xe6, 0xef, 0xf4, 0xfd, 0xc2, 0xcb, 0xd0, 0xd9, 0xae, 0xa7, 0xbc, 0xb5, 0x8a, 0x83, 0x98, 0x91,
+    0x4d, 0x44, 0x5f, 0x56, 0x69, 0x60, 0x7b, 0x72, 0x05, 0x0c, 0x17, 0x1e, 0x21, 0x28, 0x33, 0x3a,
+    0xdd, 0xd4, 0xcf, 0xc6, 0xf9, 0xf0, 0xeb, 0xe2, 0x95, 0x9c, 0x87, 0x8e, 0xb1, 0xb8, 0xa3, 0xaa,
+    0xec, 0xe5, 0xfe, 0xf7, 0xc8, 0xc1, 0xda, 0xd3, 0xa4, 0xad, 0xb6, 0xbf, 0x80, 0x89, 0x92, 0x9b,
+    0x7c, 0x75, 0x6e, 0x67, 0x58, 0x51, 0x4a, 0x43, 0x34, 0x3d, 0x26, 0x2f, 0x10, 0x19, 0x02, 0x0b,
+    0xd7, 0xde, 0xc5, 0xcc, 0xf3, 0xfa, 0xe1, 0xe8, 0x9f, 0x96, 0x8d, 0x84, 0xbb, 0xb2, 0xa9, 0xa0,
+    0x47, 0x4e, 0x55, 0x5c, 0x63, 0x6a, 0x71, 0x78, 0x0f, 0x06, 0x1d, 0x14, 0x2b, 0x22, 0x39, 0x30,
+    0x9a, 0x93, 0x88, 0x81, 0xbe, 0xb7, 0xac, 0xa5, 0xd2, 0xdb, 0xc0, 0xc9, 0xf6, 0xff, 0xe4, 0xed,
+    0x0a, 0x03, 0x18, 0x11, 0x2e, 0x27, 0x3c, 0x35, 0x42, 0x4b, 0x50, 0x59, 0x66, 0x6f, 0x74, 0x7d,
+    0xa1, 0xa8, 0xb3, 0xba, 0x85, 0x8c, 0x97, 0x9e, 0xe9, 0xe0, 0xfb, 0xf2, 0xcd, 0xc4, 0xdf, 0xd6,
+    0x31, 0x38, 0x23, 0x2a, 0x15, 0x1c, 0x07, 0x0e, 0x79, 0x70, 0x6b, 0x62, 0x5d, 0x54, 0x4f, 0x46,
+    // a = 0x0d
+    0x00, 0x0d, 0x1a, 0x17, 0x34, 0x39, 0x2e, 0x23, 0x68, 0x65, 0x72, 0x7f, 0x5c, 0x51, 0x46, 0x4b,
+    0xd0, 0xdd, 0xca, 0xc7, 0xe4, 0xe9, 0xfe, 0xf3, 0xb8, 0xb5, 0xa2, 0xaf, 0x8c, 0x81, 0x96, 0x9b,
+    0xbb, 0xb6, 0xa1, 0xac, 0x8f, 0x82, 0x95, 0x98, 0xd3, 0xde, 0xc9, 0xc4, 0xe7, 0xea, 0xfd, 0xf0,
+    0x6b, 0x66, 0x71, 0x7c, 0x5f, 0x52, 0x45, 0x48, 0x03, 0x0e, 0x19, 0x14, 0x37, 0x3a, 0x2d, 0x20,
+    0x6d, 0x60, 0x77, 0x7a, 0x59, 0x54, 0x43, 0x4e, 0x05, 0x08, 0x1f, 0x12, 0x31, 0x3c, 0x2b, 0x26,
+    0xbd, 0xb0, 0xa7, 0xaa, 0x89, 0x84, 0x93, 0x9e, 0xd5, 0xd8, 0xcf, 0xc2, 0xe1, 0xec, 0xfb, 0xf6,
+    0xd6, 0xdb, 0xcc, 0xc1, 0xe2, 0xef, 0xf8, 0xf5, 0xbe, 0xb3, 0xa4, 0xa9, 0x8a, 0x87, 0x90, 0x9d,
+    0x06, 0x0b, 0x1c, 0x11, 0x32, 0x3f, 0x28, 0x25, 0x6e, 0x63, 0x74, 0x79, 0x5a, 0x57, 0x40, 0x4d,
+    0xda, 0xd7, 0xc0, 0xcd, 0xee, 0xe3, 0xf4, 0xf9, 0xb2, 0xbf, 0xa8, 0xa5, 0x86, 0x8b, 0x9c, 0x91,
+    0x0a, 0x07, 0x10, 0x1d, 0x3e, 0x33, 0x24, 0x29, 0x62, 0x6f, 0x78, 0x75, 0x56, 0x5b, 0x4c, 0x41,
+    0x61, 0x6c, 0x7b, 0x76, 0x55, 0x58, 0x4f, 0x42, 0x09, 0x04, 0x13, 0x1e, 0x3d, 0x30, 0x27, 0x2a,
+    0xb1, 0xbc, 0xab, 0xa6, 0x85, 0x88, 0x9f, 0x92, 0xd9, 0xd4, 0xc3, 0xce, 0xed, 0xe0, 0xf7, 0xfa,
+    0xb7, 0xba, 0xad, 0xa0, 0x83, 0x8e, 0x99, 0x94, 0xdf, 0xd2, 0xc5, 0xc8, 0xeb, 0xe6, 0xf1, 0xfc,
+    0x67, 0x6a, 0x7d, 0x70, 0x53, 0x5e, 0x49, 0x44, 0x0f, 0x02, 0x15, 0x18, 0x3b, 0x36, 0x21, 0x2c,
+    0x0c, 0x01, 0x16, 0x1b, 0x38, 0x35, 0x22, 0x2f, 0x64, 0x69, 0x7e, 0x73, 0x50, 0x5d, 0x4a, 0x47,
+    0xdc, 0xd1, 0xc6, 0xcb, 0xe8, 0xe5, 0xf2, 0xff, 0xb4, 0xb9, 0xae, 0xa3, 0x80, 0x8d, 0x9a, 0x97,
+    // a = 0x0b
+    0x00, 0x0b, 0x16, 0x1d, 0x2c, 0x27, 0x3a, 0x31, 0x58, 0x53, 0x4e, 0x45, 0x74, 0x7f, 0x62, 0x69,
+    0xb0, 0xbb, 0xa6, 0xad, 0x9c, 0x97, 0x8a, 0x81, 0xe8, 0xe3, 0xfe, 0xf5, 0xc4, 0xcf, 0xd2, 0xd9,
+    0x7b, 0x70, 0x6d, 0x66, 0x57, 0x5c, 0x41, 0x4a, 0x23, 0x28, 0x35, 0x3e, 0x0f, 0x04, 0x19, 0x12,
+    0xcb, 0xc0, 0xdd, 0xd6, 0xe7, 0xec, 0xf1, 0xfa, 0x93, 0x98, 0x85, 0x8e, 0xbf, 0xb4, 0xa9, 0xa2,
+    0xf6, 0xfd, 0xe0, 0xeb, 0xda, 0xd1, 0xcc, 0xc7, 0xae, 0xa5, 0xb8, 0xb3, 0x82, 0x89, 0x94, 0x9f,
+    0x46, 0x4d, 0x50, 0x5b, 0x6a, 0x61, 0x7c, 0x77, 0x1e, 0x15, 0x08, 0x03, 0x32, 0x39, 0x24, 0x2f,
+    0x8d, 0x86, 0x9b, 0x90, 0xa1, 0xaa, 0xb7, 0xbc, 0xd5, 0xde, 0xc3, 0xc8, 0xf9, 0xf2, 0xef, 0xe4,
+    0x3d, 0x36, 0x2b, 0x20, 0x11, 0x1a, 0x07, 0x0c, 0x65, 0x6e, 0x73, 0x78, 0x49, 0x42, 0x5f, 0x54,
+    0xf7, 0xfc, 0xe1, 0xea, 0xdb, 0xd0, 0xcd, 0xc6, 0xaf, 0xa4, 0xb9, 0xb2, 0x83, 0x88, 0x95, 0x9e,
+    0x47, 0x4c, 0x51, 0x5a, 0x6b, 0x60, 0x7d, 0x76, 0x1f, 0x14, 0x09, 0x02, 0x33, 0x38, 0x25, 0x2e,
+    0x8c, 0x87, 0x9a, 0x91, 0xa0, 0xab, 0xb6, 0xbd, 0xd4, 0xdf, 0xc2, 0xc9, 0xf8, 0xf3, 0xee, 0xe5,
+    0x3c, 0x37, 0x2a, 0x21, 0x10, 0x1b, 0x06, 0x0d, 0x64, 0x6f, 0x72, 0x79, 0x48, 0x43, 0x5e, 0x55,
+    0x01, 0x0a, 0x17, 0x1c, 0x2d, 0x26, 0x3b, 0x30, 0x59, 0x52, 0x4f, 0x44, 0x75, 0x7e, 0x63, 0x68,
+    0xb1, 0xba, 0xa7, 0xac, 0x9d, 0x96, 0x8b, 0x80, 0xe9, 0xe2, 0xff, 0xf4, 0xc5, 0xce, 0xd3, 0xd8,
+    0x7a, 0x71, 0x6c, 0x67, 0x56, 0x5d, 0x40, 0x4b, 0x22, 0x29, 0x34, 0x3f, 0x0e, 0x05, 0x18, 0x13,
+    0xca, 0xc1, 0xdc, 0xd7, 0xe6, 0xed, 0xf0, 0xfb, 0x92, 0x99, 0x84, 0x8f, 0xbe, 0xb5, 0xa8, 0xa3,
+};
+const uint8_t ff_mult3[4][256] = {
+    // a = 0x02
+    0x00, 0x02, 0x04, 0x06, 0x08, 0x0a, 0x0c, 0x0e, 0x10, 0x12, 0x14, 0x16, 0x18, 0x1a, 0x1c, 0x1e,
+    0x20, 0x22, 0x24, 0x26, 0x28, 0x2a, 0x2c, 0x2e, 0x30, 0x32, 0x34, 0x36, 0x38, 0x3a, 0x3c, 0x3e,
+    0x40, 0x42, 0x44, 0x46, 0x48, 0x4a, 0x4c, 0x4e, 0x50, 0x52, 0x54, 0x56, 0x58, 0x5a, 0x5c, 0x5e,
+    0x60, 0x62, 0x64, 0x66, 0x68, 0x6a, 0x6c, 0x6e, 0x70, 0x72, 0x74, 0x76, 0x78, 0x7a, 0x7c, 0x7e,
+    0x80, 0x82, 0x84, 0x86, 0x88, 0x8a, 0x8c, 0x8e, 0x90, 0x92, 0x94, 0x96, 0x98, 0x9a, 0x9c, 0x9e,
+    0xa0, 0xa2, 0xa4, 0xa6, 0xa8, 0xaa, 0xac, 0xae, 0xb0, 0xb2, 0xb4, 0xb6, 0xb8, 0xba, 0xbc, 0xbe,
+    0xc0, 0xc2, 0xc4, 0xc6, 0xc8, 0xca, 0xcc, 0xce, 0xd0, 0xd2, 0xd4, 0xd6, 0xd8, 0xda, 0xdc, 0xde,
+    0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee, 0xf0, 0xf2, 0xf4, 0xf6, 0xf8, 0xfa, 0xfc, 0xfe,
+    0x1b, 0x19, 0x1f, 0x1d, 0x13, 0x11, 0x17, 0x15, 0x0b, 0x09, 0x0f, 0x0d, 0x03, 0x01, 0x07, 0x05,
+    0x3b, 0x39, 0x3f, 0x3d, 0x33, 0x31, 0x37, 0x35, 0x2b, 0x29, 0x2f, 0x2d, 0x23, 0x21, 0x27, 0x25,
+    0x5b, 0x59, 0x5f, 0x5d, 0x53, 0x51, 0x57, 0x55, 0x4b, 0x49, 0x4f, 0x4d, 0x43, 0x41, 0x47, 0x45,
+    0x7b, 0x79, 0x7f, 0x7d, 0x73, 0x71, 0x77, 0x75, 0x6b, 0x69, 0x6f, 0x6d, 0x63, 0x61, 0x67, 0x65,
+    0x9b, 0x99, 0x9f, 0x9d, 0x93, 0x91, 0x97, 0x95, 0x8b, 0x89, 0x8f, 0x8d, 0x83, 0x81, 0x87, 0x85,
+    0xbb, 0xb9, 0xbf, 0xbd, 0xb3, 0xb1, 0xb7, 0xb5, 0xab, 0xa9, 0xaf, 0xad, 0xa3, 0xa1, 0xa7, 0xa5,
+    0xdb, 0xd9, 0xdf, 0xdd, 0xd3, 0xd1, 0xd7, 0xd5, 0xcb, 0xc9, 0xcf, 0xcd, 0xc3, 0xc1, 0xc7, 0xc5,
+    0xfb, 0xf9, 0xff, 0xfd, 0xf3, 0xf1, 0xf7, 0xf5, 0xeb, 0xe9, 0xef, 0xed, 0xe3, 0xe1, 0xe7, 0xe5,
+    // a = 0x01
+    0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
+    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
+    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
+    0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
+    0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
+    0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
+    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
+    0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+    0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
+    0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
+    0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
+    0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
+    0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
+    0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
+    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
+    // a = 0x01
+    0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
+    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
+    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
+    0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
+    0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
+    0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
+    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
+    0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+    0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
+    0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
+    0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
+    0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
+    0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
+    0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
+    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
+    // a = 0x03
+    0x00, 0x03, 0x06, 0x05, 0x0c, 0x0f, 0x0a, 0x09, 0x18, 0x1b, 0x1e, 0x1d, 0x14, 0x17, 0x12, 0x11,
+    0x30, 0x33, 0x36, 0x35, 0x3c, 0x3f, 0x3a, 0x39, 0x28, 0x2b, 0x2e, 0x2d, 0x24, 0x27, 0x22, 0x21,
+    0x60, 0x63, 0x66, 0x65, 0x6c, 0x6f, 0x6a, 0x69, 0x78, 0x7b, 0x7e, 0x7d, 0x74, 0x77, 0x72, 0x71,
+    0x50, 0x53, 0x56, 0x55, 0x5c, 0x5f, 0x5a, 0x59, 0x48, 0x4b, 0x4e, 0x4d, 0x44, 0x47, 0x42, 0x41,
+    0xc0, 0xc3, 0xc6, 0xc5, 0xcc, 0xcf, 0xca, 0xc9, 0xd8, 0xdb, 0xde, 0xdd, 0xd4, 0xd7, 0xd2, 0xd1,
+    0xf0, 0xf3, 0xf6, 0xf5, 0xfc, 0xff, 0xfa, 0xf9, 0xe8, 0xeb, 0xee, 0xed, 0xe4, 0xe7, 0xe2, 0xe1,
+    0xa0, 0xa3, 0xa6, 0xa5, 0xac, 0xaf, 0xaa, 0xa9, 0xb8, 0xbb, 0xbe, 0xbd, 0xb4, 0xb7, 0xb2, 0xb1,
+    0x90, 0x93, 0x96, 0x95, 0x9c, 0x9f, 0x9a, 0x99, 0x88, 0x8b, 0x8e, 0x8d, 0x84, 0x87, 0x82, 0x81,
+    0x9b, 0x98, 0x9d, 0x9e, 0x97, 0x94, 0x91, 0x92, 0x83, 0x80, 0x85, 0x86, 0x8f, 0x8c, 0x89, 0x8a,
+    0xab, 0xa8, 0xad, 0xae, 0xa7, 0xa4, 0xa1, 0xa2, 0xb3, 0xb0, 0xb5, 0xb6, 0xbf, 0xbc, 0xb9, 0xba,
+    0xfb, 0xf8, 0xfd, 0xfe, 0xf7, 0xf4, 0xf1, 0xf2, 0xe3, 0xe0, 0xe5, 0xe6, 0xef, 0xec, 0xe9, 0xea,
+    0xcb, 0xc8, 0xcd, 0xce, 0xc7, 0xc4, 0xc1, 0xc2, 0xd3, 0xd0, 0xd5, 0xd6, 0xdf, 0xdc, 0xd9, 0xda,
+    0x5b, 0x58, 0x5d, 0x5e, 0x57, 0x54, 0x51, 0x52, 0x43, 0x40, 0x45, 0x46, 0x4f, 0x4c, 0x49, 0x4a,
+    0x6b, 0x68, 0x6d, 0x6e, 0x67, 0x64, 0x61, 0x62, 0x73, 0x70, 0x75, 0x76, 0x7f, 0x7c, 0x79, 0x7a,
+    0x3b, 0x38, 0x3d, 0x3e, 0x37, 0x34, 0x31, 0x32, 0x23, 0x20, 0x25, 0x26, 0x2f, 0x2c, 0x29, 0x2a,
+    0x0b, 0x08, 0x0d, 0x0e, 0x07, 0x04, 0x01, 0x02, 0x13, 0x10, 0x15, 0x16, 0x1f, 0x1c, 0x19, 0x1a,
+};
+
 static uint8_t ff_mult(uint8_t a, uint8_t b)
 {
     int retval = 0;
@@ -329,10 +470,15 @@ void native_aesimc(x64emu_t* emu, int xmm)
     sse_regs_t eax1 = emu->xmm[xmm];
 
     for(int j=0; j<4; ++j) {
-        emu->xmm[xmm].ub[0+j*4] = ff_mult(0x0E, eax1.ub[0+j*4]) ^ ff_mult(0x0B, eax1.ub[1+j*4]) ^ ff_mult(0x0D, eax1.ub[2+j*4]) ^ ff_mult(0x09, eax1.ub[3+j*4]);
-        emu->xmm[xmm].ub[1+j*4] = ff_mult(0x09, eax1.ub[0+j*4]) ^ ff_mult(0x0E, eax1.ub[1+j*4]) ^ ff_mult(0x0B, eax1.ub[2+j*4]) ^ ff_mult(0x0D, eax1.ub[3+j*4]);
-        emu->xmm[xmm].ub[2+j*4] = ff_mult(0x0D, eax1.ub[0+j*4]) ^ ff_mult(0x09, eax1.ub[1+j*4]) ^ ff_mult(0x0E, eax1.ub[2+j*4]) ^ ff_mult(0x0B, eax1.ub[3+j*4]);
-        emu->xmm[xmm].ub[3+j*4] = ff_mult(0x0B, eax1.ub[0+j*4]) ^ ff_mult(0x0D, eax1.ub[1+j*4]) ^ ff_mult(0x09, eax1.ub[2+j*4]) ^ ff_mult(0x0E, eax1.ub[3+j*4]);
+        // 0x0E -> 0, 0x09 -> 1, 0x0D -> 2, 0x0B -> 3
+        // emu->xmm[xmm].ub[0+j*4] = ff_mult(0x0E, eax1.ub[0+j*4]) ^ ff_mult(0x0B, eax1.ub[1+j*4]) ^ ff_mult(0x0D, eax1.ub[2+j*4]) ^ ff_mult(0x09, eax1.ub[3+j*4]);
+        // emu->xmm[xmm].ub[1+j*4] = ff_mult(0x09, eax1.ub[0+j*4]) ^ ff_mult(0x0E, eax1.ub[1+j*4]) ^ ff_mult(0x0B, eax1.ub[2+j*4]) ^ ff_mult(0x0D, eax1.ub[3+j*4]);
+        // emu->xmm[xmm].ub[2+j*4] = ff_mult(0x0D, eax1.ub[0+j*4]) ^ ff_mult(0x09, eax1.ub[1+j*4]) ^ ff_mult(0x0E, eax1.ub[2+j*4]) ^ ff_mult(0x0B, eax1.ub[3+j*4]);
+        // emu->xmm[xmm].ub[3+j*4] = ff_mult(0x0B, eax1.ub[0+j*4]) ^ ff_mult(0x0D, eax1.ub[1+j*4]) ^ ff_mult(0x09, eax1.ub[2+j*4]) ^ ff_mult(0x0E, eax1.ub[3+j*4]);
+        emu->xmm[xmm].ub[0+j*4] = ff_mult2[0][eax1.ub[0+j*4]] ^ ff_mult2[3][eax1.ub[1+j*4]] ^ ff_mult2[2][eax1.ub[2+j*4]] ^ ff_mult2[1][eax1.ub[3+j*4]];
+        emu->xmm[xmm].ub[1+j*4] = ff_mult2[1][eax1.ub[0+j*4]] ^ ff_mult2[0][eax1.ub[1+j*4]] ^ ff_mult2[3][eax1.ub[2+j*4]] ^ ff_mult2[2][eax1.ub[3+j*4]];
+        emu->xmm[xmm].ub[2+j*4] = ff_mult2[2][eax1.ub[0+j*4]] ^ ff_mult2[1][eax1.ub[1+j*4]] ^ ff_mult2[0][eax1.ub[2+j*4]] ^ ff_mult2[3][eax1.ub[3+j*4]];
+        emu->xmm[xmm].ub[3+j*4] = ff_mult2[3][eax1.ub[0+j*4]] ^ ff_mult2[2][eax1.ub[1+j*4]] ^ ff_mult2[1][eax1.ub[2+j*4]] ^ ff_mult2[0][eax1.ub[3+j*4]];
     }
 }
 void native_aesimc_y(x64emu_t* emu, int ymm)
@@ -340,10 +486,14 @@ void native_aesimc_y(x64emu_t* emu, int ymm)
     sse_regs_t eay1 = emu->ymm[ymm];
 
     for(int j=0; j<4; ++j) {
-        emu->ymm[ymm].ub[0+j*4] = ff_mult(0x0E, eay1.ub[0+j*4]) ^ ff_mult(0x0B, eay1.ub[1+j*4]) ^ ff_mult(0x0D, eay1.ub[2+j*4]) ^ ff_mult(0x09, eay1.ub[3+j*4]);
-        emu->ymm[ymm].ub[1+j*4] = ff_mult(0x09, eay1.ub[0+j*4]) ^ ff_mult(0x0E, eay1.ub[1+j*4]) ^ ff_mult(0x0B, eay1.ub[2+j*4]) ^ ff_mult(0x0D, eay1.ub[3+j*4]);
-        emu->ymm[ymm].ub[2+j*4] = ff_mult(0x0D, eay1.ub[0+j*4]) ^ ff_mult(0x09, eay1.ub[1+j*4]) ^ ff_mult(0x0E, eay1.ub[2+j*4]) ^ ff_mult(0x0B, eay1.ub[3+j*4]);
-        emu->ymm[ymm].ub[3+j*4] = ff_mult(0x0B, eay1.ub[0+j*4]) ^ ff_mult(0x0D, eay1.ub[1+j*4]) ^ ff_mult(0x09, eay1.ub[2+j*4]) ^ ff_mult(0x0E, eay1.ub[3+j*4]);
+        // emu->ymm[ymm].ub[0+j*4] = ff_mult(0x0E, eay1.ub[0+j*4]) ^ ff_mult(0x0B, eay1.ub[1+j*4]) ^ ff_mult(0x0D, eay1.ub[2+j*4]) ^ ff_mult(0x09, eay1.ub[3+j*4]);
+        // emu->ymm[ymm].ub[1+j*4] = ff_mult(0x09, eay1.ub[0+j*4]) ^ ff_mult(0x0E, eay1.ub[1+j*4]) ^ ff_mult(0x0B, eay1.ub[2+j*4]) ^ ff_mult(0x0D, eay1.ub[3+j*4]);
+        // emu->ymm[ymm].ub[2+j*4] = ff_mult(0x0D, eay1.ub[0+j*4]) ^ ff_mult(0x09, eay1.ub[1+j*4]) ^ ff_mult(0x0E, eay1.ub[2+j*4]) ^ ff_mult(0x0B, eay1.ub[3+j*4]);
+        // emu->ymm[ymm].ub[3+j*4] = ff_mult(0x0B, eay1.ub[0+j*4]) ^ ff_mult(0x0D, eay1.ub[1+j*4]) ^ ff_mult(0x09, eay1.ub[2+j*4]) ^ ff_mult(0x0E, eay1.ub[3+j*4]);
+        emu->ymm[ymm].ub[0+j*4] = ff_mult2[0][eay1.ub[0+j*4]] ^ ff_mult2[3][eay1.ub[1+j*4]] ^ ff_mult2[2][eay1.ub[2+j*4]] ^ ff_mult2[1][eay1.ub[3+j*4]];
+        emu->ymm[ymm].ub[1+j*4] = ff_mult2[1][eay1.ub[0+j*4]] ^ ff_mult2[0][eay1.ub[1+j*4]] ^ ff_mult2[3][eay1.ub[2+j*4]] ^ ff_mult2[2][eay1.ub[3+j*4]];
+        emu->ymm[ymm].ub[2+j*4] = ff_mult2[2][eay1.ub[0+j*4]] ^ ff_mult2[1][eay1.ub[1+j*4]] ^ ff_mult2[0][eay1.ub[2+j*4]] ^ ff_mult2[3][eay1.ub[3+j*4]];
+        emu->ymm[ymm].ub[3+j*4] = ff_mult2[3][eay1.ub[0+j*4]] ^ ff_mult2[2][eay1.ub[1+j*4]] ^ ff_mult2[1][eay1.ub[2+j*4]] ^ ff_mult2[0][eay1.ub[3+j*4]];
     }
 }
 void native_aesmc(x64emu_t* emu, int xmm)
@@ -351,10 +501,15 @@ void native_aesmc(x64emu_t* emu, int xmm)
     sse_regs_t eax1 = emu->xmm[xmm];
 
     for(int j=0; j<4; ++j) {
-        emu->xmm[xmm].ub[0+j*4] = ff_mult(0x02, eax1.ub[0+j*4]) ^ ff_mult(0x03, eax1.ub[1+j*4]) ^               eax1.ub[2+j*4]  ^               eax1.ub[3+j*4] ;
-        emu->xmm[xmm].ub[1+j*4] =               eax1.ub[0+j*4]  ^ ff_mult(0x02, eax1.ub[1+j*4]) ^ ff_mult(0x03, eax1.ub[2+j*4]) ^               eax1.ub[3+j*4] ;
-        emu->xmm[xmm].ub[2+j*4] =               eax1.ub[0+j*4]  ^               eax1.ub[1+j*4]  ^ ff_mult(0x02, eax1.ub[2+j*4]) ^ ff_mult(0x03, eax1.ub[3+j*4]);
-        emu->xmm[xmm].ub[3+j*4] = ff_mult(0x03, eax1.ub[0+j*4]) ^               eax1.ub[1+j*4]  ^               eax1.ub[2+j*4]  ^ ff_mult(0x02, eax1.ub[3+j*4]);
+        // 0x02 -> 0, 0x01 -> 1, 0x01 -> 2, 0x03 -> 3
+        // emu->xmm[xmm].ub[0+j*4] = ff_mult(0x02, eax1.ub[0+j*4]) ^ ff_mult(0x03, eax1.ub[1+j*4]) ^               eax1.ub[2+j*4]  ^               eax1.ub[3+j*4] ;
+        // emu->xmm[xmm].ub[1+j*4] =               eax1.ub[0+j*4]  ^ ff_mult(0x02, eax1.ub[1+j*4]) ^ ff_mult(0x03, eax1.ub[2+j*4]) ^               eax1.ub[3+j*4] ;
+        // emu->xmm[xmm].ub[2+j*4] =               eax1.ub[0+j*4]  ^               eax1.ub[1+j*4]  ^ ff_mult(0x02, eax1.ub[2+j*4]) ^ ff_mult(0x03, eax1.ub[3+j*4]);
+        // emu->xmm[xmm].ub[3+j*4] = ff_mult(0x03, eax1.ub[0+j*4]) ^               eax1.ub[1+j*4]  ^               eax1.ub[2+j*4]  ^ ff_mult(0x02, eax1.ub[3+j*4]);
+        emu->xmm[xmm].ub[0+j*4] = ff_mult3[0][eax1.ub[0+j*4]] ^ ff_mult3[3][eax1.ub[1+j*4]] ^ ff_mult3[2][eax1.ub[2+j*4]] ^ ff_mult3[1][eax1.ub[3+j*4]];
+        emu->xmm[xmm].ub[1+j*4] = ff_mult3[1][eax1.ub[0+j*4]] ^ ff_mult3[0][eax1.ub[1+j*4]] ^ ff_mult3[3][eax1.ub[2+j*4]] ^ ff_mult3[2][eax1.ub[3+j*4]];
+        emu->xmm[xmm].ub[2+j*4] = ff_mult3[2][eax1.ub[0+j*4]] ^ ff_mult3[1][eax1.ub[1+j*4]] ^ ff_mult3[0][eax1.ub[2+j*4]] ^ ff_mult3[3][eax1.ub[3+j*4]];
+        emu->xmm[xmm].ub[3+j*4] = ff_mult3[3][eax1.ub[0+j*4]] ^ ff_mult3[2][eax1.ub[1+j*4]] ^ ff_mult3[1][eax1.ub[2+j*4]] ^ ff_mult3[0][eax1.ub[3+j*4]];
     }
 }
 void native_aesmc_y(x64emu_t* emu, int ymm)
@@ -362,16 +517,20 @@ void native_aesmc_y(x64emu_t* emu, int ymm)
     sse_regs_t eay1 = emu->ymm[ymm];
 
     for(int j=0; j<4; ++j) {
-        emu->ymm[ymm].ub[0+j*4] = ff_mult(0x02, eay1.ub[0+j*4]) ^ ff_mult(0x03, eay1.ub[1+j*4]) ^               eay1.ub[2+j*4]  ^               eay1.ub[3+j*4] ;
-        emu->ymm[ymm].ub[1+j*4] =               eay1.ub[0+j*4]  ^ ff_mult(0x02, eay1.ub[1+j*4]) ^ ff_mult(0x03, eay1.ub[2+j*4]) ^               eay1.ub[3+j*4] ;
-        emu->ymm[ymm].ub[2+j*4] =               eay1.ub[0+j*4]  ^               eay1.ub[1+j*4]  ^ ff_mult(0x02, eay1.ub[2+j*4]) ^ ff_mult(0x03, eay1.ub[3+j*4]);
-        emu->ymm[ymm].ub[3+j*4] = ff_mult(0x03, eay1.ub[0+j*4]) ^               eay1.ub[1+j*4]  ^               eay1.ub[2+j*4]  ^ ff_mult(0x02, eay1.ub[3+j*4]);
+        // emu->ymm[ymm].ub[0+j*4] = ff_mult(0x02, eay1.ub[0+j*4]) ^ ff_mult(0x03, eay1.ub[1+j*4]) ^               eay1.ub[2+j*4]  ^               eay1.ub[3+j*4] ;
+        // emu->ymm[ymm].ub[1+j*4] =               eay1.ub[0+j*4]  ^ ff_mult(0x02, eay1.ub[1+j*4]) ^ ff_mult(0x03, eay1.ub[2+j*4]) ^               eay1.ub[3+j*4] ;
+        // emu->ymm[ymm].ub[2+j*4] =               eay1.ub[0+j*4]  ^               eay1.ub[1+j*4]  ^ ff_mult(0x02, eay1.ub[2+j*4]) ^ ff_mult(0x03, eay1.ub[3+j*4]);
+        // emu->ymm[ymm].ub[3+j*4] = ff_mult(0x03, eay1.ub[0+j*4]) ^               eay1.ub[1+j*4]  ^               eay1.ub[2+j*4]  ^ ff_mult(0x02, eay1.ub[3+j*4]);
+        emu->ymm[ymm].ub[0+j*4] = ff_mult3[0][eay1.ub[0+j*4]] ^ ff_mult3[3][eay1.ub[1+j*4]] ^ ff_mult3[2][eay1.ub[2+j*4]] ^ ff_mult3[1][eay1.ub[3+j*4]];
+        emu->ymm[ymm].ub[1+j*4] = ff_mult3[1][eay1.ub[0+j*4]] ^ ff_mult3[0][eay1.ub[1+j*4]] ^ ff_mult3[3][eay1.ub[2+j*4]] ^ ff_mult3[2][eay1.ub[3+j*4]];
+        emu->ymm[ymm].ub[2+j*4] = ff_mult3[2][eay1.ub[0+j*4]] ^ ff_mult3[1][eay1.ub[1+j*4]] ^ ff_mult3[0][eay1.ub[2+j*4]] ^ ff_mult3[3][eay1.ub[3+j*4]];
+        emu->ymm[ymm].ub[3+j*4] = ff_mult3[3][eay1.ub[0+j*4]] ^ ff_mult3[2][eay1.ub[1+j*4]] ^ ff_mult3[1][eay1.ub[2+j*4]] ^ ff_mult3[0][eay1.ub[3+j*4]];
     }
 }
                                   //   A0 B1 C2 D3 E4 F5 G6 H7 I8 J9 Ka Lb Mc Nd Oe Pf
                                   //   A  N  K  H  E  B  O  L  I  F  C  P  M  J  G  D
-static const uint8_t invshiftrows[] = {0,13,10, 7, 4, 1,14,11, 8, 5, 2,15,12, 9, 6, 3};
-static const uint8_t invsubbytes[256] = {
+const uint8_t invshiftrows[] = {0,13,10, 7, 4, 1,14,11, 8, 5, 2,15,12, 9, 6, 3};
+const uint8_t invsubbytes[256] = {
     0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
     0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
     0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
@@ -411,8 +570,8 @@ void native_aesdlast_y(x64emu_t* emu, int ymm)
         emu->ymm[ymm].ub[i] = invsubbytes[eay1.ub[i]];
 
 }
-static const uint8_t shiftrows[] = {0, 5,10,15, 4, 9,14, 3, 8,13, 2, 7,12, 1, 6,11};
-static const uint8_t subbytes[256] = {
+const uint8_t shiftrows[] = {0, 5,10,15, 4, 9,14, 3, 8,13, 2, 7,12, 1, 6,11};
+const uint8_t subbytes[256] = {
     0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76,
     0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0,
     0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15,