Adding Read Put Packet operation at Executor #441
+97
−18
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
caiomcbr
changed the title
|
This looks good to me, but I remember @Binyang2014 suggested a more general solution instead of hacking the code path. |
Binyang2014
reviewed
Jan 16, 2025
Binyang2014
reviewed
Feb 7, 2025
added 11 commits
February 7, 2025 19:58
Binyang2014
reviewed
Feb 11, 2025
Comment on lines
+361
to
+366
| // Ensuring Data Is Ready | ||
| size_t nPackets = size * 2 / sizeof(PacketType); | ||
| for (size_t pkt_idx = threadIdx.x; pkt_idx < nPackets; pkt_idx += blockDim.x) { | ||
| PacketType* pkts = (PacketType*)((char*)scratch + scratchBaseOffset + srcOffsets[ch_idx] * 2); | ||
| PacketPayload<PacketType> data = pkts[pkt_idx].read(flag); | ||
| } |
There was a problem hiding this comment.
Can you give an example for this case? It's for sending packet via intra node channel then trans via inter node channel? If so, we may need more threads for this, not just #tid < nDstChannels
| size_t nPackets = size * 2 / sizeof(PacketType); | ||
| for (size_t pkt_idx = threadIdx.x; pkt_idx < nPackets; pkt_idx += blockDim.x) { | ||
| PacketType* pkts = (PacketType*)((char*)scratch + scratchBaseOffset + srcOffsets[ch_idx] * 2); | ||
| PacketPayload<PacketType> data = pkts[pkt_idx].read(flag); |
There was a problem hiding this comment.
We may need to set data to back to the scratch buffer, not sure if compiler will optimize the instruction if we only read the data
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.