FauxVkDB
English
Home / Mali-G610 / Compare

Mesa.26.3.0-panvk.4 vs panvk_faux123_v1.0.1

On Mali-G610 (GameForce Ace, Infinix GT 20 Pro, Infinix NOTE Edge, Nothing Phone (2a) Plus, OnePlus Ace 竞速版, realme 真我 GT NEO 3 150W, Vivo V27, Xiaomi 13T). The first driver named is compared against the second, which is the baseline.

Stockpanvk_faux123_v1.0.1PanVK-kbase RC3-lowmem (Mesa 26.3.0-devel (git-25739f2d26))
vs
CustomMesa.26.3.0-panvk.4Mesa 26.3.0-devel
Graphics system version (Vulkan)1.4.363 to 1.4.354
Optional features (extensions)185 to 141+0 -44
Features that pass their check (validated)65 to 580 pass only on Mesa.26.3.0-panvk.4 7 pass only on panvk_faux123_v1.0.1
Speed test scenes (benchmark)no shared scenes
Games each driver could run (an estimate from its feature list): green likely, yellow maybe, orange limited, red no
StockDX92002+DX102006+DX112009+DX122015+Switch
CustomDX92002+DX102006+DX112009+DX122015+Switch

panvk_faux123_v1.0.1 details Mesa.26.3.0-panvk.4 details

Feature checks that differ (17)

Featurepanvk_faux123_v1.0.1Mesa.26.3.0-panvk.4Change
tessellationShader
VkPhysicalDeviceFeatures
passfaillost
textureCompressionBC
VkPhysicalDeviceFeatures
passunsupportedlost
compat.nested_map
core
passfaillost
core.mrt_partial_kill
core
passfaillost
push.max_combined_image_samplers
core
passcrashlost
stage.geometry_point_size
core
passunsupportedlost
stress.submit_memory
core
passcrashlost
extendedDynamicState3AlphaToOneEnable
VK_EXT_extended_dynamic_state3
untestedunsupportedchanged
extendedDynamicState3ProvokingVertexMode
VK_EXT_extended_dynamic_state3
unsupporteduntestedchanged
extendedDynamicState3TessellationDomainOrigin
VK_EXT_extended_dynamic_state3
unsupporteduntestedchanged
geometryStreams
VK_EXT_transform_feedback
untestedunsupportedchanged
alphaToOne
VkPhysicalDeviceFeatures
untestedunsupportedchanged
depthBounds
VkPhysicalDeviceFeatures
untestedunsupportedchanged
pipelineStatisticsQuery
VkPhysicalDeviceFeatures
untestedunsupportedchanged
shaderTessellationAndGeometryPointSize
VkPhysicalDeviceFeatures
untestedunsupportedchanged
variableMultisampleRate
VkPhysicalDeviceFeatures
untestedunsupportedchanged
mem.image_padding
core
passwarnchanged

Speed test scenes (benchmark)

The two drivers were not measured on the same set of device models. Frame times from different devices do not compare drivers, so read these numbers with that in mind.

Scenepanvk_faux123_v1.0.1 msMesa.26.3.0-panvk.4 msDifferenceStartsGPU clock, MHzPicture vs stock
compute_nbody18.89 typical 18.75n/aonly one side3 of 3 vs ?1000 vs ? clock unknownnot checked
hdr_2160p32.23 typical 31.81n/aonly one side3 of 3 vs ?1000 vs ? clock unknownnot checked
oit_linked_lists24.72 typical 24.72n/aonly one side3 of 3 vs ?883 vs ? clock unknownnot checked
pipeline_barriers8.89 typical 8.89n/aonly one side3 of 3 vs ?1000 vs ? clock unknownnot checked
subpasses18.84 typical 18.85n/aonly one side3 of 3 vs ?1000 vs ? clock unknownnot checked

Time to draw one frame, per scene: the average (mean) frame time of the scene's best round, which is how many frames the driver delivered; lower is faster. "Typical" beside it is the median frame, which can sit well under the average when a driver's frames come in two speeds. A pair of reports made before per-round averages were recorded is compared on the median. A scene whose rounds disagree by more than 15% is left out. A scene marked "paced" was held at that mean frame time by the driver or the display queue, together with at least one other scene of the same run; its time says how the frames were spaced, not how fast the driver rendered, so it is not compared. A scene marked "too light" took under 8 ms at the standard size (1920 by 1080) on both drivers, where the screen's frame queue spaces the frames more than the chip does; its heavier run is the one compared: the row ending in _2160p is the scene drawn at 3840 by 2160, and compute_nbody_2x is that scene with twice the particles. "Faster" and "slower" describe Mesa.26.3.0-panvk.4 against panvk_faux123_v1.0.1. "Picture vs stock" compares one fixed frame per scene as a coarse colour grid (0 is identical, above 40 is a different picture); it finds a scene that was not drawn. Where both reports carry the finer 64x36 grid, the second figure is how many of its 2,304 cells differ by more than 4 of 255, and "worst" is the largest single cell; this is what finds a small rendering error in a picture that otherwise matches. A row marked 16x9 comes from a report made before the finer grid existed. "Starts" is how many of a scene's process starts reached a measured round. A GPU clock marked "not comparable" differed by more than 5% of the device's maximum between the two timings.

Technical differences (Vulkan)

Extensions only in Mesa.26.3.0-panvk.4 (0)
  • None
Extensions only in panvk_faux123_v1.0.1 (44)
  • VK_EXT_pageable_device_local_memory
  • VK_EXT_primitives_generated_query
  • VK_GOOGLE_user_type
  • VK_KHR_calibrated_timestamps
  • VK_KHR_compute_shader_derivatives
  • VK_KHR_copy_memory_indirect
  • VK_KHR_dynamic_rendering
  • VK_KHR_dynamic_rendering_local_read
  • VK_KHR_format_feature_flags2
  • VK_KHR_global_priority
  • VK_KHR_index_type_uint8
  • VK_KHR_internally_synchronized_queues
  • VK_KHR_line_rasterization
  • VK_KHR_load_store_op_none
  • VK_KHR_maintenance4
  • VK_KHR_maintenance5
  • VK_KHR_maintenance6
  • VK_KHR_maintenance7
  • VK_KHR_maintenance8
  • VK_KHR_maintenance9
  • VK_KHR_map_memory2
  • VK_KHR_pipeline_library
  • VK_KHR_present_id
  • VK_KHR_present_id2
  • VK_KHR_present_wait
  • VK_KHR_present_wait2
  • VK_KHR_shader_constant_data
  • VK_KHR_shader_expect_assume
  • VK_KHR_shader_float_controls2
  • VK_KHR_shader_fma
  • VK_KHR_shader_integer_dot_product
  • VK_KHR_shader_maximal_reconvergence
  • VK_KHR_shader_quad_control
  • VK_KHR_shader_relaxed_extended_instruction
  • VK_KHR_shader_subgroup_rotate
  • VK_KHR_shader_subgroup_uniform_control_flow
  • VK_KHR_shader_terminate_invocation
  • VK_KHR_shader_untyped_pointers
  • VK_KHR_swapchain_maintenance1
  • VK_KHR_synchronization2
  • VK_KHR_unified_image_layouts
  • VK_KHR_vertex_attribute_divisor
  • VK_KHR_workgroup_memory_explicit_layout
  • VK_KHR_zero_initialize_workgroup_memory
Core features that differ (2)
shaderOutputLayer Vulkan 1.2pass to unsupported
shaderOutputViewportIndex Vulkan 1.2pass to unsupported
Limits that differ (8)
Limitpanvk_faux123_v1.0.1Mesa.26.3.0-panvk.4
sparseAddressSpaceSize1407374548008960
maxVertexInputAttributes1632
maxVertexInputBindings1632
maxTessellationControlTotalOutputComponents40964216
maxGeometryShaderInvocations6432
maxGeometryOutputComponents12864
minStorageBufferOffsetAlignment416
timestampPeriod41.66670
Formats supported by only one driver (0 gained, 16 lost)

Only in Mesa.26.3.0-panvk.4:

  • None

Only in panvk_faux123_v1.0.1:

  • BC1_RGBA_SRGB_BLOCK
  • BC1_RGBA_UNORM_BLOCK
  • BC1_RGB_SRGB_BLOCK
  • BC1_RGB_UNORM_BLOCK
  • BC2_SRGB_BLOCK
  • BC2_UNORM_BLOCK
  • BC3_SRGB_BLOCK
  • BC3_UNORM_BLOCK
  • BC4_SNORM_BLOCK
  • BC4_UNORM_BLOCK
  • BC5_SNORM_BLOCK
  • BC5_UNORM_BLOCK
  • BC6H_SFLOAT_BLOCK
  • BC6H_UFLOAT_BLOCK
  • BC7_SRGB_BLOCK
  • BC7_UNORM_BLOCK