Age | Commit message (Collapse) | Author | |
---|---|---|---|
2009-09-09 | i915g: Add buffer write callback | Jakob Bornecrantz | |
2009-09-09 | i915g: Reorg vbuf code a bit | Jakob Bornecrantz | |
2009-09-09 | i915g: Keep vertex buffers in a fifo | Jakob Bornecrantz | |
2009-09-07 | scons: Don't set LLVM_VERSION if one of the llvm-config calls fails. | Vinson Lee | |
Ubuntu 8.10 has llvm-config version 2.2, which doesn't have nativecodegen. This triggers an exception. | |||
2009-09-07 | llvmpipe: Silent debug statement. | José Fonseca | |
2009-09-07 | llvmpipe: Better abs for floating points. | José Fonseca | |
2009-09-07 | llvmpipe: Code generate the texture sampling inside the shader. | José Fonseca | |
Finally a substantial performance improvement: framerates of apps using texturing tripled, and furthermore, enabling/disabling texturing only affects around 15% of the framerate, which means the bottleneck is now somewhere else. Generated texture sampling code is not complete though -- we always sample from the base level -- so final figures will be different. | |||
2009-09-07 | llvmpipe: Texture sampling code generation primitives. | José Fonseca | |
Only supports single level 2d textures, with neareast and bilinear filtering for now. | |||
2009-09-07 | llvmpipe: Convenience function to obtain the integer type with same bitdepth ↵ | José Fonseca | |
of an arbitrary type. | |||
2009-09-07 | llvmpipe: Utility functions for linear and bilinear interpolation. | José Fonseca | |
2009-09-07 | llvmpipe: Correct implementation of floor. | José Fonseca | |
2009-09-07 | llvmpipe: Utility function to get the pointer to a structure member. | José Fonseca | |
2009-09-07 | llvmpipe: SoA pixel unpacking specialization. | José Fonseca | |
2009-09-07 | llvmpipe: Further abstract the texture sampling generation from TGSI ↵ | José Fonseca | |
translation. | |||
2009-09-06 | r300g: Fix a number of warnings | Nicolai Hähnle | |
Seriously guys.... | |||
2009-09-06 | r300g: Debug flags infrastructure | Nicolai Hähnle | |
So that debugging is no longer a full-spam-or-nothing approach, you are now supposed to set the RADEON_DEBUG environment flag just like for classic Mesa. The available debug flags are different, however. Just running an OpenGL application with RADEON_DEBUG set to an arbitrary string will print out helpful information. Everything must be compiled with -DDEBUG for any of this to work | |||
2009-09-05 | r300g: update the value of register VAP_VF_MAX_VTX_INDX | Cooper Yuan | |
according to actual vertex index count. | |||
2009-09-05 | r300g: update rs_block state after changing rasterizer | Cooper Yuan | |
2009-09-05 | r300g: need to validate scissor and viewport state if bind new rasterizer | Cooper Yuan | |
2009-09-04 | i915g: Fix warnings in scons build by using byte pointers | Jakob Bornecrantz | |
scons build complained about void pointer math | |||
2009-09-03 | i915g: Don't send flush flags to HW | Jakob Bornecrantz | |
2009-09-03 | nv50: move centroid, flat bits when making interp long | Christoph Bumiller | |
Before this, just the perspective divide bit was moved in convert_to_long of the load interpolant instruction. | |||
2009-09-03 | nv50: fix vbo_static_attrib method size error | Christoph Bumiller | |
The VTX_ATTR_3/2/1F methods also had size 4 ... a stupid copy/paste error. | |||
2009-09-03 | nv50: fix draw_elements_inline_u08/16 | Christoph Bumiller | |
We've been emitting the same two indices over and over without incrementing map. | |||
2009-09-03 | r300g: specify point/line/triangle have stuffed texture coord | Cooper Yuan | |
2009-09-02 | nv50: SWZ is the same as MOV from our perspective | Ben Skeggs | |
2009-09-01 | tgsi: remove redundant CND0 opcode | Keith Whitwell | |
Can be implemented with CMP src2, src1, src0 | |||
2009-09-01 | scons: Tool for LLVM. Gracefully disable llvmpipe if LLVM not found. | José Fonseca | |
2009-09-01 | trace: Don't set surface_[fill|copy] if not set on pipe | Jakob Bornecrantz | |
2009-09-01 | r300g: Fix clear issue on r300 | Cooper Yuan | |
2009-09-01 | i915g: Switch from pipe_winsys to intel_winsys | Jakob Bornecrantz | |
Also includes moving lots of functions from i915_batch.h into intel_batchbuffer.h | |||
2009-09-01 | i915g: Add header file for new winsys interface | Jakob Bornecrantz | |
2009-09-01 | i915g: Add new buffer code not yet hocked up | Jakob Bornecrantz | |
2009-08-31 | i915g: Reorg texture layout code | Jakob Bornecrantz | |
2009-08-31 | i915g: Move transfer functions into i915_texture.c | Jakob Bornecrantz | |
2009-08-31 | i915g: Reorg texture code a bit | Jakob Bornecrantz | |
2009-08-31 | i915g: Don't use winsys directly in the driver | Jakob Bornecrantz | |
2009-08-31 | i915g: Cleanup i915_prim_vbuf.c | Jakob Bornecrantz | |
2009-08-31 | i915g: Cleanup i915_screen.[c|h] | Jakob Bornecrantz | |
2009-08-31 | i915g: Cleanup i915_context.c | Jakob Bornecrantz | |
2009-08-31 | i915g: Cleanup i915_blit.[c|h] | Jakob Bornecrantz | |
2009-08-31 | i915g: Cleanup i915_state_emit.c | Jakob Bornecrantz | |
2009-08-31 | i915g: Cleanup i915_texture.c | Jakob Bornecrantz | |
2009-08-31 | i915g: Cleanup texture init functions a bit | Jakob Bornecrantz | |
2009-08-31 | i915g: Rename pipe field on context to base | Jakob Bornecrantz | |
2009-08-31 | i915g: Rename screen field on screen to base | Jakob Bornecrantz | |
2009-08-31 | llvmpipe: Fallback to element-wise comparisons when no comparison intrinsic ↵ | José Fonseca | |
is available. Although selection of vector elements is valid LLVM IR, no machine target supports it yet. This is a last-resort option, but it allows llvmpipe to be used on any target supported by LLVM without modifications. Obviously better performance is attainable by emitting SIMD intrinsics where otherwise LLVM doesn't. | |||
2009-08-31 | llvmpipe: In the abcense of a min/max intrinsic, use the comparison intrinsics. | José Fonseca | |
2009-08-31 | llvmpipe: Actually commit lp_buffer.[ch]. | José Fonseca | |
Thanks Michel. | |||
2009-08-31 | nouveau: introduce nouveau_miptree common to all nouveau pipe drivers | Ben Skeggs | |
The winsys once again has to know about textures it seems, so we need a common representation between all our pipe drivers to store some information the winsys will need. Only the nv50 driver has been fixed so far. |