[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 18/18] i386: AVX+AES helpers prep
From: |
Paolo Bonzini |
Subject: |
[PATCH 18/18] i386: AVX+AES helpers prep |
Date: |
Fri, 26 Aug 2022 00:14:11 +0200 |
From: Paul Brook <paul@nowt.org>
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>
---
target/i386/ops_sse.h | 49 +++++++++++++++++++++++--------------------
1 file changed, 26 insertions(+), 23 deletions(-)
diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 6b5d076685..1e8d8e5c15 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -2318,64 +2318,66 @@ void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env,
Reg *d, Reg *s,
void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
int i;
- Reg st = *d;
+ Reg st = *d; // v
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])]);
}
}
void glue(helper_aesdeclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
int i;
- Reg st = *d;
+ Reg st = *d; // v
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))]);
}
}
void glue(helper_aesenc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
int i;
- Reg st = *d;
+ Reg st = *d; // v
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])]);
}
}
void glue(helper_aesenclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
int i;
- Reg st = *d;
+ Reg st = *d; // v
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]);
}
}
@@ -2393,6 +2395,7 @@ 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
--
2.37.1
- [PATCH 12/18] i386: reimplement AVX comparison helpers, (continued)
- [PATCH 12/18] i386: reimplement AVX comparison helpers, Paolo Bonzini, 2022/08/25
- [PATCH 15/18] i386: Misc AVX helper prep, Paolo Bonzini, 2022/08/25
- [PATCH 13/18] i386: Dot product AVX helper prep, Paolo Bonzini, 2022/08/25
- [PATCH 16/18] i386: Rewrite blendv helpers, Paolo Bonzini, 2022/08/25
- [PATCH 17/18] i386: AVX pclmulqdq prep, Paolo Bonzini, 2022/08/25
- [PATCH 18/18] i386: AVX+AES helpers prep,
Paolo Bonzini <=
- Re: [PATCH 00/18] target/i386: make most SSE helpers generic in the vector size, Richard Henderson, 2022/08/25