Single-precision (fp32) build support by hardik-corintis · Pull Request #5033 · firedrakeproject/firedrake

hardik-corintis · 2026-04-15T14:04:27Z

Description

Adds single-precision (fp32) build support. Firedrake can now run on a PETSc installation compiled with --with-precision=single. The approach mirrors complex mode: precision is detected at import time from PETSc's build variables and flows through from there.

AI disclosure: Parts of this PR were developed with assistance from Claude (Anthropic). All changes have been reviewed, tested locally, and are fully understood by the author.

Prerequisite

Requires https://gitlab.com/petsc/petsc/-/merge_requests/9272 (petsc4py: handle PETSC_DOUBLE in DMSwarm.getField). Without it, DMSwarm.getField() raises AssertionError on fp32 builds because PETSC_DOUBLE is not mapped to a numpy dtype in the single-precision case where PETSC_REAL != PETSC_DOUBLE.

Changes

scripts/firedrake-configure

Adds --arch single / ScalarType.SINGLE; passes --with-precision=single to PETSc configure; excludes fftw and suitesparse (no fp32 support in those libraries)

tsfc/parameters.py, tsfc/loopy.py, tsfc/kernel_interface/common.py, tsfc/ufl_utils.py

scalar_type / scalar_type_c derived from PETSc precision at import time; constant initializers cast to the kernel scalar dtype

Core (evaluate.h, locate.c, pointquery_utils.py, pointeval_utils.py, mg/kernels.py)

Replace hardcoded double / int with PetscReal / PetscInt in generated C code
Convergence epsilon in point query tightened to 1e-6 in fp32 mode vs 1e-12 in fp64, to stay within single-precision range

firedrake/mesh.py, firedrake/utility_meshes.py

Vertex coordinates and reference-cell distances use PETSc.RealType; physical coordinate arrays for rtree and DMSwarmPIC_coor remain float64 (required by the rtree C API and PETSc swarm internals)

firedrake/function.py

Point evaluation coerces coordinates to float64 regardless of ScalarType, for geometric robustness in cell location

firedrake/assemble.py, firedrake/functionspaceimpl.py, pyop2/codegen/builder.py

Replace dtype=int with dtype=IntType in numpy.prod and array allocation calls

firedrake/utils.py

Adds single_mode boolean flag (mirrors complex_mode)

Tests

Adds @pytest.mark.skipsingle marker for tests incompatible with fp32
tests/firedrake/conftest.py: registers the marker and wires it up
Skips a small set of tests that require double-precision accuracy (test_locate_cell, test_interpolate_cross_mesh[extrudedcube], test_parallel_high_order_location)

.github/workflows/core.yml

Adds single to the CI matrix alongside default and complex

Known limitations

test_parallel_high_order_location is skipped in fp32: high-order cell location in a warped mesh requires double-precision accuracy that fp32 cannot provide at tolerance=0.0001.

connorjward · 2026-04-15T14:19:56Z

Thanks for this.

adds --arch single

What about single+complex? Isn't that a valid configuration?

PETSc version bump (v3.24.5 → v3.25.0)

This isn't necessary. That's all going to be taken care of when I release the next major version in the next 24 hours.

Fix needed upstream in petsc4py: if ctype == PETSC_DOUBLE: typenum = NPY_DOUBLE in petsc4py/PETSc/DMSwarm.pyx.

Can you get this fixed upstream? Clearly Claude already knows what to do.

hardik-corintis · 2026-05-10T00:21:26Z

Thanks for this.

adds --arch single

What about single+complex? Isn't that a valid configuration?

Added ScalarType.SINGLE_COMPLEX (--arch single-complex) to firedrake-configure for all four platform targets: single_mode (from PETSC_PRECISION) and complex_mode (from PETSC_SCALAR) are detected independently, and ScalarType already resolves to numpy.complex64 for a single+complex build.

PETSc version bump (v3.24.5 → v3.25.0)

This isn't necessary. That's all going to be taken care of when I release the next major version in the next 24 hours.

Removed from the PR description — thanks.

Fix needed upstream in petsc4py: if ctype == PETSC_DOUBLE: typenum = NPY_DOUBLE in petsc4py/PETSc/DMSwarm.pyx.

Can you get this fixed upstream? Clearly Claude already knows what to do.

Opened a PR here: https://gitlab.com/petsc/petsc/-/merge_requests/9272

connorjward

I've just looked at the CI/install related side of this (at a glance everything else seems pretty good).

We just have to be careful about adding new test builds to Firedrake. I will try and figure out a solution soon.

connorjward · 2026-05-20T14:36:42Z

We just have to be careful about adding new test builds to Firedrake. I will try and figure out a solution soon.

I have a solution for this in #5117 (merged). Once we update main (#5134) then you can use it in this pull request. You basically need to follow the same procedure that we have for testing complex or CUDA builds.

…spatialindex float64 coercion

- mesh.py: clarify why PETSc.RealType is correct for plex_from_cell_list - mg/kernels.py: fix to_reference_coords_kernel signature (PetscScalar *X -> %(RealType)s *X) and add RealType to the template substitution dict - evaluate.h: comment explaining why int/double is intentional for evaluate() - test_stokes_mini.py: replace fp32 solver workaround with @pytest.mark.skipsingle; fieldsplit path needs a dedicated fp32 test - conftest.py: remove trailing blank line

…nd skip VertexOnlyMesh tests in fp32

…ests

# Conflicts: # scripts/firedrake-configure

…ecision

…rallel)

…l style

…unction

…es, skip non-nested MG transfer and mixed-poisson submesh convergence

…x-sqrt limitation

…sion

# Conflicts: # firedrake/function.py # firedrake/mesh.py # scripts/firedrake-configure

# Conflicts: # .github/workflows/core.yml # .github/workflows/pr.yml # .github/workflows/push.yml # firedrake/evaluate.h # firedrake/function.py # firedrake/locate.c # firedrake/mesh.py # firedrake/nullspace.py # firedrake/pointeval_utils.py # scripts/firedrake-configure # tests/firedrake/adjoint/test_transformed_functional.py # tests/firedrake/multigrid/test_adaptive_multigrid.py # tests/firedrake/regression/test_bddc.py # tests/firedrake/vertexonly/test_vertex_only_mesh_generation.py

Threads dtype=RealType (or the numpy-derived real dtype from scalar_type in TSFC) through every as_fiat_cell/create_element call site in firedrake and tsfc, using FIAT PR firedrakeproject#260 and FInAT's new dtype support (firedrakeproject/fiat#263). Removes the finat.element_factory.ufc_cell monkeypatch in firedrake/utils.py, which is no longer needed now that callers declare their working precision explicitly instead of relying on a globally-overridden default. Also fixes petsc_sparse's hardcoded rtol=1E-10 drop tolerance (firedrake/preconditioners/fdm.py), which is too tight for single precision: reference-cell geometry feeding into these matrices is only accurate to float32 round-off (~1e-7), so entries that should be exactly zero (e.g. in a Nedelec discrete gradient matrix) were leaking into the sparsity pattern above the fp64-tuned threshold, corrupting the exact combinatorial structure PETSc's PCBDDCNedelecSupport expects and causing test_bddc_aij_simplex[N1curl-3-False] to fail.

test_fieldsplit: h *= 8.0 (was 10.0) for the Taylor test perturbation. test_transformed_functional_poisson_tao_nls: widen the fp32 error_norm bound to 2e-1 (was 7e-2) and correct the comment -- round-off shifts which critical point tao_nls converges to, not a solver tolerance issue.

pbrubeck · 2026-08-07T15:07:01Z

Some of the tests could get a global tolerance per module. There's no need to add repeated logic each time a tolerance is used

Co-authored-by: Cursor <cursoragent@cursor.com>

hardik-corintis marked this pull request as draft April 15, 2026 14:13

Olender mentioned this pull request Apr 23, 2026

Add support for single precision NDF-Poli-USP/spyro#281

Open

hardik-corintis force-pushed the fp32-support branch 2 times, most recently from 0dc7472 to dd517a9 Compare May 9, 2026 23:10

hardik-corintis marked this pull request as ready for review May 10, 2026 00:18

connorjward requested changes May 11, 2026

View reviewed changes

Comment thread .github/workflows/core.yml Outdated

Comment thread scripts/firedrake-configure Outdated

hardik-corintis added 20 commits May 21, 2026 11:35

Fix single-precision (fp32) support: TSFC initializer dtype cast and …

fac7012

…spatialindex float64 coercion

Replacing double with Petsc.RealType

fcf7b57

Use PETSc types for precision and integer width in C code

561feed

Replace hardcoded dtypes with PETSc-derived types

47a1ad2

Add single-precision (fp32) build support and detection

e38b9a7

Fix sparsity.pyx: revert broken PetscScalar cimport

39f82af

skipping tests for single precision

fa4b924

DBL_MAX to PETSC_MAX_REAL

d3d8aec

fp32 detection in tests

2a0b767

ensuring that coordinates are real

b0bbca6

Fix PetscScalar/PetscReal type mismatch in prolong/restrict kernels a…

a986f20

…nd skip VertexOnlyMesh tests in fp32

restoring tests/test_durations.json

6ddb6ae

reverting solver parameters back to original form

3076a4d

Port missing dtype=int -> IntType fixes

d65cd77

adding dtypes for int

64cce3f

Update skipsingle comment for test_parallel_high_order_location

21337e9

removed alias fp32

15fd4cc

Add single-complex arch to firedrake-configure; drop _fp32 alias in t…

b8a679f

…ests

Fix duplicate SINGLE arch keys and missing CC in UNKNOWN SINGLE_COMPLEX

3cd08b8

hardik-corintis force-pushed the fp32-support branch from cf73186 to 3cd08b8 Compare May 21, 2026 11:22

hardik-corintis added 4 commits July 10, 2026 14:57

Merge remote-tracking branch 'origin/main' into fp32-support

06a1641

# Conflicts: # scripts/firedrake-configure

merge origin/main into fp32-support

7f8c919

fp32: scale test_partition_behaviour offsets/tolerances for single pr…

55f3608

…ecision

fp32: relax unreachable ksp_rtol in checkpoint/IO project() calls

0a04977

hardik-corintis force-pushed the fp32-support branch from 9111b4a to 0a04977 Compare July 13, 2026 14:52

hardik-corintis added 5 commits July 13, 2026 17:14

relax more unreachable tolerances (test_patch_pc, test_stokes_hdiv_pa…

477bcfb

…rallel)

fp32: fix remaining undocumented failures, normalize tolerance litera…

886a72f

…l style

fp32: revert harmful ksp_rtol change, use tolerance-only fix for io_f…

a85a415

…unction

fix adjoint Taylor test h/threshold tuning, tighten test_fdm toleranc…

2840d9d

…es, skip non-nested MG transfer and mixed-poisson submesh convergence

fp32: fix adjoint Taylor/optimisation tests, skip genuine SLEPc matri…

6ff6b11

…x-sqrt limitation

connorjward mentioned this pull request Jul 15, 2026

Petsc 64 bit int fixes #5252

Merged

hardik-corintis mentioned this pull request Jul 16, 2026

Loosen tolerances for single precision firedrakeproject/fiat#260

Merged

hardik-corintis added 4 commits July 21, 2026 16:36

calibrate FIAT's macro-element tolerance for our actual working preci…

d9e1017

…sion

Merge remote-tracking branch 'origin/main' into fp32-support

db1a215

# Conflicts: # firedrake/function.py # firedrake/mesh.py # scripts/firedrake-configure

Fix missing int_type in CI single-precision matrix entry

d95600a

hardik-corintis mentioned this pull request Aug 6, 2026

propagate dtype through finat element construction firedrakeproject/fiat#263

Draft

hardik-corintis added 4 commits August 7, 2026 12:02

temporary chagne to see if the change in fiat helps or not

d1c5860

Relax fp32 tolerances in adaptive multigrid restrict/patch tests

528d348

hardik-corintis marked this pull request as draft August 7, 2026 15:29

hardik-corintis and others added 7 commits September 3, 2026 13:11

Merge remote-tracking branch 'origin/main' into fp32-support

f82b838

Co-authored-by: Cursor <cursoragent@cursor.com>

Clarify fp32 test tolerances

79bbdf9

Co-authored-by: Cursor <cursoragent@cursor.com>

Normalize real scalars in adjoint assignment

012ee85

Relax fp32 SNES objective tolerances

8d1499b

Adjust fp32 direct projection pivot tolerance

3cfdbc2

Fix PCD setup for fp32 pressure solves

b55723b

Relax fp32 demo solver tolerances

0effd12

Navigation Menu

Uh oh!

Single-precision (fp32) build support - #5033

Single-precision (fp32) build support#5033
hardik-corintis wants to merge 99 commits into
firedrakeproject:mainfrom
Corintis:fp32-support

hardik-corintis commented Apr 15, 2026 •

edited

Loading

Uh oh!

connorjward commented Apr 15, 2026

Uh oh!

hardik-corintis commented May 10, 2026

Uh oh!

connorjward left a comment

Uh oh!

Uh oh!

Uh oh!

connorjward commented May 20, 2026

Uh oh!

pbrubeck commented Aug 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Uh oh!

Conversation

hardik-corintis commented Apr 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Prerequisite

Changes

Known limitations

Uh oh!

connorjward commented Apr 15, 2026

Uh oh!

hardik-corintis commented May 10, 2026

Uh oh!

connorjward left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

connorjward commented May 20, 2026

Uh oh!

pbrubeck commented Aug 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

hardik-corintis commented Apr 15, 2026 •

edited

Loading