WN-Turnip-1.14-p_Axxx vs Qualcomm Technologies Inc. Adreno Vulkan Driver
On Adreno (TM) 740 (AYN Odin2, AYN Odin2 Portal, AYN Thor, Moorechip Retroid Pocket Nova, motorola edge plus 2023, OnePlus 11 5G, POCO F6 Pro, Samsung Galaxy S23, Samsung Galaxy S23, Samsung Galaxy S23, Samsung Galaxy S23 Ultra, Samsung Galaxy S23 Ultra, Samsung Galaxy S23+, Sony Xperia 1 V, Xiaomi 13 pro). The first driver named is compared against the second, which is the baseline.
- hdr_2160p23% slower
- pipeline_barriers_2160p25% faster
- subpasses_2160p13% faster
Small areas of the picture differ from the stock driver in 2 scenes (pipeline_barriers: 1671 of 2304 cells, pipeline_barriers_2160p: 1596 of 2304 cells). The picture matches overall, so this is a local rendering fault, not a different scene.
Did not start every time: compute_nbody (stock 3 of 3, custom 0 of 3).
Not on equal terms: the GPU clock differed during 1 of these scenes (for example pipeline_barriers_2160p: stock at 90% of the device's maximum, custom at 100%). Part of the frame-time difference comes from the clock the device chose, not from the driver.
Qualcomm Technologies Inc. Adreno Vulkan Driver details WN-Turnip-1.14-p_Axxx details
Feature checks that differ (35)
| Feature | Stock | Custom | Change |
|---|---|---|---|
| core.compute_udiv | pass | fail | lost |
| borderColorSwizzle | unsupported | pass | gained |
| extendedDynamicState3ColorBlendEnable | unsupported | pass | gained |
| extendedDynamicState3ColorBlendEquation | unsupported | pass | gained |
| extendedDynamicState3ColorWriteMask | unsupported | pass | gained |
| extendedDynamicState3DepthClampEnable | unsupported | pass | gained |
| extendedDynamicState3LogicOpEnable | unsupported | pass | gained |
| extendedDynamicState3PolygonMode | unsupported | pass | gained |
| inlineUniformBlock | unsupported | pass | gained |
| shaderBufferInt64Atomics | unsupported | pass | gained |
| borderColorSwizzleFromImage | unsupported | untested | changed |
| extendedDynamicState3AlphaToCoverageEnable | unsupported | untested | changed |
| extendedDynamicState3AlphaToOneEnable | unsupported | untested | changed |
| extendedDynamicState3ConservativeRasterizationMode | unsupported | untested | changed |
| extendedDynamicState3DepthClipEnable | unsupported | untested | changed |
| extendedDynamicState3DepthClipNegativeOneToOne | unsupported | untested | changed |
| extendedDynamicState3ExtraPrimitiveOverestimationSize | unsupported | untested | changed |
| extendedDynamicState3LineRasterizationMode | unsupported | untested | changed |
| extendedDynamicState3ProvokingVertexMode | unsupported | untested | changed |
| extendedDynamicState3RasterizationSamples | unsupported | untested | changed |
| extendedDynamicState3RasterizationStream | unsupported | untested | changed |
| extendedDynamicState3SampleLocationsEnable | unsupported | untested | changed |
| extendedDynamicState3SampleMask | unsupported | untested | changed |
| extendedDynamicState3TessellationDomainOrigin | unsupported | untested | changed |
| descriptorBindingInlineUniformBlockUpdateAfterBind | unsupported | untested | changed |
| shaderInt64 | unsupported | untested | changed |
| shaderResourceMinLod | unsupported | untested | changed |
| shaderResourceResidency | unsupported | untested | changed |
| shaderTessellationAndGeometryPointSize | unsupported | untested | changed |
| sparseResidency16Samples | untested | unsupported | changed |
| sparseResidency2Samples | untested | unsupported | changed |
| sparseResidency4Samples | untested | unsupported | changed |
| sparseResidency8Samples | untested | unsupported | changed |
| sparseResidencyAliased | unsupported | untested | changed |
| sparseResidencyImage2D | untested | unsupported | 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 | 7.84 | n/a | only one side | 3 of 3 vs 0 of 3 | 561 vs ? | not checked |
| compute_nbody_2x | 25.49 | n/a | only one side | 3 of 3 vs ? | 550 vs ? | not checked |
| hdr_2160p | 26.73 | 34.82 | 23% slower | 3 of 3 vs 3 of 3 | 550 vs 680 | no large difference no small difference |
| oit_linked_lists | n/a | 26.44 | only one side | 3 of 3 vs 3 of 3 | 719 vs 680 | no large difference no small difference |
| pipeline_barriers | n/a | 2.26 | too light, see pipeline_barriers_2160p | 3 of 3 vs 3 of 3 | 680 vs 680 | no large difference differs in 1671 small areas |
| pipeline_barriers_2160p | 9.55 | 7.62 | 25% faster | 3 of 3 vs 3 of 3 | 495 vs 680 not comparable | no large difference differs in 1596 small areas |
| subpasses | 5.53 | 3.80 | too light, see subpasses_2160p | 3 of 3 vs 3 of 3 | 549 vs 680 not comparable | not checked |
| subpasses_2160p | 15.58 | 13.75 | 13% faster | 3 of 3 vs 3 of 3 | 550 vs 680 | not checked |
Technical differences (Vulkan)
Extensions only in WN-Turnip-1.14-p_Axxx (67)
- VK_AMD_buffer_marker
- VK_ARM_rasterization_order_attachment_access
- VK_EXT_attachment_feedback_loop_dynamic_state
- VK_EXT_attachment_feedback_loop_layout
- VK_EXT_border_color_swizzle
- VK_EXT_conditional_rendering
- VK_EXT_custom_resolve
- VK_EXT_debug_marker
- VK_EXT_depth_clamp_control
- VK_EXT_depth_clamp_zero_one
- VK_EXT_descriptor_buffer
- VK_EXT_device_address_binding_report
- VK_EXT_dynamic_rendering_unused_attachments
- VK_EXT_extended_dynamic_state3
- VK_EXT_external_memory_dma_buf
- VK_EXT_fragment_density_map_offset
- VK_EXT_graphics_pipeline_library
- VK_EXT_host_image_copy
- VK_EXT_image_2d_view_of_3d
- VK_EXT_image_compression_control
- VK_EXT_image_drm_format_modifier
- VK_EXT_inline_uniform_block
- VK_EXT_legacy_dithering
- VK_EXT_legacy_vertex_attributes
- VK_EXT_map_memory_placed
- VK_EXT_memory_budget
- VK_EXT_multi_draw
- VK_EXT_multisampled_render_to_single_sampled
- VK_EXT_mutable_descriptor_type
- VK_EXT_nested_command_buffer
- VK_EXT_non_seamless_cube_map
- VK_EXT_primitive_restart_index
- VK_EXT_primitives_generated_query
- VK_EXT_rasterization_order_attachment_access
- VK_EXT_shader_image_atomic_int64
- VK_EXT_shader_module_identifier
- VK_EXT_shader_replicated_composites
- VK_EXT_shader_subgroup_vote
- VK_EXT_shader_uniform_buffer_unsized_array
- VK_EXT_shader_viewport_index_layer
- VK_EXT_zero_initialize_device_memory
- VK_GOOGLE_decorate_string
- VK_GOOGLE_hlsl_functionality1
- VK_KHR_compute_shader_derivatives
- VK_KHR_dynamic_rendering_local_read
- VK_KHR_index_type_uint8
- VK_KHR_line_rasterization
- VK_KHR_load_store_op_none
- VK_KHR_maintenance5
- VK_KHR_maintenance6
- VK_KHR_maintenance7
- VK_KHR_map_memory2
- VK_KHR_pipeline_library
- VK_KHR_ray_tracing_maintenance1
- VK_KHR_shader_atomic_int64
- VK_KHR_shader_clock
- VK_KHR_shader_expect_assume
- VK_KHR_shader_float_controls2
- VK_KHR_shader_relaxed_extended_instruction
- VK_KHR_shader_subgroup_rotate
- VK_KHR_vertex_attribute_divisor
- VK_KHR_workgroup_memory_explicit_layout
- VK_NV_compute_shader_derivatives
- VK_QCOM_multiview_per_view_render_areas
- VK_QCOM_multiview_per_view_viewports
- VK_VALVE_fragment_density_map_layered
- VK_VALVE_mutable_descriptor_type
Extensions only in Qualcomm Technologies Inc. Adreno Vulkan Driver (10)
- VK_EXT_astc_decode_mode
- VK_EXT_blend_operation_advanced
- VK_EXT_fragment_density_map2
- VK_EXT_swapchain_maintenance1
- VK_KHR_shared_presentable_image
- VK_KHR_swapchain_mutable_format
- VK_QCOM_render_pass_store_ops
- VK_QCOM_render_pass_transform
- VK_QCOM_rotated_copy_commands
- VK_QCOM_tile_properties
Core features that differ (23)
| multiviewGeometryShader | unsupported to pass |
| protectedMemory | pass to unsupported |
| shaderBufferInt64Atomics | unsupported to pass |
| shaderInputAttachmentArrayDynamicIndexing | pass to unsupported |
| shaderInputAttachmentArrayNonUniformIndexing | pass to unsupported |
| shaderOutputLayer | unsupported to pass |
| shaderOutputViewportIndex | unsupported to pass |
| bresenhamLines | unsupported to pass |
| dynamicRenderingLocalRead | unsupported to pass |
| globalPriorityQuery | unsupported to pass |
| hostImageCopy | unsupported to pass |
| indexTypeUint8 | unsupported to pass |
| maintenance5 | unsupported to pass |
| maintenance6 | unsupported to pass |
| pipelineRobustness | unsupported to pass |
| pushDescriptor | unsupported to pass |
| rectangularLines | unsupported to pass |
| shaderExpectAssume | unsupported to pass |
| shaderFloatControls2 | unsupported to pass |
| shaderSubgroupRotate | unsupported to pass |
| shaderSubgroupRotateClustered | unsupported to pass |
| vertexAttributeInstanceRateDivisor | unsupported to pass |
| vertexAttributeInstanceRateZeroDivisor | unsupported to pass |
Limits that differ (18)
| Limit | Stock | Custom |
|---|---|---|
| bufferImageGranularity | 1 | 64 |
| sparseAddressSpaceSize | 562949953421311 | 274877906944 |
| maxPerStageResources | 50331648 | 16777216 |
| maxDescriptorSetUniformBuffersDynamic | 32 | 16 |
| maxDescriptorSetStorageBuffersDynamic | 16 | 8 |
| maxVertexInputAttributeOffset | 4096 | 4095 |
| maxGeometryInputComponents | 128 | 64 |
| maxGeometryOutputVertices | 1024 | 256 |
| maxGeometryTotalOutputComponents | 131072 | 1024 |
| maxFragmentInputComponents | 112 | 128 |
| maxComputeWorkGroupInvocations | 1024 | 2048 |
| minMemoryMapAlignment | 64 | 4096 |
| minStorageBufferOffsetAlignment | 64 | 4 |
| maxFramebufferLayers | 2048 | 1024 |
| discreteQueuePriorities | 3 | 2 |
| optimalBufferCopyOffsetAlignment | 64 | 128 |
| optimalBufferCopyRowPitchAlignment | 64 | 128 |
| nonCoherentAtomSize | 1 | 64 |
Formats supported by only one driver (31 gained, 1 lost)
- A1B5G5R5_UNORM_PACK16
- A2B10G10R10_SSCALED_PACK32
- A2B10G10R10_USCALED_PACK32
- A2R10G10B10_SSCALED_PACK32
- A2R10G10B10_USCALED_PACK32
- A8B8G8R8_SSCALED_PACK32
- A8B8G8R8_USCALED_PACK32
- A8_UNORM
- B8G8R8A8_SSCALED
- B8G8R8A8_USCALED
- B8G8R8_SINT
- B8G8R8_SNORM
- B8G8R8_UINT
- R16G16B16A16_SSCALED
- R16G16B16A16_USCALED
- R16G16B16_SSCALED
- R16G16B16_USCALED
- R16G16_SSCALED
- R16G16_USCALED
- R16_SSCALED
- R16_USCALED
- R64_SINT
- R64_UINT
- R8G8B8A8_SSCALED
- R8G8B8A8_USCALED
- R8G8B8_SSCALED
- R8G8B8_USCALED
- R8G8_SSCALED
- R8G8_USCALED
- R8_SSCALED
- R8_USCALED
- G10X6_B10X6R10X6_2PLANE_420_UNORM_3PACK16