Fix arm support for Linux #1064
Open
Conversation
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
…where (with Andrea Valassi)
Qubitol
force-pushed
the
fix-arm-support
branch
from
a427610 to
1e1c899
Compare
Collaborator
Author
Collaborator
Author
|
Needed to cancel some job since they hang when running |
valassi
added a commit
to valassi/madgraph4gpu
that referenced
this pull request
Nov 14, 2025
…ests on aarch64 (with DanieleM) This fixes a hang in the testMist tests on aarch64 in sqrtNewtonRaphson (madgraph5#1064) (testMisc -> constexpr_tan -> constexpr_tan_quad -> constexpr_cos_quad -> constexpr_sqrt -> sqrtNewtonRaphson) It uses the same workaround previously adopted for avoiding testMisc hangs when running valgrind (madgraph5#906)
valassi
added a commit
to valassi/madgraph4gpu
that referenced
this pull request
Nov 14, 2025
…ts on aarch64 (with DanieleM) This fixes a hang in the testMist tests on aarch64 in sqrtNewtonRaphson (madgraph5#1064) (testMisc -> constexpr_tan -> constexpr_tan_quad -> constexpr_cos_quad -> constexpr_sqrt -> sqrtNewtonRaphson) It uses the same workaround previously adopted for avoiding testMisc hangs when running valgrind (madgraph5#906)
valassi
added a commit
to valassi/madgraph4gpu
that referenced
this pull request
Nov 14, 2025
…ests on aarch64 (with DanieleM) This fixes a hang in the testMisc tests on aarch64 in sqrtNewtonRaphson (madgraph5#1064) (testMisc -> constexpr_tan -> constexpr_tan_quad -> constexpr_cos_quad -> constexpr_sqrt -> sqrtNewtonRaphson) It uses the same workaround previously adopted for avoiding testMisc hangs when running valgrind (madgraph5#906)
valassi
added a commit
to valassi/madgraph4gpu
that referenced
this pull request
Nov 14, 2025
…ts on aarch64 (with DanieleM) This fixes a hang in the testMisc tests on aarch64 in sqrtNewtonRaphson (madgraph5#1064) (testMisc -> constexpr_tan -> constexpr_tan_quad -> constexpr_cos_quad -> constexpr_sqrt -> sqrtNewtonRaphson) It uses the same workaround previously adopted for avoiding testMisc hangs when running valgrind (madgraph5#906)
…ts on aarch64 (with DanieleM) This fixes a hang in the testMisc tests on aarch64 in sqrtNewtonRaphson (madgraph5#1064) (testMisc -> constexpr_tan -> constexpr_tan_quad -> constexpr_cos_quad -> constexpr_sqrt -> sqrtNewtonRaphson) It uses the same workaround previously adopted for avoiding testMisc hangs when running valgrind (madgraph5#906)
…ith DanieleM) Remove the custom __ARM_NEON__ with two extra underscores Use 'g++ -march=armv8.2-a+simd -E -dM - < /dev/null | grep ARM' to check
…e (with DanieleM)
Qubitol
force-pushed
the
fix-arm-support
branch
from
1e1c899 to
c7296ac
Compare
Collaborator
Author
|
Latest changes involves using |
…ts (#2) on aarch64 (with DanieleM)
…using constexpr_sqrt on aarch64 (with DanieleM)
Qubitol
force-pushed
the
fix-arm-support
branch
from
c7296ac to
2232671
Compare
Collaborator
Author
|
We should consider changing the instances of |
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.
Apparently, arm was working only in case of Mac (where
uname -pgivesarm) and not in case of most Linux distributions (whereuname -pisaarch64).I fixed that: CUDACPP can now run on arm, with support also for neon (equivalent to
cppsse4and picked up using the same backend name).In the makefiles, support for higher vectorisation is not present, but this can be something that we could think of adding in the next future.
I added tests on Linux arm as well.
I needed to regenerate the processes to update the makefiles.