fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-06-19 04:08:25 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

kk: Fix issues with maximal reconvergence

Browse source 
If a loop has only one break case, Metal appears to re-order it to after
the loop ends, which goes against the expected behavior for reconvergence.
Work around this by putting the break statement into a trivial, always-true
runtime conditional, when maximal reconvergence is requested.

Fixes dEQP-VK.reconvergence.maximal.compute.nesting*

Reviewed-by: Arcady Goldmints-Orlov <arcady@lunarg.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41229>
This commit is contained in:
squidbus 2026-04-27 21:59:56 -07:00 • committed by Marge Bot
parent 26ec32dada
commit 76a3951e03
3 changed files with 42 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

33
docs/drivers/kosmickrisp/workarounds.rst
View file

@ -49,6 +49,39 @@ info on what was updated.
Workarounds
===========
KK_WORKAROUND_9
---------------
| macOS version: 26.4.1
| Metal ticket: Not reported
| Metal ticket status:
| CTS test failure: ``dEQP-VK.reconvergence.maximal.compute.nesting*``
| Comments:
Metal seems to re-order the sole break case of a loop such that execution
reconverges earlier than expected.
From the above mentioned CTS test, consider the following, which is the
only code path that breaks within a loop:
.. code-block:: c
if (subgroupElect()) {
outputC.loc[gl_LocalInvocationIndex]++;
outputB.b[(outLoc++)*invocationStride + gl_LocalInvocationIndex] =
subgroupBallot(true);
break;
}
The test expects the ``subgroupBallot`` to yield just one bit set for the
thread picked by ``subgroupElect``; however, Metal returns the full 0xFFFFFFFF,
presumably because it re-ordered the operations to after the loop.
To work around this, we add a trivial, always-true runtime condition to the
break to ensure that the prior logic is not re-ordered.
| Log:
| 2026-04-27: Workaround implemented
KK_WORKAROUND_7
---------------
| macOS version: 26.0.1

8
src/kosmickrisp/compiler/nir_to_msl.c
View file

@ -1809,7 +1809,13 @@ jump_instr_to_msl(struct nir_to_msl_ctx *ctx, nir_jump_instr *jump)
assert(!"Unimplemented");
break;
case nir_jump_break:
P_IND(ctx, "break;\n");
/* KK_WORKAROUND_9 */
if (!ctx->shader->info.maximally_reconverges ||
(ctx->disabled_workarounds & BITFIELD64_BIT(9))) {
P_IND(ctx, "break;\n");
} else {
P_IND(ctx, "if ((ulong)simd_active_threads_mask()) break;\n");
}
break;
case nir_jump_continue:
P_IND(ctx, "continue;\n");

8
src/kosmickrisp/vulkan/kk_physical_device.c
View file

@ -123,9 +123,7 @@ kk_get_device_extensions(const struct kk_instance *instance,
/* Optional extensions */
.KHR_calibrated_timestamps = true,
/* Temporarily disabled due to failing tests in
* dEQP-VK.reconvergence.maximal.compute.nesting* */
.KHR_shader_maximal_reconvergence = false,
.KHR_shader_maximal_reconvergence = true,
.KHR_shader_relaxed_extended_instruction = true,
.KHR_shader_subgroup_uniform_control_flow = true,
#ifdef KK_USE_WSI_PLATFORM
@ -287,9 +285,7 @@ kk_get_device_features(
.shaderExpectAssume = true,
/* VK_KHR_shader_maximal_reconvergence */
/* Temporarily disabled due to failing tests in
* dEQP-VK.reconvergence.maximal.compute.nesting* */
.shaderMaximalReconvergence = false,
.shaderMaximalReconvergence = true,
/* VK_KHR_shader_relaxed_extended_instruction */
.shaderRelaxedExtendedInstruction = true,