Home / Quasar Xclipse 940 MAGELLAN Mesa 26.3.0-devel / Compare

Quasar-v0.3.7-bounds vs Quasar-v0.4.0-mesa

On Quasar Xclipse 940 MAGELLAN Mesa 26.3.0-devel (Samsung Galaxy S24+). The first driver named is compared against the second, which is the baseline.

StockQuasar-v0.4.0-mesaMesa 26.3.0-devel

CustomQuasar-v0.3.7-boundsMesa 26.3.0-devel

Graphics system version (Vulkan)1.4.363 to 1.4.363

Optional features (extensions)275 to 274+0 -1

Features that pass their check (validated)52 to 52both pass the same checks

Speed test scenes (benchmark)1 faster 0 slower 3 even2% 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_nbody2% faster
hdr_2160p2% faster
oit_linked_lists3% faster
pipeline_barriers_2160p2% 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: 490 of 2304 cells, pipeline_barriers_2160p: 11 of 2304 cells). The picture matches overall, so this is a local rendering fault, not a different scene.

Quasar-v0.4.0-mesa details Quasar-v0.3.7-bounds details

Feature checks that differ (0)

Every feature check ends the same way on both drivers.

Speed test scenes (benchmark)

Scene	Quasar-v0.4.0-mesa ms	Quasar-v0.3.7-bounds ms	Difference	Starts	GPU clock, MHz	Picture vs stock
compute_nbody	5.44 typical 5.36	5.35 typical 5.24	2% faster	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
compute_nbody_2x	n/a	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
hdr_2160p	30.48 typical 29.83	29.96 typical 30.63	2% faster	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	8.06 typical 8.02	7.81 typical 7.79	3% 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	n/a	4.11	too light, see pipeline_barriers_2160p	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 2.7 differs in 490 small areas worst 65.3 64x36
pipeline_barriers_2160p	9.37 typical 9.34	9.19 typical 9.16	2% faster	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.1 differs in 11 small areas worst 15.0 64x36
subpasses	n/a	n/a	only one side	3 of 3 vs 3 of 3	? vs ? clock unknown	not checked
subpasses_2160p	13.74	n/a	only one side	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 Quasar-v0.3.7-bounds against Quasar-v0.4.0-mesa. "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 Quasar-v0.3.7-bounds (0)

None

Extensions only in Quasar-v0.4.0-mesa (1)

VK_AMD_anti_lag

Core features that differ (0)

None

Limits that differ (0)

Limit	Quasar-v0.4.0-mesa	Quasar-v0.3.7-bounds

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

Only in Quasar-v0.3.7-bounds:

None

Only in Quasar-v0.4.0-mesa:

None