aboutsummaryrefslogtreecommitdiff
path: root/target/arm/vec_helper.c
diff options
context:
space:
mode:
Diffstat (limited to 'target/arm/vec_helper.c')
-rw-r--r--target/arm/vec_helper.c42
1 files changed, 41 insertions, 1 deletions
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 74a497f38c..27e9bdd329 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -2385,7 +2385,7 @@ static void do_mmla_b(void *vd, void *vn, void *vm, void *va, uint32_t desc,
* Process the entire segment at once, writing back the
* results only after we've consumed all of the inputs.
*
- * Key to indicies by column:
+ * Key to indices by column:
* i j i j
*/
sum0 = a[H4(0 + 0)];
@@ -2472,3 +2472,43 @@ void HELPER(gvec_bfdot_idx)(void *vd, void *vn, void *vm,
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
+
+void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
+{
+ intptr_t s, opr_sz = simd_oprsz(desc);
+ float32 *d = vd, *a = va;
+ uint32_t *n = vn, *m = vm;
+
+ for (s = 0; s < opr_sz / 4; s += 4) {
+ float32 sum00, sum01, sum10, sum11;
+
+ /*
+ * Process the entire segment at once, writing back the
+ * results only after we've consumed all of the inputs.
+ *
+ * Key to indicies by column:
+ * i j i k j k
+ */
+ sum00 = a[s + H4(0 + 0)];
+ sum00 = bfdotadd(sum00, n[s + H4(0 + 0)], m[s + H4(0 + 0)]);
+ sum00 = bfdotadd(sum00, n[s + H4(0 + 1)], m[s + H4(0 + 1)]);
+
+ sum01 = a[s + H4(0 + 1)];
+ sum01 = bfdotadd(sum01, n[s + H4(0 + 0)], m[s + H4(2 + 0)]);
+ sum01 = bfdotadd(sum01, n[s + H4(0 + 1)], m[s + H4(2 + 1)]);
+
+ sum10 = a[s + H4(2 + 0)];
+ sum10 = bfdotadd(sum10, n[s + H4(2 + 0)], m[s + H4(0 + 0)]);
+ sum10 = bfdotadd(sum10, n[s + H4(2 + 1)], m[s + H4(0 + 1)]);
+
+ sum11 = a[s + H4(2 + 1)];
+ sum11 = bfdotadd(sum11, n[s + H4(2 + 0)], m[s + H4(2 + 0)]);
+ sum11 = bfdotadd(sum11, n[s + H4(2 + 1)], m[s + H4(2 + 1)]);
+
+ d[s + H4(0 + 0)] = sum00;
+ d[s + H4(0 + 1)] = sum01;
+ d[s + H4(2 + 0)] = sum10;
+ d[s + H4(2 + 1)] = sum11;
+ }
+ clear_tail(d, opr_sz, simd_maxsz(desc));
+}