forked from pytorch/pytorch
-
Notifications
You must be signed in to change notification settings - Fork 7
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.
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
[PROTOTYPE] Inner heuristics refactor #1695
Open
csarofeen
wants to merge
3
commits into
devel
Choose a base branch
from
timm_nhwc
base: devel
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
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
…oops without turning the kernel cooperative.
@jjsjann123 we may want this in for 1.12. |
naoyam
reviewed
May 17, 2022
Comment on lines
+26
to
+59
int64_t roundUpPow2OrMultipleOf(const int64_t x, const int64_t multiple) { | ||
auto round_up_pow2 = scheduler_utils::lastPow2(x); | ||
if (round_up_pow2 < x) { | ||
round_up_pow2 *= 2; | ||
} | ||
constexpr int64_t kEight = 8; // clang tidy | ||
auto round_up_8 = x % kEight == 0 ? x : x + (kEight - x % kEight); | ||
return std::min(round_up_8, round_up_pow2); | ||
auto round_up_multiple = | ||
x % multiple == 0 ? x : x + (multiple - x % multiple); | ||
return std::min(round_up_multiple, round_up_pow2); | ||
} | ||
|
||
int64_t safeDiv(const int64_t x, const int64_t y) { | ||
return x / y == 0 ? 1 : x / y; | ||
} | ||
|
||
int64_t clamp(const int64_t val, const int64_t min_val, const int64_t max_val) { | ||
return std::min(std::max(val, min_val), max_val); | ||
} | ||
|
||
// Reduce x, y, z until it's product is less than max value, reduce round robin | ||
// starting with x | ||
void reduceProductTo(int64_t& x, int64_t& y, int64_t& z, const int64_t max) { | ||
TORCH_INTERNAL_ASSERT(max > 1); | ||
if (x * y * z > max) { | ||
x = safeDiv(x, 2); | ||
} | ||
if (x * y * z > max) { | ||
y = safeDiv(y, 2); | ||
} | ||
if (x * y * z > max) { | ||
z = safeDiv(z, 2); | ||
} | ||
if (x * y * z > max) { | ||
reduceProductTo(x, y, z, max); | ||
} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Should merge them with those in the reduction scheduler.
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.
Fixes #ISSUE_NUMBER