mali-panvk-27.0.0-devel-r8 vs Mali-G52 MC2
On Mali-G52 (CHUWI HiPad-Air, HONOR X5c, HONOR X5c, Infinix HOT 60i, Oppo A18, Oppo A38, realme RMX3710, Redmi 12, Redmi 12C, Redmi 14C, Redmi 15C, TECNO POVA 3, TECNO SPARK 20, Xiaomi 24049RN28L). The first driver named is compared against the second, which is the baseline.
StockMali-G52 MC2
vsCustommali-panvk-27.0.0-devel-r8
Graphics system version (Vulkan)1.3.278 to 1.3.363
Optional features (extensions)131 to 160+46 -17
Features that pass their check (validated)34 to 4514 pass only on mali-panvk-27.0.0-devel-r8 3 pass only on Mali-G52 MC2
Speed test scenes (benchmark)0 faster 4 slower 1 even14% slower overall (geometric mean)
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
- compute_nbody20% slower
- hdr_2160p2% faster
- oit_linked_lists13% slower
- pipeline_barriers23% slower
- subpasses13% slower
Small areas of the picture differ from the stock driver in 1 scene (pipeline_barriers: 1422 of 2304 cells). The picture matches overall, so this is a local rendering fault, not a different scene.
Mali-G52 MC2 details mali-panvk-27.0.0-devel-r8 details
Feature checks that differ (37)
| Feature | Stock | Custom | Change |
|---|---|---|---|
| transformFeedback | pass | fail | lost |
| shaderBufferInt64Atomics | pass | unsupported | lost |
| limit.uniform_buffer_range | pass | fail | lost |
| colorWriteEnable | unsupported | pass | gained |
| depthClipControl | unsupported | pass | gained |
| extendedDynamicState2LogicOp | unsupported | pass | gained |
| extendedDynamicState3ColorBlendEnable | unsupported | pass | gained |
| extendedDynamicState3ColorBlendEquation | unsupported | pass | gained |
| extendedDynamicState3ColorWriteMask | unsupported | pass | gained |
| extendedDynamicState3DepthClampEnable | unsupported | pass | gained |
| extendedDynamicState3LogicOpEnable | unsupported | pass | gained |
| robustBufferAccess2 | unsupported | pass | gained |
| multiDrawIndirect | unsupported | pass | gained |
| multiViewport | unsupported | pass | gained |
| textureCompressionBC | unsupported | pass | gained |
| push.max_uniform_buffers | unsupported | pass | gained |
| stress.multi_draw_indirect_large | unsupported | pass | gained |
| customBorderColorWithoutFormat | untested | unsupported | changed |
| depthBiasControl | unsupported | untested | changed |
| depthBiasExact | unsupported | untested | changed |
| extendedDynamicState2PatchControlPoints | untested | unsupported | changed |
| extendedDynamicState3AlphaToCoverageEnable | unsupported | untested | changed |
| extendedDynamicState3DepthClipEnable | unsupported | untested | changed |
| extendedDynamicState3ProvokingVertexMode | untested | unsupported | changed |
| extendedDynamicState3RasterizationSamples | unsupported | untested | changed |
| extendedDynamicState3TessellationDomainOrigin | untested | unsupported | changed |
| nullDescriptor | unsupported | untested | changed |
| geometryStreams | unsupported | untested | changed |
| shaderSharedInt64Atomics | untested | unsupported | changed |
| depthClamp | unsupported | untested | changed |
| fillModeNonSolid | unsupported | untested | changed |
| shaderClipDistance | unsupported | untested | changed |
| shaderCullDistance | unsupported | untested | changed |
| vertexPipelineStoresAndAtomics | unsupported | untested | changed |
| compat.helper_loop_terminator | untested | fail | changed |
| compat.nested_map | untested | fail | changed |
| push.max_combined_image_samplers | unsupported | fail | changed |
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.
| Scene | Stock ms | Custom ms | Difference | Starts | GPU clock, MHz | Picture vs stock |
|---|---|---|---|---|---|---|
| compute_nbody | 70.13 | 87.12 | 20% slower | 3 of 3 vs 3 of 3 | ? vs ? | no large difference no small difference |
| hdr_2160p | 150.63 | 148.09 | 2% faster | 3 of 3 vs 3 of 3 | ? vs ? | no large difference no small difference |
| oit_linked_lists | 65.71 | 75.37 | 13% slower | 3 of 3 vs 3 of 3 | ? vs ? | no large difference no small difference |
| pipeline_barriers | 56.80 | 74.16 | 23% slower | 3 of 3 vs 3 of 3 | ? vs ? | no large difference differs in 1422 small areas |
| subpasses | 110.56 | 126.86 | 13% slower | 3 of 3 vs 3 of 3 | ? vs ? | not checked |
Technical differences (Vulkan)
Extensions only in mali-panvk-27.0.0-devel-r8 (46)
- VK_ARM_scheduling_controls
- VK_EXT_attachment_feedback_loop_dynamic_state
- VK_EXT_attachment_feedback_loop_layout
- VK_EXT_buffer_device_address
- VK_EXT_color_write_enable
- VK_EXT_depth_bias_control
- VK_EXT_depth_clamp_control
- VK_EXT_depth_clamp_zero_one
- VK_EXT_depth_clip_control
- VK_EXT_depth_clip_enable
- VK_EXT_graphics_pipeline_library
- VK_EXT_hdr_metadata
- VK_EXT_host_image_copy
- VK_EXT_image_view_min_lod
- VK_EXT_map_memory_placed
- VK_EXT_memory_budget
- VK_EXT_non_seamless_cube_map
- VK_EXT_physical_device_drm
- VK_EXT_robustness2
- VK_EXT_shader_atomic_float
- VK_EXT_shader_module_identifier
- VK_EXT_shader_replicated_composites
- VK_EXT_shader_stencil_export
- VK_EXT_shader_uniform_buffer_unsized_array
- VK_EXT_vertex_attribute_divisor
- VK_EXT_zero_initialize_device_memory
- VK_GOOGLE_hlsl_functionality1
- VK_INTEL_shader_integer_functions2
- VK_KHR_depth_clamp_zero_one
- VK_KHR_internally_synchronized_queues
- VK_KHR_maintenance10
- VK_KHR_maintenance11
- VK_KHR_maintenance7
- VK_KHR_maintenance8
- VK_KHR_maintenance9
- VK_KHR_pipeline_binary
- VK_KHR_pipeline_executable_properties
- VK_KHR_pipeline_library
- VK_KHR_push_descriptor
- VK_KHR_robustness2
- VK_KHR_shader_clock
- VK_KHR_shader_constant_data
- VK_KHR_shader_fma
- VK_KHR_shader_relaxed_extended_instruction
- VK_KHR_unified_image_layouts
- VK_KHR_workgroup_memory_explicit_layout
Extensions only in Mali-G52 MC2 (17)
- VK_ANDROID_external_format_resolve
- VK_ARM_rasterization_order_attachment_access
- VK_EXT_device_fault
- VK_EXT_frame_boundary
- VK_EXT_image_compression_control_swapchain
- VK_EXT_pipeline_protected_access
- VK_EXT_primitives_generated_query
- VK_EXT_rasterization_order_attachment_access
- VK_EXT_rgba10x6_formats
- VK_EXT_shader_image_atomic_int64
- VK_EXT_shader_tile_image
- VK_EXT_subpass_merge_feedback
- VK_KHR_shader_atomic_int64
- VK_KHR_shader_maximal_reconvergence
- VK_KHR_shader_quad_control
- VK_KHR_shader_subgroup_uniform_control_flow
- VK_KHR_shared_presentable_image
Core features that differ (16)
| descriptorBindingVariableDescriptorCount | unsupported to pass |
| runtimeDescriptorArray | unsupported to pass |
| shaderBufferInt64Atomics | pass to unsupported |
| shaderFloat16 | pass to unsupported |
| shaderInputAttachmentArrayDynamicIndexing | unsupported to pass |
| shaderInputAttachmentArrayNonUniformIndexing | unsupported to pass |
| shaderOutputViewportIndex | pass to unsupported |
| shaderSampledImageArrayNonUniformIndexing | unsupported to pass |
| shaderSharedInt64Atomics | pass to unsupported |
| shaderStorageBufferArrayNonUniformIndexing | unsupported to pass |
| shaderStorageImageArrayNonUniformIndexing | unsupported to pass |
| shaderStorageTexelBufferArrayDynamicIndexing | unsupported to pass |
| shaderStorageTexelBufferArrayNonUniformIndexing | unsupported to pass |
| shaderUniformBufferArrayNonUniformIndexing | unsupported to pass |
| shaderUniformTexelBufferArrayDynamicIndexing | unsupported to pass |
| shaderUniformTexelBufferArrayNonUniformIndexing | unsupported to pass |
Limits that differ (52)
| Limit | Stock | Custom |
|---|---|---|
| maxImageDimension1D | 16384 | 65536 |
| maxImageDimension2D | 16384 | 65536 |
| maxImageDimension3D | 16384 | 65536 |
| maxImageDimensionCube | 16384 | 65536 |
| maxImageArrayLayers | 4096 | 65536 |
| maxTexelBufferElements | 268435456 | 134217728 |
| maxUniformBufferRange | 65536 | 1048576 |
| maxStorageBufferRange | 2147483648 | 4294967295 |
| maxMemoryAllocationCount | 16384 | 4294967295 |
| bufferImageGranularity | 1 | 64 |
| sparseAddressSpaceSize | 0 | 30064771072 |
| maxPerStageDescriptorUniformBuffers | 241 | 223 |
| maxPerStageDescriptorStorageBuffers | 35 | 64 |
| maxPerStageDescriptorStorageImages | 21 | 32 |
| maxPerStageResources | 570 | 712 |
| maxDescriptorSetSamplers | 768 | 65535 |
| maxDescriptorSetUniformBuffers | 1446 | 223 |
| maxDescriptorSetUniformBuffersDynamic | 32 | 16 |
| maxDescriptorSetStorageBuffers | 210 | 4096 |
| maxDescriptorSetStorageBuffersDynamic | 32 | 8 |
| maxDescriptorSetSampledImages | 1536 | 65535 |
| maxDescriptorSetStorageImages | 126 | 256 |
| maxVertexInputAttributes | 32 | 16 |
| maxVertexInputBindings | 32 | 16 |
| maxVertexInputAttributeOffset | 2047 | 4294967295 |
| maxVertexInputBindingStride | 2048 | 65535 |
| maxTessellationControlPerVertexInputComponents | 128 | 64 |
| maxTessellationControlPerVertexOutputComponents | 128 | 64 |
| maxTessellationControlTotalOutputComponents | 4096 | 2048 |
| maxTessellationEvaluationInputComponents | 128 | 64 |
| maxTessellationEvaluationOutputComponents | 128 | 64 |
| maxGeometryInputComponents | 128 | 64 |
| maxGeometryTotalOutputComponents | 2048 | 1024 |
| maxFragmentCombinedOutputResources | 64 | 4360 |
| maxComputeWorkGroupCount | 4294967295, 4294967295, 4294967295 | 65535, 65535, 65535 |
| maxDrawIndirectCount | 1 | 4294967295 |
| maxSamplerLodBias | 126 | 127.996 |
| maxViewports | 1 | 16 |
| minMemoryMapAlignment | 64 | 4096 |
| minTexelBufferOffsetAlignment | 64 | 16 |
| minStorageBufferOffsetAlignment | 64 | 16 |
| maxInterpolationOffset | 0.4375 | 0.5 |
| subPixelInterpolationOffsetBits | 4 | 8 |
| framebufferNoAttachmentsSampleCounts | 29 | 5 |
| timestampComputeAndGraphics | 1 | 0 |
| timestampPeriod | 76.9231 | 0 |
| maxClipDistances | 0 | 8 |
| maxCullDistances | 0 | 8 |
| maxCombinedClipAndCullDistances | 0 | 8 |
| pointSizeRange | 1, 1024 | 0.125, 4095.94 |
| lineWidthRange | 1, 4095.94 | 0, 7.99219 |
| lineWidthGranularity | 0.0625 | 0.0078125 |
Formats supported by only one driver (27 gained, 10 lost)
- A2R10G10B10_SNORM_PACK32
- 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
- G10X6_B10X6R10X6_2PLANE_444_UNORM_3PACK16
- G10X6_B10X6_R10X6_3PLANE_420_UNORM_3PACK16
- G10X6_B10X6_R10X6_3PLANE_422_UNORM_3PACK16
- G10X6_B10X6_R10X6_3PLANE_444_UNORM_3PACK16
- G16_B16R16_2PLANE_420_UNORM
- G16_B16R16_2PLANE_422_UNORM
- G16_B16R16_2PLANE_444_UNORM
- G8_B8R8_2PLANE_444_UNORM
- R10X6G10X6_UNORM_2PACK16
- R10X6_UNORM_PACK16
- B10X6G10X6R10X6G10X6_422_UNORM_4PACK16
- B5G5R5A1_UNORM_PACK16
- B8G8R8G8_422_UNORM
- B8G8R8_SNORM
- G10X6B10X6G10X6R10X6_422_UNORM_4PACK16
- G8B8G8R8_422_UNORM
- R4G4_UNORM_PACK8
- R5G5B5A1_UNORM_PACK16
- R64_SINT
- R64_UINT