[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 07/18] target/s390x: Use clmul_16* routines
From: |
Richard Henderson |
Subject: |
[PATCH 07/18] target/s390x: Use clmul_16* routines |
Date: |
Thu, 13 Jul 2023 22:14:24 +0100 |
Use generic routines for 16-bit carry-less multiply.
Remove our local version of galois_multiply16.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/s390x/tcg/vec_int_helper.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/target/s390x/tcg/vec_int_helper.c
b/target/s390x/tcg/vec_int_helper.c
index e110a7581a..523d6375bb 100644
--- a/target/s390x/tcg/vec_int_helper.c
+++ b/target/s390x/tcg/vec_int_helper.c
@@ -180,7 +180,6 @@ static uint##TBITS##_t
galois_multiply##BITS(uint##TBITS##_t a, \
}
\
return res;
\
}
-DEF_GALOIS_MULTIPLY(16, 32)
DEF_GALOIS_MULTIPLY(32, 64)
static S390Vector galois_multiply64(uint64_t a, uint64_t b)
@@ -226,6 +225,25 @@ void HELPER(gvec_vgfma8)(void *v1, const void *v2, const
void *v3,
*(Int128 *)v1 = int128_xor(r, *(Int128 *)v4);
}
+static Int128 do_gfm16(Int128 n, Int128 m)
+{
+ Int128 e = clmul_16x4_even(n, m);
+ Int128 o = clmul_16x4_odd(n, m);
+ return int128_xor(e, o);
+}
+
+void HELPER(gvec_vgfm16)(void *v1, const void *v2, const void *v3, uint32_t d)
+{
+ *(Int128 *)v1 = do_gfm16(*(const Int128 *)v2, *(const Int128 *)v3);
+}
+
+void HELPER(gvec_vgfma16)(void *v1, const void *v2, const void *v3,
+ const void *v4, uint32_t d)
+{
+ Int128 r = do_gfm16(*(const Int128 *)v2, *(const Int128 *)v3);
+ *(Int128 *)v1 = int128_xor(r, *(Int128 *)v4);
+}
+
#define DEF_VGFM(BITS, TBITS)
\
void HELPER(gvec_vgfm##BITS)(void *v1, const void *v2, const void *v3,
\
uint32_t desc)
\
@@ -243,7 +261,6 @@ void HELPER(gvec_vgfm##BITS)(void *v1, const void *v2,
const void *v3, \
s390_vec_write_element##TBITS(v1, i, d);
\
}
\
}
-DEF_VGFM(16, 32)
DEF_VGFM(32, 64)
void HELPER(gvec_vgfm64)(void *v1, const void *v2, const void *v3,
@@ -279,7 +296,6 @@ void HELPER(gvec_vgfma##BITS)(void *v1, const void *v2,
const void *v3, \
s390_vec_write_element##TBITS(v1, i, d);
\
}
\
}
-DEF_VGFMA(16, 32)
DEF_VGFMA(32, 64)
void HELPER(gvec_vgfma64)(void *v1, const void *v2, const void *v3,
--
2.34.1
- [RFC PATCH for-8.2 00/18] crypto: Provide clmul.h and host accel, Richard Henderson, 2023/07/13
- [PATCH 03/18] target/s390x: Use clmul_8* routines, Richard Henderson, 2023/07/13
- [PATCH 02/18] target/arm: Use clmul_8* routines, Richard Henderson, 2023/07/13
- [PATCH 10/18] target/arm: Use clmul_32* routines, Richard Henderson, 2023/07/13
- [PATCH 06/18] target/arm: Use clmul_16* routines, Richard Henderson, 2023/07/13
- [PATCH 07/18] target/s390x: Use clmul_16* routines,
Richard Henderson <=
- [PATCH 09/18] crypto: Add generic 32-bit carry-less multiply routines, Richard Henderson, 2023/07/13
- [PATCH 08/18] target/ppc: Use clmul_16* routines, Richard Henderson, 2023/07/13
- [PATCH 11/18] target/s390x: Use clmul_32* routines, Richard Henderson, 2023/07/13
- [PATCH 12/18] target/ppc: Use clmul_32* routines, Richard Henderson, 2023/07/13
- [PATCH 01/18] crypto: Add generic 8-bit carry-less multiply routines, Richard Henderson, 2023/07/13
- [PATCH 13/18] crypto: Add generic 64-bit carry-less multiply routine, Richard Henderson, 2023/07/13
- [PATCH 05/18] crypto: Add generic 16-bit carry-less multiply routines, Richard Henderson, 2023/07/13
- [PATCH 04/18] target/ppc: Use clmul_8* routines, Richard Henderson, 2023/07/13
- [PATCH 17/18] host/include/i386: Implement clmul.h, Richard Henderson, 2023/07/13