Replace gpu_asm_extra_flags string option by individual flags #19836
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
b5e4b21 to
4fbcee0
Compare
`gpu_asm_extra_flags` allowed the user to pass arbitrary command line flags to `ptxas`. This was working well enough when calling ptxas was our only PTX compilation option. With library compilation and support for parallel compilation a wrong flag can easily mess up the PTX compilation with weird error. It also doesn't support flags for `nvlink` which might be needed when using parallel compilation. So I'm replacing the list of opaque flags by individual boolean options for the two main use cases (debug compile and preserving line info). The new compilation providers will take those booleans options and generate the right flags or API calls. As a temporary shim the function `PtxOptsFromDebugOptions` will still generate the command line flags for users of the legacy PTX compilation functions. PiperOrigin-RevId: 701850432
4fbcee0 to
ff5f61c
Compare
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Outdated suggestions cannot be applied.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.
Replace gpu_asm_extra_flags string option by individual flags
gpu_asm_extra_flagsallowed the user to pass arbitrary command line flagsto
ptxas. This was working well enough when calling ptxas was our onlyPTX compilation option.
With library compilation and support for parallel compilation a wrong flag can easily mess up the PTX compilation with weird error. It also doesn't support flags for
nvlinkwhich might be needed when using parallel compilation.So I'm replacing the list of opaque flags by individual boolean options for the two main use cases (debug compile and preserving line info). The new compilation providers will take those booleans options and generate the right flags or API calls.
As a temporary shim the function
PtxOptsFromDebugOptionswill still generate the command line flags for users of the legacy PTX compilation functions.