janetsc commented on code in PR #13256:
URL: https://github.com/apache/tvm/pull/13256#discussion_r1034920993
##########
src/runtime/hexagon/ops/conv2d.h:
##########
@@ -133,7 +155,48 @@ inline uintptr_t hwio_at(const DLTensor& f, int y, int x,
int i, int o) {
* @param width
* @param depth
*/
-void blockize_hwc_16b(void* out, void* inp_flat, int height, int width, int
depth);
+template <typename T, int block_height, int block_width, int block_depth>
+void blockize_hwc(void* out, void* inp_flat, int height, int width, int depth)
{
+ int (*index_func)(int, int, int);
+ if constexpr (std::is_same_v<T, uint8_t>)
+ index_func = yxc_to_sm_8b;
+ else if constexpr (std::is_same_v<T, uint16_t>)
+ index_func = yxc_to_sm_16b;
+ else
+ LOG_ERROR << "blockize_hwc is only supported for uint8_t and uint16_t
types";
+
+ auto inp_data = static_cast<T*>(inp_flat);
+ auto out_data = static_cast<uintptr_t*>(out);
+ const int stride_x = depth;
+ const int stride_y = stride_x * width;
+
+ for (int cy = 0; cy < height; cy += block_height) {
+ for (int cx = 0; cx < width; cx += block_width) {
+ for (int cc = 0; cc < depth; cc += block_depth) {
+ auto block = reinterpret_cast<T*>(*out_data++);
+ int max_y = std::min(block_height, height - cy);
+ int max_x = std::min(block_width, width - cx);
+ int max_c = std::min(block_depth, depth - cc);
Review Comment:
This is an example where you could check to see that max_y, max_x and max_c
are in bounds for index_func.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
