[PATCH v3 03/19] target/s390x: Use clmul_8* routines

[Richard Henderson]

Use generic routines for 8-bit carry-less multiply.
Remove our local version of galois_multiply8.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/s390x/tcg/vec_int_helper.c | 32 ++++++++++++++++++++++++++++---
 1 file changed, 29 insertions(+), 3 deletions(-)

diff --git a/target/s390x/tcg/vec_int_helper.c 
b/target/s390x/tcg/vec_int_helper.c
index 53ab5c5eb3..edff4d6b2b 100644
--- a/target/s390x/tcg/vec_int_helper.c
+++ b/target/s390x/tcg/vec_int_helper.c
@@ -14,6 +14,7 @@
 #include "vec.h"
 #include "exec/helper-proto.h"
 #include "tcg/tcg-gvec-desc.h"
+#include "crypto/clmul.h"
 
 static bool s390_vec_is_zero(const S390Vector *v)
 {
@@ -179,7 +180,6 @@ static uint##TBITS##_t 
galois_multiply##BITS(uint##TBITS##_t a,                \
     }                                                                          
\
     return res;                                                                
\
 }
-DEF_GALOIS_MULTIPLY(8, 16)
 DEF_GALOIS_MULTIPLY(16, 32)
 DEF_GALOIS_MULTIPLY(32, 64)
 
@@ -203,6 +203,34 @@ static S390Vector galois_multiply64(uint64_t a, uint64_t b)
     return res;
 }
 
+/*
+ * There is no carry across the two doublewords, so their order does
+ * not matter.  Nor is there partial overlap between registers.
+ */
+static inline uint64_t do_gfma8(uint64_t n, uint64_t m, uint64_t a)
+{
+    return clmul_8x4_even(n, m) ^ clmul_8x4_odd(n, m) ^ a;
+}
+
+void HELPER(gvec_vgfm8)(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_gfma8(q2[0], q3[0], 0);
+    q1[1] = do_gfma8(q2[1], q3[1], 0);
+}
+
+void HELPER(gvec_vgfma8)(void *v1, const void *v2, const void *v3,
+                         const void *v4, uint32_t desc)
+{
+    uint64_t *q1 = v1;
+    const uint64_t *q2 = v2, *q3 = v3, *q4 = v4;
+
+    q1[0] = do_gfma8(q2[0], q3[0], q4[0]);
+    q1[1] = do_gfma8(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)                                    
\
@@ -220,7 +248,6 @@ void HELPER(gvec_vgfm##BITS)(void *v1, const void *v2, 
const void *v3,         \
         s390_vec_write_element##TBITS(v1, i, d);                               
\
     }                                                                          
\
 }
-DEF_VGFM(8, 16)
 DEF_VGFM(16, 32)
 DEF_VGFM(32, 64)
 
@@ -257,7 +284,6 @@ void HELPER(gvec_vgfma##BITS)(void *v1, const void *v2, 
const void *v3,        \
         s390_vec_write_element##TBITS(v1, i, d);                               
\
     }                                                                          
\
 }
-DEF_VGFMA(8, 16)
 DEF_VGFMA(16, 32)
 DEF_VGFMA(32, 64)
 
-- 
2.34.1