GPU Bandwidth: Difference between revisions
| Revision as of 05:11, 23 October 2026 RemmyLee (Hardware tests: 72 more test pages, listed on the main page by area; RUN.toml no longer published) | Revision as of 05:41, 23 October 2026 RemmyLee (Hardware tests: See also links back from 37 existing pages to the new ones) | ||
| Line 14: | Line 14: | ||
| The program converts the count to milliseconds with 60 frames of 263 lines a second, and to MB/s from 320 x 240 x 2 bytes for each call. Its millisecond figure prints the remainder of that division after the point unscaled, so the horizontal blank count is the measurement to read.[^src] | The program converts the count to milliseconds with 60 frames of 263 lines a second, and to MB/s from 320 x 240 x 2 bytes for each call. Its millisecond figure prints the remainder of that division after the point unscaled, so the horizontal blank count is the measurement to read.[^src] | ||
| + | See also: | ||
| + | |||
| + | - [GPU Flat Quad Fill Time](/tests/gpu-flat-quad-fill-time/) | ||
| + | |||
| ## Results | ## Results | ||
| Line 39: | Line 43: | ||
| A fill was about six times as fast as a flat rectangle of the same size. A semi-transparent flat rectangle or quad took about 1.5 times the time of an opaque one.[^run] | A fill was about six times as fast as a flat rectangle of the same size. A semi-transparent flat rectangle or quad took about 1.5 times the time of an opaque one.[^run] | ||
| − | Semi-transparency added nothing to the textured rectangle or the textured quad. A textured quad took about 2.6 times the time of a textured rectangle of the same size.[^run] | + | Semi-transparency added nothing to the textured rectangle or the textured quad. A textured quad took about 2.6 times the time of a textured rectangle of the same size.[^run] The quad a quarter off the screen took 76% of the time of the full quad, and the quad half off the screen 52%.[^run] |
| − | The quad a quarter off the screen took 76% of the time of the full quad, and the quad half off the screen 52%.[^run] | ||
| − | |||
| ## Runs | ## Runs | ||