Graphics system version (Vulkan)1.3.363 to 1.3.354
Optional features (extensions)159 to 142+3-20
Features that pass their check (validated)54 to 55PanVK-FristOneRR-V.3.6.0: sent from a device this site could not confirm (unverified)2 pass only on PanVK-FristOneRR-V.3.6.01 pass only on panvk_faux123_v1.1.3
Speed test scenes (benchmark)2 faster3 slower69% faster 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_nbody18% faster
hdr_2160p12% slower
oit_linked_lists14% slower
pipeline_barriers3% slower
subpasses1481% faster
Custom driver against stock, per scene. Bars to the right are faster, to the left slower.
Small areas of the picture differ from the stock driver in 1 scene (pipeline_barriers: 1636 of 2304 cells). The picture matches overall, so this is a local rendering fault, not a different scene.
Unverified PanVK-FristOneRR-V.3.6.0: The results below were sent from a device this site could not confirm. A result the site counts replaces them.
Feature
panvk_faux123_v1.1.3
PanVK-FristOneRR-V.3.6.0
Change
textureCompressionBC
VkPhysicalDeviceFeatures
pass
unsupported
lost
robustBufferAccess2
VK_EXT_robustness2
unsupported
pass
gained
stress.scratch_per_batch
core
unsupported
pass
gained
nullDescriptor
VK_EXT_robustness2
unsupported
untested
changed
Speed test scenes (benchmark)
unverified PanVK-FristOneRR-V.3.6.0: The times below were sent from a device this site could not confirm. A result the site counts replaces them.
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
panvk_faux123_v1.1.3 ms
PanVK-FristOneRR-V.3.6.0 ms
Difference
Starts
GPU clock, MHz
Picture vs stock
compute_nbody
88.87 typical 88.44
75.15 typical 74.98
18% faster
3 of 3 vs 3 of 3
? vs ? clock unknown
no large difference0.1no small differenceworst 3.064x36
hdr_2160p
147.08 typical 146.02
167.46 typical 165.54
12% slower
3 of 3 vs 3 of 3
? vs ? clock unknown
no large difference0.0no small differenceworst 0.064x36
oit_linked_lists
76.53 typical 77.81
88.56 typical 88.31
14% slower
3 of 3 vs 3 of 3
? vs ? clock unknown
no large difference0.0no small differenceworst 0.064x36
pipeline_barriers
72.64 typical 73.73
74.84 typical 74.84
3% slower
3 of 3 vs 3 of 3
? vs ? clock unknown
no large difference10.6differs in 1636 small areasworst 65.064x36
subpasses
130.57 typical 130.09
8.26 typical 3.90
1481% faster
3 of 3 vs 3 of 3
? vs ? clock unknown
not 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 PanVK-FristOneRR-V.3.6.0 against panvk_faux123_v1.1.3. "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 PanVK-FristOneRR-V.3.6.0 (3)
VK_EXT_external_memory_host
VK_EXT_robustness2
VK_EXT_vertex_attribute_robustness
Extensions only in panvk_faux123_v1.1.3 (20)
VK_EXT_astc_decode_mode
VK_EXT_image_compression_control
VK_EXT_map_memory_placed
VK_EXT_present_timing
VK_EXT_swapchain_maintenance1
VK_GOOGLE_user_type
VK_KHR_internally_synchronized_queues
VK_KHR_maintenance7
VK_KHR_maintenance8
VK_KHR_maintenance9
VK_KHR_present_id
VK_KHR_present_id2
VK_KHR_present_wait
VK_KHR_present_wait2
VK_KHR_shader_constant_data
VK_KHR_shader_fma
VK_KHR_shader_relaxed_extended_instruction
VK_KHR_swapchain_maintenance1
VK_KHR_swapchain_mutable_format
VK_KHR_unified_image_layouts
Core features that differ (1)
shaderFloat16 Vulkan 1.2
unsupportedtopass
Limits that differ (3)
Limit
panvk_faux123_v1.1.3
PanVK-FristOneRR-V.3.6.0
sparseAddressSpaceSize
17146314752
0
maxBoundDescriptorSets
7
4
viewportSubPixelBits
0
8
Formats supported by only one driver (0 gained, 0 lost)