|
|
@@ -358,8 +358,8 @@ void main() {
|
|
|
}
|
|
|
|
|
|
if ((p.mask_n_head_log2 & SINK_ENABLE_BIT) != 0) {
|
|
|
- [[unroll]] for (uint32_t r = 0; r < Br; ++r) {
|
|
|
- float sink = perElemOpGetSink(r, 0u, ACC_TYPE(0), iq2);
|
|
|
+ [[unroll]] for (uint32_t r = 0; r < rows_per_thread; ++r) {
|
|
|
+ float sink = perElemOpGetSink(tile_row(r), 0u, ACC_TYPE(0), iq2);
|
|
|
|
|
|
float ms = 1.0f;
|
|
|
float vs = 1.0f;
|