From 4384c8782ede3d5a0b3e6fcf3b7f7edad383ad6d Mon Sep 17 00:00:00 2001 From: Paulo Zanoni Date: Mon, 4 Mar 2024 14:52:25 -0800 Subject: [PATCH] anv+zink/ci: add failures related to multi-sampled sparse binding After enabling multi-sampled sparse binding in Anv, we get these failures. I've investigated them and none are trivial, it's not clear if they're Anv's fault or not, especially considering how many other texture-related failures we already have in this fails.txt file. Since both deqp-vk and Vulkan native apps seem to be working with pure Anv (no Zink), I don't think it's worth blocking multi-sampled sparse on Anv just because of Zink. From what I have investigated, the problems seem related to the following: - glcts is expecting 1D images to have 2D block shapes (this is definitely the case for StandardPageSizesTestCase, we get rid of the failure by either removing sparse support for 1D images or telling their block shapes are the same as the 2D images) - glcts/zink may be trying to use formats that are unsupported by Anv as if they were supported - there's probably something funny going on with the GL_R8 format v2: Adjust test results after merging merging MR 29118. v3: Zink test results are a moving target... Reviewed-by: Lionel Landwerlin (v1) Signed-off-by: Paulo Zanoni Part-of: --- .../drivers/zink/ci/zink-anv-tgl-fails.txt | 22 ++++++++++++++++++- .../drivers/zink/ci/zink-anv-tgl-skips.txt | 1 + 2 files changed, 22 insertions(+), 1 deletion(-) diff --git a/src/gallium/drivers/zink/ci/zink-anv-tgl-fails.txt b/src/gallium/drivers/zink/ci/zink-anv-tgl-fails.txt index c5b580c4f18..7b009ebac45 100644 --- a/src/gallium/drivers/zink/ci/zink-anv-tgl-fails.txt +++ b/src/gallium/drivers/zink/ci/zink-anv-tgl-fails.txt @@ -584,9 +584,29 @@ spec@arb_gpu_shader_fp64@execution@arb_gpu_shader_fp64-gs-getuniformdv,Crash spec@arb_fragment_layer_viewport@layer-no-gs,Fail -# sparse_backing_alloc: Assertion `bo->u.sparse.num_backing_pages < DIV_ROUND_UP(bo->base.size, ZINK_SPARSE_BUFFER_PAGE_SIZE)' failed +# Crashes with VUID-VkSparseMemoryBind-size-01102 due to 2D_3D compability +# issues. KHR-GL46.sparse_texture_tests.SparseTextureCommitment,Crash +# Test fails because it expects 1D images to have 2D block shapes +KHR-GL46.sparse_texture2_tests.StandardPageSizesTestCase,Fail + +# Issue 11073 constains a big explanation on why this fails. The test is using a +# 2D_3D compatible format that ends up being marked by Anv as "everything is +# miptail" and the test is not expecting that. +KHR-GL46.sparse_texture2_tests.UncommittedRegionsAccess,Fail + +# glcts: ../../src/intel/vulkan/anv_sparse.c:970: vk_bind_to_anv_vm_bind: Assertion `vk_bind->memoryOffset + vk_bind->size <= anv_bind.bo->size' failed. +# Also related to https://gitlab.freedesktop.org/mesa/mesa/-/issues/11073 +KHR-GL46.sparse_texture_clamp_tests.SparseTextureClampLookupColor,Crash + +# Error detected at x,y,z: expected [a] got [b] +KHR-GL46.sparse_texture_clamp_tests.SparseTextureClampLookupResidency,Fail +KHR-GL46.sparse_texture2_tests.SparseTexture2Commitment,Fail + +# This one crashes in CI but just fails in other TGL machines. +KHR-GL46.sparse_texture2_tests.SparseTexture2Lookup,Crash + # uprev Piglit in Mesa spec@arb_shader_storage_buffer_object@max-ssbo-size@fs,Crash spec@arb_shader_storage_buffer_object@max-ssbo-size@vs,Crash diff --git a/src/gallium/drivers/zink/ci/zink-anv-tgl-skips.txt b/src/gallium/drivers/zink/ci/zink-anv-tgl-skips.txt index 241cdee87b3..6b4bb31be29 100644 --- a/src/gallium/drivers/zink/ci/zink-anv-tgl-skips.txt +++ b/src/gallium/drivers/zink/ci/zink-anv-tgl-skips.txt @@ -14,6 +14,7 @@ KHR-Single-GL46.enhanced_layouts.xfb_global_buffer KHR-Single-GL46.arrays_of_arrays_gl.SubroutineFunctionCalls1 KHR-GL46.direct_state_access.framebuffers_texture_layer_attachment KHR-GL46.sparse_buffer_tests.BufferStorageTest +KHR-GL46.sparse_texture_clamp_tests.SparseTextureClampLookupColor # Definitely shouldn't take this long, but times out at 3 minutes. glx@glx-visuals-depth$