Turnip-Duo-v4.4-exp vs Turnip-v27.0.0-20261029
On Adreno (TM) 740 (AYN Odin2, AYN Odin2 Portal, AYN Thor, HONOR Magic5 Pro, Moorechip Retroid Pocket 6, Moorechip Retroid Pocket Nova, motorola edge plus 2023, OnePlus 11 5G, OnePlus 12R, POCO F6 Pro, Samsung Galaxy S23, Samsung Galaxy S23, Samsung Galaxy S23, Samsung Galaxy S23 Ultra, Samsung Galaxy S23 Ultra, Samsung Galaxy S23+, Samsung Galaxy Z Fold5, Sony Xperia 1 V, Xiaomi 13 pro). The first driver named is compared against the second, which is the baseline.
StockTurnip-v27.0.0-20261029Mesa 27.0.0-devel (git-1c3a936490)
vsCustomTurnip-Duo-v4.4-expMesa 27.0.0-devel (git-74920caaa0)
Graphics system version (Vulkan)? to ?
Optional features (extensions)? to ?not checked on both
Features that pass their check (validated)not tested on bothTurnip-v27.0.0-20261029 and Turnip-Duo-v4.4-exp: no driver check yet
Speed test scenes (benchmark)2 faster 1 slower6% faster overall (geometric mean)
- compute_nbody37% faster
- hdr_2160p21% faster
- pipeline_barriers29% 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 2 scenes (pipeline_barriers: 246 of 2304 cells, pipeline_barriers_2160p: 21 of 2304 cells). The picture matches overall, so this is a local rendering fault, not a different scene.
Not on equal terms: the GPU clock differed during 1 of these scenes (for example compute_nbody: stock at 69% 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.
Turnip-v27.0.0-20261029 details Turnip-Duo-v4.4-exp details
Feature checks that differ
Turnip-v27.0.0-20261029 and Turnip-Duo-v4.4-exp: no driver check (validation report) yet. Both drivers need a driver check before their feature checks can be compared.
Speed test scenes (benchmark)
| Scene | Turnip-v27.0.0-20261029 ms | Turnip-Duo-v4.4-exp ms | Difference | Starts | GPU clock, MHz | Picture vs stock |
|---|
| compute_nbody | 8.09 typical 8.28 | 5.89 typical 5.87 | 37% faster | 3 of 3 vs 3 of 3 | 498 vs 719 not comparable | no large difference 0.0 no small difference worst 0.0 64x36 |
| compute_nbody_2x | n/a | n/a | only one side | ? vs 3 of 3 | ? vs 719 clock unknown | not checked |
| hdr_2160p | 17.64 typical 17.06 | 14.54 typical 14.80 | 21% faster | 3 of 3 vs 3 of 3 | 660 vs 648 | no large difference 0.0 no small difference worst 1.0 64x36 |
| oit_linked_lists | 25.50 | n/a | only one side | 3 of 3 vs 3 of 3 | 719 vs 719 | no large difference 0.0 no small difference worst 0.0 64x36 |
| pipeline_barriers | 2.18 typical 2.16 | 3.06 typical 3.06 | 29% slower | 3 of 3 vs 3 of 3 | 719 vs 719 | no large difference 1.4 differs in 246 small areas worst 40.0 64x36 |
| pipeline_barriers_2160p | n/a | 11.03 | only one side | 3 of 3 vs 3 of 3 | 719 vs 680 not comparable | no large difference 0.4 differs in 21 small areas worst 7.3 64x36 |
| subpasses | n/a | 4.55 | only one side | 3 of 3 vs 3 of 3 | 719 vs 615 not comparable | not checked |
| subpasses_2160p | n/a | 16.70 | only one side | 3 of 3 vs 3 of 3 | 719 vs 719 | 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-Duo-v4.4-exp against Turnip-v27.0.0-20261029. "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)
Both drivers need a driver check (validation report) before their technical details (Vulkan) can be compared.