FEAT: MultiGPU for golang bindings #417
Merged
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
|
@jeremyfelder one thing I found really useful when designing Rust-side device slices is the ability to look up device id of any device pointer using CUDA runtime cudaPointerGetAttributes function. This allows to avoid explicitly storing device id alongside the actual data. |
…ll device association managed implicitly
jeremyfelder
force-pushed
the
feat/golang/multigpu
branch
from
139fcab to
afa9617
Compare
ImmanuelSegol
suggested changes
Mar 6, 2024
ImmanuelSegol
approved these changes
Mar 12, 2024
| } | ||
|
|
||
| // CheckDevice is used to ensure that the DeviceSlice about to be used resides on the currently set device | ||
| func (d DeviceSlice) CheckDevice() { |
There was a problem hiding this comment.
honestly the name is confusing i think
| return convert{{if .IsG2}}G2{{end}}ProjectivePointsMontgomery(points, true) | ||
| } | ||
|
|
||
| func {{if .IsG2}}G2{{end}}ProjectiveFromMontgomery(points *core.DeviceSlice) cr.CudaError { | ||
| points.CheckDevice() | ||
| return convert{{if .IsG2}}G2{{end}}ProjectivePointsMontgomery(points, false) | ||
| } | ||
| {{end}} |
| return convertScalarsMontgomery(scalars, true) | ||
| } | ||
|
|
||
| func FromMontgomery(scalars *core.DeviceSlice) cr.CudaError { | ||
| scalars.CheckDevice() | ||
| return convertScalarsMontgomery(scalars, false) | ||
| }{{- end}} |
LeonHibnik
approved these changes
Mar 13, 2024
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Outdated suggestions cannot be applied.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.
Describe the changes
This PR adds multi gpu support in the golang bindings.
Tha main changes are to DeviceSlice which now includes a
deviceIdattribute specifying which device the underlying data resides on and checks for correct deviceId and current device when using DeviceSlices in any operation.In Go, most concurrency can be done via Goroutines (described as lightweight threads - in reality, more of a threadpool manager), however, there is no guarantee that a goroutine stays on a specific host thread. Therefore, a function
RunOnDevicewas added to the cuda_runtime package which locks a goroutine into a specific host thread, sets a current GPU device, runs a provided function, and unlocks the goroutine from the host thread after the provided function finishes. While the goroutine is locked to the hsot thread, the Go runtime will not assign other goroutines to that host thread