Hi; Here's another try to inline sse41 code and get rid of gtt maps in intel_miptree_map (revert 58fb613a519). To be able to safely utilize sse41 we separate sse41 functionality as a library and then choose run time if we want to use it.
Couple of different approaches were tried, this one seems one with minimal overall changes. // Tapani Scott D Phillips (2): i965/tiled_memcpy: inline movntdqa loads in tiled_to_linear i965/miptree: Use cpu tiling/detiling when mapping Tapani Pälli (1): i965: expose type of memcpy instead of memcpy function itself src/mesa/drivers/dri/i965/Android.mk | 38 ++++ src/mesa/drivers/dri/i965/Makefile.am | 14 ++ src/mesa/drivers/dri/i965/Makefile.sources | 10 +- src/mesa/drivers/dri/i965/intel_mipmap_tree.c | 110 +++++++++- src/mesa/drivers/dri/i965/intel_pixel_read.c | 6 +- src/mesa/drivers/dri/i965/intel_tex_image.c | 14 +- .../drivers/dri/i965/intel_tiled_memcpy.c | 192 ++++++++++-------- .../drivers/dri/i965/intel_tiled_memcpy.h | 86 +++++++- .../dri/i965/intel_tiled_memcpy_normal.c | 59 ++++++ .../dri/i965/intel_tiled_memcpy_sse41.c | 61 ++++++ .../dri/i965/intel_tiled_memcpy_sse41.h | 59 ++++++ src/mesa/drivers/dri/i965/meson.build | 38 +++- 12 files changed, 579 insertions(+), 108 deletions(-) create mode 100644 src/mesa/drivers/dri/i965/intel_tiled_memcpy_normal.c create mode 100644 src/mesa/drivers/dri/i965/intel_tiled_memcpy_sse41.c create mode 100644 src/mesa/drivers/dri/i965/intel_tiled_memcpy_sse41.h -- 2.17.1 _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev