turnip_faux123_v1.2.0 vs turnip_faux123_v1.1.9-rc14

On Adreno (TM) 830 (AYN Odin 3). The first driver named is compared against the second, which is the baseline.

Stockturnip_faux123_v1.1.9-rc14Mesa 26.3.0-devel (git-dd45fd0baa)

Customturnip_faux123_v1.2.0Mesa 26.3.0-devel (git-dd45fd0baa)

Graphics system version (Vulkan)1.4.359 to 1.4.359

Optional features (extensions)172 to 172+0 -0

Features that pass their check (validated)51 to 6615 pass only on turnip_faux123_v1.2.0 0 pass only on turnip_faux123_v1.1.9-rc14

Speed test scenes (benchmark)3 faster 0 slower 2 even24% 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_nbody_2x28% faster
hdr_2160p121% faster
oit_linked_lists1% faster
pipeline_barriers_2160p0% slower
subpasses_2160p3% faster

Custom driver against stock, per scene. Bars to the right are faster, to the left slower.

Not on equal terms: the GPU clock differed during 1 of these scenes (for example hdr_2160p: stock at 83% of the device's maximum, custom at 96%). Part of the frame-time difference comes from the clock the device chose, not from the driver.

turnip_faux123_v1.1.9-rc14 details turnip_faux123_v1.2.0 details

Feature checks that differ (15)

Feature	turnip_faux123_v1.1.9-rc14	turnip_faux123_v1.2.0	Change
depthClamp VkPhysicalDeviceFeatures	untested	pass	gained
largePoints VkPhysicalDeviceFeatures	untested	pass	gained
compat.helper_loop_terminator core	untested	pass	gained
compat.nested_map core	untested	pass	gained
core.blend_advertised_formats core	untested	pass	gained
core.compute_big_stack core	untested	pass	gained
core.host_coherent_readback core	untested	pass	gained
core.mrt_partial_kill core	untested	pass	gained
core.ubo_update_buffer core	untested	pass	gained
core.ubo_written_after_record core	untested	pass	gained
core.varying_subset core	untested	pass	gained
mem.image_padding core	untested	pass	gained
stage.geometry_max_output core	untested	pass	gained
stage.geometry_point_size core	untested	pass	gained
sync.first_submit_clear_then_compute core	untested	pass	gained

Speed test scenes (benchmark)

Scene	turnip_faux123_v1.1.9-rc14 ms	turnip_faux123_v1.2.0 ms	Difference	Starts	GPU clock, MHz	Picture vs stock
compute_nbody	n/a	2.70	too light, see compute_nbody_2x	3 of 3 vs 3 of 3	1100 vs 1100	no large difference 0.0 no small difference worst 0.0 64x36
compute_nbody_2x	10.82 typical 10.79	8.42 typical 8.33	28% faster	3 of 3 vs 3 of 3	1100 vs 1067	no large difference 0.0 no small difference worst 0.0 64x36
hdr_2160p	17.25 typical 17.42	7.80 typical 7.87	121% faster	3 of 3 vs 3 of 3	911 vs 1058 not comparable	no large difference 0.0 no small difference worst 0.3 64x36
oit_linked_lists	17.46 typical 17.45	17.31 typical 17.30	1% faster	3 of 3 vs 3 of 3	1100 vs 1100	no large difference 0.0 no small difference worst 0.0 64x36
pipeline_barriers	n/a	1.42	too light, see pipeline_barriers_2160p	3 of 3 vs 3 of 3	1100 vs 1100	no large difference 0.0 no small difference worst 0.0 64x36
pipeline_barriers_2160p	5.96 typical 5.58	5.97 typical 5.57	0% slower	3 of 3 vs 3 of 3	995 vs 967	no large difference 0.0 no small difference worst 0.0 64x36
subpasses	2.52 typical 2.30	2.46 typical 2.29	too light, see subpasses_2160p	3 of 3 vs 3 of 3	1100 vs 1100	not checked
subpasses_2160p	9.68 typical 9.65	9.37 typical 9.57	3% faster	3 of 3 vs 3 of 3	1036 vs 1061	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_v1.2.0 against turnip_faux123_v1.1.9-rc14. "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 turnip_faux123_v1.2.0 (0)

None

Extensions only in turnip_faux123_v1.1.9-rc14 (0)

None

Core features that differ (0)

None

Limits that differ (0)

Limit	turnip_faux123_v1.1.9-rc14	turnip_faux123_v1.2.0

Formats supported by only one driver (0 gained, 0 lost)

Only in turnip_faux123_v1.2.0:

None

Only in turnip_faux123_v1.1.9-rc14:

None