Home / Samsung Xclipse 920 / Compare

RADV-Xclipse-Android--1- vs radv-xclipse-26.3.0-devel-05b3092

On Samsung Xclipse 920 (Samsung Galaxy S22, Samsung Galaxy S23 FE, Samsung Galaxy S24 FE, Samsung Galaxy S24+). The first driver named is compared against the second, which is the baseline.

Stockradv-xclipse-26.3.0-devel-05b3092Mesa 26.3.0-devel (git-05b3092fcc)

CustomRADV-Xclipse-Android--1-Mesa 26.3.0-devel (git-cd638916b5)

Graphics system version (Vulkan)1.4.358 to 1.4.358

Optional features (extensions)228 to 228+0 -0

Features that pass their check (validated)50 to 522 pass only on RADV-Xclipse-Android--1- 0 pass only on radv-xclipse-26.3.0-devel-05b3092

Speed test scenes (benchmark)1 faster 1 slower 1 even8% slower 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_2x0% slower
hdr_2160p4% faster
pipeline_barriers_2160p25% 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: 1500 of 2304 cells, pipeline_barriers_2160p: 7 of 2304 cells). The picture matches overall, so this is a local rendering fault, not a different scene.

radv-xclipse-26.3.0-devel-05b3092 details RADV-Xclipse-Android--1- details

Feature checks that differ (2)

Feature	radv-xclipse-26.3.0-devel-05b3092	RADV-Xclipse-Android--1-	Change
transformFeedback VK_EXT_transform_feedback	fail	pass	gained
tessellationShader VkPhysicalDeviceFeatures	fail	pass	gained

Speed test scenes (benchmark)

Scene	radv-xclipse-26.3.0-devel-05b3092 ms	RADV-Xclipse-Android--1- ms	Difference	Starts	GPU clock, MHz	Picture vs stock
compute_nbody	6.10 typical 6.04	6.66 typical 6.50	too light, see compute_nbody_2x	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	19.29 typical 18.44	19.37 typical 19.38	0% slower	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
hdr_2160p	41.15 typical 39.15	39.63 typical 39.41	4% 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	6.93	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
pipeline_barriers	n/a	n/a	too light, see pipeline_barriers_2160p	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 8.7 differs in 1500 small areas worst 76.3 64x36
pipeline_barriers_2160p	14.25 typical 15.04	19.06 typical 19.54	25% slower	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.1 differs in 7 small areas worst 7.3 64x36
subpasses	n/a	n/a	only one side	3 of 3 vs 3 of 3	? vs ? clock unknown	not checked
subpasses_2160p	n/a	32.72	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 RADV-Xclipse-Android--1- against radv-xclipse-26.3.0-devel-05b3092. "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 RADV-Xclipse-Android--1- (0)

None

Extensions only in radv-xclipse-26.3.0-devel-05b3092 (0)

None

Core features that differ (0)

None

Limits that differ (0)

Limit	radv-xclipse-26.3.0-devel-05b3092	RADV-Xclipse-Android--1-

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

Only in RADV-Xclipse-Android--1-:

None

Only in radv-xclipse-26.3.0-devel-05b3092:

None