target/s390x: Use clmul_32* routines

Use generic routines for 32-bit carry-less multiply.
Remove our local version of galois_multiply32.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

target/s390x/tcg/vec_int_helper.c

@@ -165,22 +165,6 @@ DEF_VCTZ(8)
 DEF_VCTZ(16)
 
 /* like binary multiplication, but XOR instead of addition */
-#define DEF_GALOIS_MULTIPLY(BITS, TBITS)                                       \
-static uint##TBITS##_t galois_multiply##BITS(uint##TBITS##_t a,                \
-                                             uint##TBITS##_t b)                \
-{                                                                              \
-    uint##TBITS##_t res = 0;                                                   \
-                                                                               \
-    while (b) {                                                                \
-        if (b & 0x1) {                                                         \
-            res = res ^ a;                                                     \
-        }                                                                      \
-        a = a << 1;                                                            \
-        b = b >> 1;                                                            \
-    }                                                                          \
-    return res;                                                                \
-}
-DEF_GALOIS_MULTIPLY(32, 64)
 
 static S390Vector galois_multiply64(uint64_t a, uint64_t b)
 {
@@ -254,24 +238,29 @@ void HELPER(gvec_vgfma16)(void *v1, const void *v2, const void *v3,
     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)                                    \
-{                                                                              \
-    int i;                                                                     \
-                                                                               \
-    for (i = 0; i < (128 / TBITS); i++) {                                      \
-        uint##BITS##_t a = s390_vec_read_element##BITS(v2, i * 2);             \
-        uint##BITS##_t b = s390_vec_read_element##BITS(v3, i * 2);             \
-        uint##TBITS##_t d = galois_multiply##BITS(a, b);                       \
-                                                                               \
-        a = s390_vec_read_element##BITS(v2, i * 2 + 1);                        \
-        b = s390_vec_read_element##BITS(v3, i * 2 + 1);                        \
-        d = d ^ galois_multiply32(a, b);                                       \
-        s390_vec_write_element##TBITS(v1, i, d);                               \
-    }                                                                          \
+static inline uint64_t do_gfma32(uint64_t n, uint64_t m, uint64_t a)
+{
+    return clmul_32(n, m) ^ clmul_32(n >> 32, m >> 32) ^ a;
+}
+
+void HELPER(gvec_vgfm32)(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_gfma32(q2[0], q3[0], 0);
+    q1[1] = do_gfma32(q2[1], q3[1], 0);
+}
+
+void HELPER(gvec_vgfma32)(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_gfma32(q2[0], q3[0], q4[0]);
+    q1[1] = do_gfma32(q2[1], q3[1], q4[1]);
 }
-DEF_VGFM(32, 64)
 
 void HELPER(gvec_vgfm64)(void *v1, const void *v2, const void *v3,
                          uint32_t desc)
@@ -288,26 +277,6 @@ void HELPER(gvec_vgfm64)(void *v1, const void *v2, const void *v3,
     s390_vec_xor(v1, &tmp1, &tmp2);
 }
 
-#define DEF_VGFMA(BITS, TBITS)                                                 \
-void HELPER(gvec_vgfma##BITS)(void *v1, const void *v2, const void *v3,        \
-                              const void *v4, uint32_t desc)                   \
-{                                                                              \
-    int i;                                                                     \
-                                                                               \
-    for (i = 0; i < (128 / TBITS); i++) {                                      \
-        uint##BITS##_t a = s390_vec_read_element##BITS(v2, i * 2);             \
-        uint##BITS##_t b = s390_vec_read_element##BITS(v3, i * 2);             \
-        uint##TBITS##_t d = galois_multiply##BITS(a, b);                       \
-                                                                               \
-        a = s390_vec_read_element##BITS(v2, i * 2 + 1);                        \
-        b = s390_vec_read_element##BITS(v3, i * 2 + 1);                        \
-        d = d ^ galois_multiply32(a, b);                                       \
-        d = d ^ s390_vec_read_element##TBITS(v4, i);                           \
-        s390_vec_write_element##TBITS(v1, i, d);                               \
-    }                                                                          \
-}
-DEF_VGFMA(32, 64)
-
 void HELPER(gvec_vgfma64)(void *v1, const void *v2, const void *v3,
                           const void *v4, uint32_t desc)
 {