Graphics system version (Vulkan)1.4.363 to 1.4.359
Optional features (extensions)177 to 174+0-3
Features that pass their check (validated)66 to 70DD-Turnip-v0.3.4 and turnip_faux123_v1.2.1: sent from a device this site could not confirm (unverified)4 pass only on turnip_faux123_v1.2.10 pass only on DD-Turnip-v0.3.4
Speed test scenes (benchmark)2 faster3 slower0% 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_nbody_2x34% slower
hdr_2160p3% faster
oit_linked_lists96% faster
pipeline_barriers_2160p15% slower
subpasses_2160p12% slower
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 (hdr_2160p: 2304 of 2304 cells). The picture matches overall, so this is a local rendering fault, not a different scene.
Unverified DD-Turnip-v0.3.4 and turnip_faux123_v1.2.1: The results below were sent from a device this site could not confirm. A result the site counts replaces them.
Feature
DD-Turnip-v0.3.4
turnip_faux123_v1.2.1
Change
compat.nested_map
core
crash
pass
gained
core.compute_udiv
core
fail
pass
gained
core.copy_wide_row_length
core
fail
pass
gained
stress.spill_helper_lanes
core
untested
pass
gained
Speed test scenes (benchmark)
unverified DD-Turnip-v0.3.4 and turnip_faux123_v1.2.1: 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
DD-Turnip-v0.3.4 ms
turnip_faux123_v1.2.1 ms
Difference
Starts
GPU clock, MHz
Picture vs stock
compute_nbody
10.22 typical 10.17
12.35 typical 12.24
too light, see compute_nbody_2x
3 of 3 vs 3 of 3
? vs 295 clock unknown
no large difference0.0no small differenceworst 0.064x36
compute_nbody_2x
20.35 typical 20.29
30.91 typical 30.92
34% slower
? vs 3 of 3
? vs ? clock unknown
not checked
hdr_2160p
29.48 typical 29.35
28.70 typical 28.35
3% faster
3 of 3 vs 3 of 3
? vs 618 clock unknown
no large difference35.7differs in 2304 small areasworst 83.764x36
oit_linked_lists
49.35 typical 48.79
25.14 typical 25.19
96% faster
3 of 3 vs 3 of 3
? vs 719 clock unknown
no large difference0.0no small differenceworst 0.064x36
pipeline_barriers
4.43 typical 4.42
4.60 typical 4.51
too light, see pipeline_barriers_2160p
3 of 3 vs 3 of 3
? vs 636 clock unknown
no large difference0.0no small differenceworst 0.064x36
pipeline_barriers_2160p
14.86 typical 14.86
17.56 typical 16.97
15% slower
3 of 3 vs 3 of 3
? vs 719 clock unknown
no large difference0.0no small differenceworst 0.064x36
subpasses
7.07 typical 7.07
3.57 typical 3.56
too light, see subpasses_2160p
3 of 3 vs 3 of 3
? vs 719 clock unknown
not checked
subpasses_2160p
25.36 typical 25.35
28.92 typical 27.12
12% slower
3 of 3 vs 3 of 3
? vs 719 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 turnip_faux123_v1.2.1 against DD-Turnip-v0.3.4. "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.