xemu-project/xemu
1
0
Fork 0
mirror of https://github.com/xemu-project/xemu.git synced 2024-11-27 05:20:50 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

target/i386: AVX+AES helpers prep

Browse Source 
Make the AES vector helpers AVX ready

No functional changes to existing helpers

Signed-off-by: Paul Brook <paul@nowt.org>
Message-Id: <20220424220204.2493824-22-paul@nowt.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Paul Brook 2022-04-24 23:01:43 +01:00 committed by Paolo Bonzini
parent 5a09df21f7
commit a64fc26919
1 changed files with 22 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
target/i386/ops_sse.h
View File

@ -2256,11 +2256,12 @@ void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
Reg st = *d;
Reg rk = *s;
for (i = 0 ; i < 4 ; i++) {
d->L(i) = rk.L(i) ^ bswap32(AES_Td0[st.B(AES_ishifts[4*i+0])] ^
AES_Td1[st.B(AES_ishifts[4*i+1])] ^
AES_Td2[st.B(AES_ishifts[4*i+2])] ^
AES_Td3[st.B(AES_ishifts[4*i+3])]);
for (i = 0 ; i < 2 << SHIFT ; i++) {
int j = i & 3;
d->L(i) = rk.L(i) ^ bswap32(AES_Td0[st.B(AES_ishifts[4 * j + 0])] ^
AES_Td1[st.B(AES_ishifts[4 * j + 1])] ^
AES_Td2[st.B(AES_ishifts[4 * j + 2])] ^
AES_Td3[st.B(AES_ishifts[4 * j + 3])]);
}
}
@ -2270,8 +2271,8 @@ void glue(helper_aesdeclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
Reg st = *d;
Reg rk = *s;
for (i = 0; i < 16; i++) {
d->B(i) = rk.B(i) ^ (AES_isbox[st.B(AES_ishifts[i])]);
for (i = 0; i < 8 << SHIFT; i++) {
d->B(i) = rk.B(i) ^ (AES_isbox[st.B(AES_ishifts[i & 15] + (i & ~15))]);
}
}
@ -2281,11 +2282,12 @@ void glue(helper_aesenc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
Reg st = *d;
Reg rk = *s;
for (i = 0 ; i < 4 ; i++) {
d->L(i) = rk.L(i) ^ bswap32(AES_Te0[st.B(AES_shifts[4*i+0])] ^
AES_Te1[st.B(AES_shifts[4*i+1])] ^
AES_Te2[st.B(AES_shifts[4*i+2])] ^
AES_Te3[st.B(AES_shifts[4*i+3])]);
for (i = 0 ; i < 2 << SHIFT ; i++) {
int j = i & 3;
d->L(i) = rk.L(i) ^ bswap32(AES_Te0[st.B(AES_shifts[4 * j + 0])] ^
AES_Te1[st.B(AES_shifts[4 * j + 1])] ^
AES_Te2[st.B(AES_shifts[4 * j + 2])] ^
AES_Te3[st.B(AES_shifts[4 * j + 3])]);
}
}
@ -2295,22 +2297,22 @@ void glue(helper_aesenclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
Reg st = *d;
Reg rk = *s;
for (i = 0; i < 16; i++) {
d->B(i) = rk.B(i) ^ (AES_sbox[st.B(AES_shifts[i])]);
for (i = 0; i < 8 << SHIFT; i++) {
d->B(i) = rk.B(i) ^ (AES_sbox[st.B(AES_shifts[i & 15] + (i & ~15))]);
}
}
#if SHIFT == 1
void glue(helper_aesimc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
int i;
Reg tmp = *s;
for (i = 0 ; i < 4 ; i++) {
d->L(i) = bswap32(AES_imc[tmp.B(4*i+0)][0] ^
AES_imc[tmp.B(4*i+1)][1] ^
AES_imc[tmp.B(4*i+2)][2] ^
AES_imc[tmp.B(4*i+3)][3]);
d->L(i) = bswap32(AES_imc[tmp.B(4 * i + 0)][0] ^
AES_imc[tmp.B(4 * i + 1)][1] ^
AES_imc[tmp.B(4 * i + 2)][2] ^
AES_imc[tmp.B(4 * i + 3)][3]);
}
}
@ -2328,6 +2330,7 @@ void glue(helper_aeskeygenassist, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
d->L(3) = (d->L(2) << 24 | d->L(2) >> 8) ^ ctrl;
}
#endif
#endif
#undef SSE_HELPER_S