Home / Adreno (TM) 825 / Compare

v37_Turnip_Gen8_V37_patch vs Turnip-v26.3.0-20261012-A8xx

On Adreno (TM) 825 (Nothing Phone (3), OnePlus Nord 6, Oppo K13 Turbo Pro 5G, Poco F7, Poco F7, REDMI Turbo 4 Pro). The first driver named is compared against the second, which is the baseline.

StockTurnip-v26.3.0-20261012-A8xxMesa 26.3.0-devel (git-1f4952878d)

Customv37_Turnip_Gen8_V37_patchMesa 26.3.0-devel (git-aa35464ee5)

Graphics system version (Vulkan)1.4.363 to 1.4.363

Optional features (extensions)180 to 180+1 -1

Features that pass their check (validated)49 to 49both pass the same checks

Speed test scenes (benchmark)3 faster 0 slower10% 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

oit_linked_lists5% faster
pipeline_barriers_2160p17% faster
subpasses_2160p10% 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: 1486 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).

Turnip-v26.3.0-20261012-A8xx details v37_Turnip_Gen8_V37_patch details

Feature checks that differ (0)

Every feature check ends the same way on both drivers.

Speed test scenes (benchmark)

Scene	Turnip-v26.3.0-20261012-A8xx ms	v37_Turnip_Gen8_V37_patch ms	Difference	Starts	GPU clock, MHz	Picture vs stock
compute_nbody	10.25 typical 10.00	n/a	only one side	3 of 3 vs 0 of 3	? vs ? clock unknown	not checked
hdr_2160p	12.38	n/a	only one side	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
oit_linked_lists	18.49 typical 18.19	17.68 typical 17.44	5% faster	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
pipeline_barriers	2.23 typical 2.05	2.98 typical 2.39	too light, see pipeline_barriers_2160p	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 10.6 differs in 1486 small areas worst 62.7 64x36
pipeline_barriers_2160p	9.74 typical 9.61	8.35 typical 8.28	17% faster	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
subpasses	3.94 typical 3.85	3.90 typical 3.64	too light, see subpasses_2160p	3 of 3 vs 3 of 3	? vs ? clock unknown	not checked
subpasses_2160p	16.38 typical 16.29	14.85 typical 14.85	10% 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 v37_Turnip_Gen8_V37_patch against Turnip-v26.3.0-20261012-A8xx. "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 v37_Turnip_Gen8_V37_patch (1)

VK_EXT_shader_subgroup_ballot

Extensions only in Turnip-v26.3.0-20261012-A8xx (1)

VK_QCOM_rotated_copy_commands

Core features that differ (0)

None

Limits that differ (2)

Limit	Turnip-v26.3.0-20261012-A8xx	v37_Turnip_Gen8_V37_patch
maxComputeSharedMemorySize	65536	32768
maxComputeWorkGroupInvocations	2048	1024

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

Only in v37_Turnip_Gen8_V37_patch:

None

Only in Turnip-v26.3.0-20261012-A8xx:

None