Add leading/trailing ones and zero count instructions (part 2) #1179
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
Fumuran
commented
Dec 12, 2023
Fumuran
force-pushed
the
andrew-leading-trailing-one-zero
branch
from
6db6e1d
to
193048e
Compare
Fumuran
force-pushed
the
andrew-bitwise-counters-u64
branch
from
509f93a
to
4ca468e
Compare
bobbinth
requested changes
Feb 15, 2024
Fumuran
force-pushed
the
andrew-leading-trailing-one-zero
branch
3 times, most recently
from
d6b7450
to
0e7b44b
Compare
Fumuran
force-pushed
the
andrew-bitwise-counters-u64
branch
3 times, most recently
from
3fff4c5
to
6f49946
Compare
bobbinth
reviewed
Feb 19, 2024
bobbinth
reviewed
Feb 19, 2024
Fumuran
force-pushed
the
andrew-bitwise-counters-u64
branch
from
6f49946
to
a82dc87
Compare
bobbinth
approved these changes
Feb 21, 2024
Comment on lines
53
to
56
| | clz | Counts the number of leading zeros of one unsigned 64-bit integer.<br /> The input value is assumed to be represented using 32 bit limbs, but this is not checked.<br /> The stack transition looks as follows: `[n_hi, n_lo, ...] -> [clz, ...]`, where `clz` is a number of leading zeros of value `n`.<br /> This takes 59 cycles if $n < 2^{32}$ and 32 cycles otherwise. | | ||
| | ctz | Counts the number of trailing zeros of one unsigned 64-bit integer.<br /> The input value is assumed to be represented using 32 bit limbs, but this is not checked.<br /> The stack transition looks as follows: `[n_hi, n_lo, ...] -> [ctz, ...]`, where `ctz` is a number of trailing zeros of value `n`.<br /> This takes 60 cycles if $n < 2^{32}$ and 33 cycles otherwise. | | ||
| | clo | Counts the number of leading ones of one unsigned 64-bit integer.<br /> The input value is assumed to be represented using 32 bit limbs, but this is not checked.<br /> The stack transition looks as follows: `[n_hi, n_lo, ...] -> [clo, ...]`, where `clo` is a number of leading ones of value `n`.<br /> This takes 69 cycles if $n < 2^{32}$ and 37 cycles otherwise. | | ||
| | cto | Counts the number of trailing ones of one unsigned 64-bit integer.<br /> The input value is assumed to be represented using 32 bit limbs, but this is not checked.<br /> The stack transition looks as follows: `[n_hi, n_lo, ...] -> [cto, ...]`, where `cto` is a number of trailing ones of value `n`.<br /> This takes 70 cycles if $n < 2^{32}$ and 38 cycles otherwise. | |
There was a problem hiding this comment.
Cycle counts here need to be updated.
Fumuran
force-pushed
the
andrew-leading-trailing-one-zero
branch
2 times, most recently
from
ea080b2
to
6fd200e
Compare
Fumuran
force-pushed
the
andrew-bitwise-counters-u64
branch
2 times, most recently
from
b4da798
to
f4c5c5f
Compare
Fumuran
force-pushed
the
andrew-leading-trailing-one-zero
branch
from
6fd200e
to
9b75f1d
Compare
Fumuran
force-pushed
the
andrew-bitwise-counters-u64
branch
from
f4c5c5f
to
6e985d8
Compare
bobbinth
force-pushed
the
andrew-bitwise-counters-u64
branch
from
6e985d8
to
945663c
Compare
bobbinth
pushed a commit
that referenced
this pull request
Feb 26, 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.
This PR adds 4 new instructions for
std::math::u64module:This PR partially implements features mentioned in #1133 issue. This PR should be merged after #1176.