Skip to content

Update CUDA graph on scale change plus clear nodes/params #9550

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 21, 2024
Merged

Update CUDA graph on scale change plus clear nodes/params #9550

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c6b3ea6
Avoid using saved CUDA graph if scale changes and reset nodes/params …
agray3 Sep 17, 2024
b51dacc
clear before resize
agray3 Sep 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions ggml/src/ggml-cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2451,6 +2451,7 @@ static void set_ggml_graph_node_properties(ggml_tensor * node, ggml_graph_node_p
for (int i = 0; i < GGML_MAX_SRC; i++) {
graph_node_properties->src_address[i] = node->src[i] ? node->src[i]->data : nullptr;
}
memcpy(graph_node_properties->op_params, node->op_params, GGML_MAX_OP_PARAMS);
}

static bool ggml_graph_node_has_matching_properties(ggml_tensor * node, ggml_graph_node_properties * graph_node_properties) {
Expand Down Expand Up @@ -2482,6 +2483,12 @@ static bool ggml_graph_node_has_matching_properties(ggml_tensor * node, ggml_gra
return false;
}
}

if (node->op == GGML_OP_SCALE &&
memcmp(graph_node_properties->op_params, node->op_params, GGML_MAX_OP_PARAMS) != 0) {
return false;
}

return true;
}

Expand Down Expand Up @@ -2694,7 +2701,9 @@ GGML_CALL static enum ggml_status ggml_backend_cuda_graph_compute(ggml_backend_t
CUDA_CHECK(cudaGraphGetNodes(cuda_ctx->cuda_graph->graph, nullptr, &cuda_ctx->cuda_graph->num_nodes));
// Subsequent call with non-null argument gets nodes
cuda_ctx->cuda_graph->nodes.resize(cuda_ctx->cuda_graph->num_nodes);
cuda_ctx->cuda_graph->nodes.clear();
cuda_ctx->cuda_graph->params.resize(cuda_ctx->cuda_graph->num_nodes);
cuda_ctx->cuda_graph->params.clear();
Copy link
Member

@slaren slaren Sep 20, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What's the intention here? clear after resize seems very strange.

Copy link
Contributor Author

@agray3 agray3 Sep 20, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry, should be clear before resize, now fixed (silly mistake when applying this to the scale ops changes after debugging separately).

if (cuda_ctx->cuda_graph->num_nodes > 0) {
CUDA_CHECK(cudaGraphGetNodes(cuda_ctx->cuda_graph->graph, cuda_ctx->cuda_graph->nodes.data(), &cuda_ctx->cuda_graph->num_nodes));

Expand Down
1 change: 1 addition & 0 deletions ggml/src/ggml-cuda/common.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -569,6 +569,7 @@ struct ggml_graph_node_properties {
int64_t ne[GGML_MAX_DIMS];
size_t nb[GGML_MAX_DIMS];
void * src_address[GGML_MAX_SRC];
int32_t op_params[GGML_MAX_OP_PARAMS / sizeof(int32_t)];
};

struct ggml_cuda_graph {
Expand Down
Loading