@@ -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)
@@ -231,6 +230,30 @@ void HELPER(gvec_vgfma8)(void *v1, const void *v2, const void *v3,
q1[1] = do_gfma8(q2[1], q3[1], q4[1]);
}
+static inline uint64_t do_gfma16(uint64_t n, uint64_t m, uint64_t a)
+{
+ return clmul_16x2_even(n, m) ^ clmul_16x2_odd(n, m) ^ a;
+}
+
+void HELPER(gvec_vgfm16)(void *v1, const void *v2, const void *v3, uint32_t d)
+{
+ uint64_t *q1 = v1;
+ const uint64_t *q2 = v2, *q3 = v3;
+
+ q1[0] = do_gfma16(q2[0], q3[0], 0);
+ q1[1] = do_gfma16(q2[1], q3[1], 0);
+}
+
+void HELPER(gvec_vgfma16)(void *v1, const void *v2, const void *v3,
+ const void *v4, uint32_t d)
+{
+ uint64_t *q1 = v1;
+ const uint64_t *q2 = v2, *q3 = v3, *q4 = v4;
+
+ q1[0] = do_gfma16(q2[0], q3[0], q4[0]);
+ q1[1] = do_gfma16(q2[1], q3[1], q4[1]);
+}
+
#define DEF_VGFM(BITS, TBITS) \
void HELPER(gvec_vgfm##BITS)(void *v1, const void *v2, const void *v3, \
uint32_t desc) \
@@ -248,7 +271,6 @@ 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,
@@ -284,7 +306,6 @@ 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,
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 | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-)