![]() |
Welcome to ftp.nluug.nl Current directory: /ftp/os/NetBSD/NetBSD-release-10/xsrc/external/mit/xf86-video-intel-2014/dist/src/sna/ |
|
Contents of README:SandyBridge's New Acceleration ------------------------------ The guiding principle behind the design is to avoid GPU context switches. On SandyBridge (and beyond), these are especially pernicious because the RENDER and BLT engine are now on different rings and require synchronisation of the various execution units when switching contexts. They were not cheap on early generation, but with the increasing complexity of the GPU, avoiding such serialisations is important. Furthermore, we try very hard to avoid migrating between the CPU and GPU. Every pixmap (apart from temporary "scratch" surfaces which we intend to use on the GPU) is created in system memory. All operations are then done upon this shadow copy until we are forced to move it onto the GPU. Such migration can only be first triggered by: setting the pixmap as the scanout (we obviously need a GPU buffer here), using the pixmap as a DRI buffer (the client expects to perform hardware acceleration and we do not want to disappoint) and lastly using the pixmap as a RENDER target. This last is chosen because when we know we are going to perform hardware acceleration and will continue to do so without fallbacks, using the GPU is much, much faster than the CPU. The heuristic I chose therefore was that if the application uses RENDER, i.e. cairo, then it will only be using those paths and not intermixing core drawing operations and so unlikely to trigger a fallback. The complicating case is front-buffer rendering. So in order to accommodate using RENDER on an application whilst running xterm without a composite manager redirecting all the pixmaps to backing surfaces, we have to perform damage tracking to avoid excess migration of portions of the buffer. |
Name Last modified Size
Parent Directory -
CVS/ 17-Dec-2022 21:58 -
brw/ 17-Dec-2022 21:58 -
fb/ 17-Dec-2022 21:58 -
Makefile.am 10-May-2019 08:22 3.6K
Makefile.in 10-May-2019 08:22 33K
README 10-May-2019 08:22 1.7K
atomic.h 10-May-2019 08:22 3.1K
blt.c 10-May-2019 08:22 28K
compiler.h 10-May-2019 08:22 3.0K
debug.h 10-May-2019 08:22 1.5K
gen2_render.c 10-May-2019 08:22 92K
gen2_render.h 10-May-2019 08:22 28K
gen3_render.c 10-May-2019 08:22 165K
gen3_render.h 10-May-2019 08:22 55K
gen4_common.c 10-May-2019 08:22 2.0K
gen4_common.h 10-May-2019 08:22 1.7K
gen4_render.c 10-May-2019 08:22 86K
gen4_render.h 10-May-2019 08:22 78K
gen4_source.c 10-May-2019 08:22 5.6K
gen4_source.h 10-May-2019 08:22 424
gen4_vertex.c 10-May-2019 08:22 78K
gen4_vertex.h 10-May-2019 08:22 514
gen5_render.c 10-May-2019 08:22 91K
gen5_render.h 10-May-2019 08:22 82K
gen6_common.c 10-May-2019 08:22 2.1K
gen6_common.h 10-May-2019 08:22 4.6K
gen6_render.c 10-May-2019 08:22 99K
gen6_render.h 10-May-2019 08:22 59K
gen7_render.c 10-May-2019 08:22 103K
gen7_render.h 10-May-2019 08:22 53K
gen8_eu.c 10-May-2019 08:22 34K
gen8_eu.h 10-May-2019 08:22 886
gen8_render.c 10-May-2019 08:22 103K
gen8_render.h 10-May-2019 08:22 45K
gen8_vertex.c 10-May-2019 08:22 9.2K
gen8_vertex.h 10-May-2019 08:22 337
kgem.c 10-May-2019 08:22 187K
kgem.h 10-May-2019 08:22 22K
kgem_debug.c 10-May-2019 08:22 17K
kgem_debug.h 10-May-2019 08:22 1.0K
kgem_debug_gen2.c 10-May-2019 08:22 20K
kgem_debug_gen3.c 10-May-2019 08:22 43K
kgem_debug_gen4.c 10-May-2019 08:22 18K
kgem_debug_gen5.c 10-May-2019 08:22 18K
kgem_debug_gen6.c 10-May-2019 08:22 31K
kgem_debug_gen7.c 10-May-2019 08:22 17K
rop.h 10-May-2019 08:22 6.3K
sna.h 10-May-2019 08:22 31K
sna_accel.c 10-May-2019 08:22 463K
sna_acpi.c 10-May-2019 08:22 5.1K
sna_blt.c 10-May-2019 08:22 114K
sna_composite.c 10-May-2019 08:22 32K
sna_cpu.c 10-May-2019 08:22 2.9K
sna_cpuid.h 10-May-2019 08:22 2.1K
sna_damage.c 10-May-2019 08:22 45K
sna_damage.h 10-May-2019 08:22 8.9K
sna_display.c 10-May-2019 08:22 194K
sna_display_fake.c 10-May-2019 08:22 8.5K
sna_dri2.c 10-May-2019 08:22 88K
sna_dri3.c 10-May-2019 08:22 10K
sna_driver.c 10-May-2019 08:22 34K
sna_glyphs.c 10-May-2019 08:22 60K
sna_gradient.c 10-May-2019 08:22 12K
sna_io.c 10-May-2019 08:22 50K
sna_module.h 10-May-2019 08:22 54
sna_present.c 10-May-2019 08:22 12K
sna_reg.h 10-May-2019 08:22 2.8K
sna_render.c 10-May-2019 08:22 61K
sna_render.h 10-May-2019 08:22 21K
sna_render_inline.h 10-May-2019 08:22 8.8K
sna_stream.c 10-May-2019 08:22 4.0K
sna_threads.c 10-May-2019 08:22 8.2K
sna_tiling.c 10-May-2019 08:22 31K
sna_transform.c 10-May-2019 08:22 5.4K
sna_trapezoids.c 10-May-2019 08:22 32K
sna_trapezoids.h 10-May-2019 08:22 11K
sna_trapezoids_boxes.c 10-May-2019 08:22 38K
sna_trapezoids_imprecise.c 10-May-2019 08:22 95K
sna_trapezoids_mono.c 10-May-2019 08:22 39K
sna_trapezoids_precise.c 10-May-2019 08:22 87K
sna_vertex.c 10-May-2019 08:22 1.4K
sna_video.c 10-May-2019 08:22 19K
sna_video.h 10-May-2019 08:22 5.7K
sna_video_hwmc.c 10-May-2019 08:22 6.4K
sna_video_hwmc.h 10-May-2019 08:22 1.6K
sna_video_overlay.c 10-May-2019 08:22 23K
sna_video_sprite.c 10-May-2019 08:22 20K
sna_video_textured.c 10-May-2019 08:22 11K
xassert.h 10-May-2019 08:22 1.6K
NLUUG - Open Systems. Open Standards
Become a member
and get discounts on conferences and more, see the NLUUG website!