On 9/1/25 23:38, 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)); \
+ int64_t partial_sum = 0; \
I think it's clear partial_sum should be the 32-bit type TD.
Indeed, I'm not sure why you don't just have
TD acc = ((TD *)vd)[HD(i)];
+ \
+ for (idx = 0; idx < 4; ++idx) { \
+ r1 = *((T1 *)r1_buf + HS1(idx)); \
+ r2 = *((T2 *)r2_buf + HS2(idx)); \
+ partial_sum += (r1 * r2); \
acc += r1 * r2;
+ } \
+ *((TD *)vd + HD(i)) = (acc + partial_sum) & MAKE_64BIT_MASK(0, 32); \
((TD *)vd)[HD(i)] = acc;
because that final mask is bogus.
r~
+}
+
+RVVCALL(OPMVV_VQDOTQ, vqdot_vv, QOP_SSS_B, H4, H1, H1)
+RVVCALL(OPMVV_VQDOTQ, vqdotu_vv, QOP_UUU_B, H4, H1, H1)
+RVVCALL(OPMVV_VQDOTQ, vqdotsu_vv, QOP_SUS_B, H4, H1, H1)
