arne
/
cryptopp
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Add IncrementPointerAndStore 

This speeds up XL C/C++ by 0.1 to 0.2 cpb
pull/484/merge
Jeffrey Walton 2017-09-22 20:35:18 -04:00
parent bb5be2979e
commit 12953fd0e4
No known key found for this signature in database
GPG Key ID: B36AB348921B1838
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
rijndael-simd.cpp
View File

@ -821,6 +821,13 @@ Rijndael_Subkey_POWER8(uint8x16_p8 r1, const uint8x16_p8 r4, const uint8x16_p8 r
return r1;
}
static inline uint8_t*
IncrementPointerAndStore(const uint8x16_p8& r, uint8_t* p)
{
VectorStore(r, (p += 16));
return p;
}
// We still need rcon and Se to fallback to C/C++ for AES-192 and AES-256.
// The IBM docs on AES sucks. Intel's docs on AESNI puts IBM to shame.
void Rijndael_UncheckedSetKey_POWER8(const byte* userKey, size_t keyLen, word32* rk,
@ -846,18 +853,18 @@ void Rijndael_UncheckedSetKey_POWER8(const byte* userKey, size_t keyLen, word32*
{
r1 = Rijndael_Subkey_POWER8(r1, r4, r5);
r4 = vec_add(r4, r4);
skptr += 16; VectorStore(r1, skptr);
skptr = IncrementPointerAndStore(r1, skptr);
}
/* Round 9 using rcon=0x1b */
r4 = (uint8x16_p8)VectorLoadKey(s_rcon[1]);
r1 = Rijndael_Subkey_POWER8(r1, r4, r5);
skptr += 16; VectorStore(r1, skptr);
skptr = IncrementPointerAndStore(r1, skptr);
/* Round 10 using rcon=0x36 */
r4 = (uint8x16_p8)VectorLoadKey(s_rcon[2]);
r1 = Rijndael_Subkey_POWER8(r1, r4, r5);
skptr += 16; VectorStore(r1, skptr);
skptr = IncrementPointerAndStore(r1, skptr);
}
else
{