v37_Turnip_Gen8_V37_patch vs Qualcomm Technologies Inc. Adreno Vulkan Driver
On Adreno (TM) 830 (AYN Odin 3). The first driver named is compared against the second, which is the baseline.
StockQualcomm Technologies Inc. Adreno Vulkan DriverDriver Build: 3967b80d3b, Ica4ce9bea6, 1770914544
vsCustomv37_Turnip_Gen8_V37_patchMesa 26.3.0-devel (git-aa35464ee5)
Graphics system version (Vulkan)1.3.284 to ?
Optional features (extensions)164 to ?not checked on both
Features that pass their check (validated)not tested on bothv37_Turnip_Gen8_V37_patch: no driver check yet
Speed test scenes (benchmark)3 faster 0 slower 1 even11% faster overall (geometric mean)
- hdr_2160p13% faster
- oit_linked_lists1% slower
- pipeline_barriers_2160p21% faster
- subpasses_2160p14% 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 2 scenes (pipeline_barriers: 1698 of 2304 cells, pipeline_barriers_2160p: 1038 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).
Not on equal terms: the GPU clock differed during 3 of these scenes (for example oit_linked_lists: stock at 88% 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.
Not compared: 3 scenes with a paced frame rate (compute_nbody, pipeline_barriers, subpasses). At least one of the two drivers was held at a fixed frame rate there, so the two times do not measure the same thing.
Qualcomm Technologies Inc. Adreno Vulkan Driver details v37_Turnip_Gen8_V37_patch details
Feature checks that differ
v37_Turnip_Gen8_V37_patch: no driver check (validation report) yet. Both drivers need a driver check before their feature checks can be compared.
Speed test scenes (benchmark)
| Scene | Stock ms | Custom ms | Difference | Starts | GPU clock, MHz | Picture vs stock |
|---|
| compute_nbody | paced at 4.11 | n/a | not compared | 3 of 3 vs 0 of 3 | 967 vs ? clock unknown | not checked |
| compute_nbody_2x | 8.49 typical 8.42 | n/a | only one side | 3 of 3 vs ? | 967 vs ? clock unknown | not checked |
| hdr_2160p | 13.63 typical 13.52 | 12.11 typical 12.08 | 13% faster | ? vs 3 of 3 | ? vs 1100 clock unknown | not checked |
| oit_linked_lists | 16.38 typical 16.32 | 16.50 typical 16.50 | 1% slower | 3 of 3 vs 3 of 3 | 967 vs 1100 not comparable | no large difference 0.0 no small difference worst 0.0 64x36 |
| pipeline_barriers | paced at 2.73 | 1.33 typical 1.32 | too light, see pipeline_barriers_2160p | 3 of 3 vs 3 of 3 | 967 vs 1083 not comparable | no large difference 9.3 differs in 1698 small areas worst 47.7 64x36 |
| pipeline_barriers_2160p | 6.02 typical 6.15 | 4.96 typical 4.93 | 21% faster | 3 of 3 vs 3 of 3 | 967 vs 1050 not comparable | no large difference 6.4 differs in 1038 small areas worst 51.7 64x36 |
| subpasses | paced at 2.74 | 2.19 typical 2.19 | too light, see subpasses_2160p | 3 of 3 vs 3 of 3 | 967 vs 1100 not comparable | not checked |
| subpasses_2160p | 9.44 typical 9.40 | 8.32 typical 8.25 | 14% faster | 3 of 3 vs 3 of 3 | 967 vs 1083 not comparable | 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 Qualcomm Technologies Inc. Adreno Vulkan Driver. "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.