Use max clock for analytical calculations of peak flops#2801
Merged
jlebar merged 1 commit intotriton-lang:mainfrom Dec 14, 2023
Merged
Use max clock for analytical calculations of peak flops#2801jlebar merged 1 commit intotriton-lang:mainfrom
jlebar merged 1 commit intotriton-lang:mainfrom
Conversation
Summary: By reading the current clock, our analytical calculations can vary while we're evaluating different configs. It turns out the choice of config is very sensitive to the clock, such that a slight throttling can make us reject very good configs, in favor of very bad ones. A reproducer can be found here: https://gist.github.com/bertmaher/8ff5e9631666846fff55d81326cacb4d ``` $ python thermal_throttle.py chosen config BLOCK_M: 128, BLOCK_N: 256, BLOCK_K: 32, SPLIT_K: 1, num_warps: 8, num_ctas: 1, num_stages: 3, enable_warp_specialization: False, enable_persistent: False tflops/s: 107.92460196062149 $ python thermal_throttle.py --preheat chosen config BLOCK_M: 32, BLOCK_N: 32, BLOCK_K: 32, SPLIT_K: 1, num_warps: 2, num_ctas: 1, num_stages: 6, enable_warp_specialization: False, enable_persistent: False tflops/s: 39.29629633970286 ```
bertmaher
added a commit
to bertmaher/triton
that referenced
this pull request
Jan 3, 2024
…2801) By reading the current clock, our analytical calculations can vary while we're evaluating different configs. It turns out the choice of config is very sensitive to the clock, such that a slight throttling can make us reject very good configs, in favor of very bad ones. A reproducer can be found here: https://gist.github.com/bertmaher/8ff5e9631666846fff55d81326cacb4d ``` $ python thermal_throttle.py chosen config BLOCK_M: 128, BLOCK_N: 256, BLOCK_K: 32, SPLIT_K: 1, num_warps: 8, num_ctas: 1, num_stages: 3, enable_warp_specialization: False, enable_persistent: False tflops/s: 107.92460196062149 $ python thermal_throttle.py --preheat chosen config BLOCK_M: 32, BLOCK_N: 32, BLOCK_K: 32, SPLIT_K: 1, num_warps: 2, num_ctas: 1, num_stages: 6, enable_warp_specialization: False, enable_persistent: False tflops/s: 39.29629633970286 ```
malfet
pushed a commit
that referenced
this pull request
Jan 3, 2024
…ps (#2870) By reading the current clock, our analytical calculations can vary while we're evaluating different configs. It turns out the choice of config is very sensitive to the clock, such that a slight throttling can make us reject very good configs, in favor of very bad ones. A reproducer can be found here: https://gist.github.com/bertmaher/8ff5e9631666846fff55d81326cacb4d ``` $ python thermal_throttle.py chosen config BLOCK_M: 128, BLOCK_N: 256, BLOCK_K: 32, SPLIT_K: 1, num_warps: 8, num_ctas: 1, num_stages: 3, enable_warp_specialization: False, enable_persistent: False tflops/s: 107.92460196062149 $ python thermal_throttle.py --preheat chosen config BLOCK_M: 32, BLOCK_N: 32, BLOCK_K: 32, SPLIT_K: 1, num_warps: 2, num_ctas: 1, num_stages: 6, enable_warp_specialization: False, enable_persistent: False tflops/s: 39.29629633970286 ``` Cherry-pick of #2801 into release/2.2.x
peterbell10
added a commit
to peterbell10/pytorch
that referenced
this pull request
Jan 4, 2024
See triton-lang/triton#2801 Current SM clocks may fluctuate at runtime and change the result of `get_device_tflops`.
peterbell10
added a commit
to pytorch/pytorch
that referenced
this pull request
Jan 4, 2024
See triton-lang/triton#2801 Current SM clocks may fluctuate at runtime and change the result of `get_device_tflops`. [ghstack-poisoned]
peterbell10
added a commit
to pytorch/pytorch
that referenced
this pull request
Jan 4, 2024
See triton-lang/triton#2801 Current SM clocks may fluctuate at runtime and change the result of `get_device_tflops`. ghstack-source-id: dd85b17 Pull Request resolved: #116754
pytorchmergebot
pushed a commit
to pytorch/pytorch
that referenced
this pull request
Jan 4, 2024
See triton-lang/triton#2801 Current SM clocks may fluctuate at runtime and change the result of `get_device_tflops`. Pull Request resolved: #116754 Approved by: https://github.com/lezcano
pingzhuu
pushed a commit
to siliconflow/triton
that referenced
this pull request
Apr 2, 2024
…ps (triton-lang#2870) By reading the current clock, our analytical calculations can vary while we're evaluating different configs. It turns out the choice of config is very sensitive to the clock, such that a slight throttling can make us reject very good configs, in favor of very bad ones. A reproducer can be found here: https://gist.github.com/bertmaher/8ff5e9631666846fff55d81326cacb4d ``` $ python thermal_throttle.py chosen config BLOCK_M: 128, BLOCK_N: 256, BLOCK_K: 32, SPLIT_K: 1, num_warps: 8, num_ctas: 1, num_stages: 3, enable_warp_specialization: False, enable_persistent: False tflops/s: 107.92460196062149 $ python thermal_throttle.py --preheat chosen config BLOCK_M: 32, BLOCK_N: 32, BLOCK_K: 32, SPLIT_K: 1, num_warps: 2, num_ctas: 1, num_stages: 6, enable_warp_specialization: False, enable_persistent: False tflops/s: 39.29629633970286 ``` Cherry-pick of triton-lang#2801 into release/2.2.x
binarman
pushed a commit
to binarman/triton
that referenced
this pull request
Apr 2, 2024
…2801) By reading the current clock, our analytical calculations can vary while we're evaluating different configs. It turns out the choice of config is very sensitive to the clock, such that a slight throttling can make us reject very good configs, in favor of very bad ones. A reproducer can be found here: https://gist.github.com/bertmaher/8ff5e9631666846fff55d81326cacb4d ``` $ python thermal_throttle.py chosen config BLOCK_M: 128, BLOCK_N: 256, BLOCK_K: 32, SPLIT_K: 1, num_warps: 8, num_ctas: 1, num_stages: 3, enable_warp_specialization: False, enable_persistent: False tflops/s: 107.92460196062149 $ python thermal_throttle.py --preheat chosen config BLOCK_M: 32, BLOCK_N: 32, BLOCK_K: 32, SPLIT_K: 1, num_warps: 2, num_ctas: 1, num_stages: 6, enable_warp_specialization: False, enable_persistent: False tflops/s: 39.29629633970286 ```
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
By reading the current clock, our analytical calculations can vary while we're evaluating different configs. It turns out the choice of config is very sensitive to the clock, such that a slight throttling can make us reject very good configs, in favor of very bad ones.
A reproducer can be found here:
https://gist.github.com/bertmaher/8ff5e9631666846fff55d81326cacb4d