summaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2013-02-27sna: Prettify GCC version detection in headersChris Wilson
2013-02-27sna: Improve compatibility of cpuid.h detectionChris Wilson
2013-02-27sna: Remove the trailing '.' from the previous commitChris Wilson
2013-02-27sna: Migrate dirty tracking across ScreenPixmap updatesChris Wilson
2013-02-26sna/gen2: Add SSE2 fast paths for vertex emissionChris Wilson
2013-02-26sna: Force GCC to use the SSE unit for SSE2 routinesChris Wilson
2013-02-26sna: Flatten the glyph emittersChris Wilson
2013-02-26sna/gen3: Expand the number of SSE2 routines for basic composite opsChris Wilson
2013-02-26sna/trapezoids: Add a pair of unlikely hints for forced box emissionChris Wilson
2013-02-26sna: Improve handling of migrated userptr boChris Wilson
2013-02-26sna: Flatten unaligned box emissionChris Wilson
2013-02-26sna: Bump required GCC for sse2Chris Wilson
2013-02-26sna: Conditionally compile sse2 routinesChris Wilson
2013-02-26sna: Conditionally compile sse4_2 routinesChris Wilson
2013-02-26sna: Conditionally compile avx routinesChris Wilson
2013-02-26sna/gen4: Cluster ISAChris Wilson
2013-02-26sna/gen4+: All associated CPUs have sse2 at leastChris Wilson
2013-02-26sna: Only use the GPU bo after migratingChris Wilson
2013-02-26sna: Mention if compiled as 64bit as part of the CPU feature detectionChris Wilson
2013-02-26sna: Ignore SSE4a - not an Intel ISA!Chris Wilson
2013-02-26sna/gen3: Allow conditional use of SSE2Chris Wilson
2013-02-26sna: Print detected CPU featuresChris Wilson
2013-02-26sna: Fix build on older GCC for cpuid()Chris Wilson
2013-02-26sna: Reverse inverted assertionsChris Wilson
2013-02-26sna/gen4+: Begin specialising vertex programs for ISAChris Wilson
2013-02-25test: Correct ignore path for async.aviChris Wilson
2013-02-25sna: Detect available instruction sets at runtimeChris Wilson
2013-02-25sna/gen3+: Restart vertex space checks after lock contentionChris Wilson
2013-02-25sna/gen3+: Assert that nbox is not 0Chris Wilson
2013-02-25sna/trapezoids: Instruct the compiler to flatten the callees whilst rasterisingChris Wilson
2013-02-24sna/gen3: Factor out the per-vertex divide for gradientsChris Wilson
2013-02-24sna: Reduce DefaultDepth to 16 on older chipsetsChris Wilson
2013-02-23sna: Tidy a call to set the gamma before setting up a CRTCChris Wilson
2013-02-22Refuse to load driver for depth-8 X server.Carl Worth
2013-02-22sna: Refuse to create larger than max temporary upload boChris Wilson
2013-02-22sna: Retire before looking for a large 2D bufferChris Wilson
2013-02-22sna: Allow search_linear_cache() to reuse large buffersChris Wilson
2013-02-22sna: Allow picture fixup in channel format if not changing RGB depthChris Wilson
2013-02-22sna: Optimise mmap of GPU bo for read-read operationsChris Wilson
2013-02-22sna: Avoid migrating and making the GPU bo busy prior to mmapping itChris Wilson
2013-02-22sna/gen7: Skip CLEAR_PARAMS for the null depthbufferChris Wilson
2013-02-22sna/gen7: Only a pipeline stall is required for the CA passChris Wilson
2013-02-21sna/dri: Eradicate the DRI2 name exchange mechanismChris Wilson
2013-02-21sna: Always enable the solid-cache and gradient-cacheChris Wilson
2013-02-20sna: Honour LinearFramebufferChris Wilson
2013-02-202.21.3 release2.22.32.21.3Chris Wilson
2013-02-20sna/trapezoids: Clamp cells to valid rangeChris Wilson
2013-02-20sna/trapezoids: Embed a few cells into the stackChris Wilson
2013-02-20sna/trapezoids: Perform the cell allocation upfrontChris Wilson
2013-02-19sna/video: Only setup XvMC if we first setup XvChris Wilson
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-22 18:58:30 +0000