On 9/3/25 15:01, Max Chou wrote:
+#define OPMVV_VQDOTQ(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2)          \
+static void do_##NAME(void *vd, void *vs1, void *vs2, int i)            \
+{                                                                       \
+    int idx;                                                            \
+    T1 r1;                                                              \
+    T2 r2;                                                              \
+    TX1 *r1_buf = (TX1 *)vs1 + HD(i);                                   \
+    TX2 *r2_buf = (TX2 *)vs2 + HD(i);                                   \
+    TD acc = ((TD *)vd)[HD(i)];                                         \
+                                                                        \
+    for (idx = 0; idx < 4; ++idx) {                                     \
+        r1 = (TD)(*((T1 *)r1_buf + HS1(idx)));                          \
+        r2 = (TD)(*((T2 *)r2_buf + HS2(idx)));                          \
+        acc += r1 * r2;                                                 \
Incorrect typing or casting, take your pick.

I suggest

    for (int idx = 0; idx < 4; ++idx) {
        T1 r1 = ((T1 *)r1_buf)[HS1(idx)];
        T2 r2 = ((T2 *)r1_buf)[HS2(idx)];
        acc += (TD)r1 * (TD)r2;
    }


r~

Reply via email to