From: Michel Dänzer Date: Thu, 5 Feb 2015 03:46:04 +0000 (+0900) Subject: st/mesa: Don't use PIPE_USAGE_STREAM for GL_PIXEL_UNPACK_BUFFER_ARB X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=a338dc01866ce50bf7555ee8dc08491c7f63b585;p=mesa.git st/mesa: Don't use PIPE_USAGE_STREAM for GL_PIXEL_UNPACK_BUFFER_ARB The latter currently implies CPU read access, so only PIPE_USAGE_STAGING can be expected to be fast. Mesa demos src/tests/streaming_rect on Kaveri (radeonsi): Unpatched: 42 frames in 1.023 seconds = 41.056 FPS Patched: 615 frames in 1.000 seconds = 615.000 FPS Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88658 Cc: "10.3 10.4" Reviewed-by: Marek Olšák --- diff --git a/src/mesa/state_tracker/st_cb_bufferobjects.c b/src/mesa/state_tracker/st_cb_bufferobjects.c index 55f36442a07..90f786cc1f2 100644 --- a/src/mesa/state_tracker/st_cb_bufferobjects.c +++ b/src/mesa/state_tracker/st_cb_bufferobjects.c @@ -256,8 +256,15 @@ st_bufferobj_data(struct gl_context *ctx, break; case GL_STREAM_DRAW: case GL_STREAM_COPY: - pipe_usage = PIPE_USAGE_STREAM; - break; + /* XXX: Remove this test and fall-through when we have PBO unpacking + * acceleration. Right now, PBO unpacking is done by the CPU, so we + * have to make sure CPU reads are fast. + */ + if (target != GL_PIXEL_UNPACK_BUFFER_ARB) { + pipe_usage = PIPE_USAGE_STREAM; + break; + } + /* fall through */ case GL_STATIC_READ: case GL_DYNAMIC_READ: case GL_STREAM_READ: