summaryrefslogtreecommitdiff
path: root/src/gallium/drivers
AgeCommit message (Collapse)AuthorFilesLines
2012-05-18radeonsi: Only honour point related rasterizer state when rendering points.Michel Dänzer1-2/+3
Avoids hangs when not rendering points.
2012-05-18radeonsi: Fix parameter cache offsets for fragment shader inputs.Michel Dänzer3-2/+4
2012-05-17radeon/llvm: Fix segfault while lowering lrp intrinsicTom Stellard1-2/+3
2012-05-17radeon/llvm: Add DAG nodes for MIN instructionsTom Stellard6-14/+38
Also, remove the AMDIL MIN* instruction defs.
2012-05-18llvmpipe: Avoid adding floating point zero to flat inputs.José Fonseca1-1/+4
Which could clobber integer inputs, if the addition is not optimized away (e.g., if optimizations are disabled for debugging purposes).
2012-05-18llvmpipe: Implement TXQ.Olivier Galibert1-0/+23
Piglits test for fragment shaders pass, vertex shaders fail. The actual failure seems to be in the interpolators, and not the textureSize query. Signed-off-by: Olivier Galibert <galibert@pobox.com> Reviewed-by: Roland Scheidegger <sroland@vmware.com> Reviewed-by: José Fonseca <jose.r.fonseca@gmail.com>
2012-05-18llvmpipe: Don't mess with the provoking vertex when inverting a triangle.Olivier Galibert1-5/+40
Fixes a bunch of piglit tests related to flat interpolation of floats. Signed-off-by: Olivier Galibert <galibert@pobox.com> Signed-off-by: José Fonseca <jose.r.fonseca@gmail.com>
2012-05-17radeon/llvm: Lower lrp intrinsic during ISelTom Stellard3-7/+19
2012-05-17radeon/llvm: Remove AMDIL MAD instruction defsTom Stellard6-7/+14
2012-05-17radeon/llvm: Remove AMDIL MUL_IEEE* instructionsTom Stellard3-7/+3
2012-05-17r600g: Handle MUL_IEEE in r600_bytecode_get_num_operandsTom Stellard1-0/+2
2012-05-17radeon/llvm: Expand fsub during ISelTom Stellard2-11/+2
2012-05-17radeon/llvm: Remove AMDIL floating-point ADD instruction defsTom Stellard5-8/+9
2012-05-17radeon/llvm: Remove AMDIL CMOVLOG* instruction defsTom Stellard4-26/+6
2012-05-17radeon/llvm: Move lowering of ABS_i32 to ISelTom Stellard4-17/+16
2012-05-17radeon/llvm: Remove sub patterns from AMDILInstrPatterns.tdTom Stellard2-21/+1
2012-05-17radeon/llvm: Add custom SDNodes for MAXTom Stellard10-10/+108
We now lower the various intrinsics for max to SDNodes and then use tablegen patterns to lower the SDNodes to instructions.
2012-05-17nouveau: place static buffers in VRAM if preferred by the driverChristoph Bumiller6-12/+62
2012-05-17nv50/ir: fix reversed order of lane ops in quadopsChristoph Bumiller2-4/+6
2012-05-17nv50,nvc0: handle user vertex buffersChristoph Bumiller14-308/+423
And restructure VBO validation a little in the process.
2012-05-17nv50,nvc0: handle user index buffersChristoph Bumiller8-47/+49
2012-05-17nv50,nvc0: handle user constbufs without wrapping them in a resourceChristoph Bumiller14-165/+201
2012-05-16gallium/radeon: Fix r300g tiling breakage.Michel Dänzer4-0/+4
Commit 11f056a3f0b87e86267efa8b5ac9d36a343c9dc1 broke the r300g build. Fix it up, and reinstate some code which isn't needed by r600g and radeonsi but is by r300g.
2012-05-16radeonsi: Initial tiling support.Michel Dänzer5-128/+356
Largely based on the corresponding Evergreen support in r600g.
2012-05-16r600g: Set tiling information for BOs being shared.Michel Dänzer1-0/+12
Fixes https://bugs.freedesktop.org/show_bug.cgi?id=48747
2012-05-16radeonsi: Bump MAX_DRAW_CS_DWORDS.Michel Dänzer3-3/+3
I missed this when updating si_context_draw().
2012-05-16draw,llvmpipe: Avoid named struct types on LLVM 3.0 and later.José Fonseca1-10/+2
Starting with LLVM 3.0, named structures are meant not for debugging, but for recursive data types, previously also known as opaque types. The recursive nature of these types leads to several memory management difficulties. Given that we don't actually need recursive types, avoid them altogether. This is an attempt to address fdo bugs 41791 and 44466. The issue is somewhat random so there's no easy way to check how effective this is.
2012-05-16llvmpipe: Color slot interpolation can be flat or perspective, not linear.Olivier Galibert3-3/+3
Fixes a bunch of glsl 1.10 interpolation piglit tests. Signed-off-by: Olivier Galibert <galibert@pobox.com> Signed-off-by: José Fonseca <jfonseca@vmware.com>
2012-05-15llvmpipe: Add a test for lp_build_sgn.José Fonseca1-0/+13
Only floating point though, but better than nothing.
2012-05-15svga: fix FBO / viewport bugsBrian Paul1-7/+24
When drawing to a FBO, the viewport wasn't always set correctly. It was fine in the usual case of the viewport dims matching the surface dims but broken otherwise. In particular, this was happening because the viewport scale is negative for FBO rendering. The piglit fbo-viewport test exercises this. Reviewed-by: José Fonseca <jfonseca@vmware.com>
2012-05-15radeon/llvm: add support for texture offsets, fix TEX_LDVadim Girlin4-10/+51
Signed-off-by: Vadim Girlin <vadimgirlin@gmail.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
2012-05-15radeon/llvm: add SET_GRADIENTS*, fix SAMPLE_GVadim Girlin6-9/+108
Signed-off-by: Vadim Girlin <vadimgirlin@gmail.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
2012-05-15radeon/llvm: increase const regs countVadim Girlin1-1/+1
Signed-off-by: Vadim Girlin <vadimgirlin@gmail.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
2012-05-15radeon/llvm: use IntrNoMem property for intrinsics where possibleVadim Girlin7-105/+171
Signed-off-by: Vadim Girlin <vadimgirlin@gmail.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
2012-05-15radeon/llvm: use correct intrinsic for CEILVadim Girlin2-3/+3
Should be round_posinf instead of round_neginf. Signed-off-by: Vadim Girlin <vadimgirlin@gmail.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
2012-05-15radeon/llvm: improve ABS_i32 loweringVadim Girlin1-13/+5
We can save one instruction by lowering it to: SUB_INT tmp, 0, src MAX_INT dst, src, tmp Signed-off-by: Vadim Girlin <vadimgirlin@gmail.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
2012-05-15radeon/llvm: fix BUILD_VECTOR lowering for replicated valueVadim Girlin1-0/+2
We expect that all elements will be assigned even if they are equal Signed-off-by: Vadim Girlin <vadimgirlin@gmail.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
2012-05-15radeon/llvm: add names for AMDGPU* passesVadim Girlin2-0/+5
Signed-off-by: Vadim Girlin <vadimgirlin@gmail.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
2012-05-15radeon/llvm: add generated files to .gitignoreVadim Girlin1-0/+18
Signed-off-by: Vadim Girlin <vadimgirlin@gmail.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
2012-05-14radeonsi: Keep around copies of original sampler states.Michel Dänzer1-0/+2
Fixes crashes when restoring sampler states after blits.
2012-05-14radeonsi: Flesh out shader interpolation related code.Michel Dänzer3-4/+38
Handle perspective interpolation and ceontroid vs. center.
2012-05-14radeonsi: Add proper SI family names.Michel Dänzer1-1/+3
2012-05-14radeonsi: Separate states for samplers and sampler views.Michel Dänzer2-3/+6
And reset nregs on updates. Prevents eventual assertion failure.
2012-05-14radeonsi: Fixups for drawing with an index buffer.Michel Dänzer3-14/+13
Mostly using the DRAW_INDEX_2 type 3 packet instead of DRAW_INDEX, which is no longer supported on SI.
2012-05-14llvmpipe: Calculate fixed point coordinates for triangle setup earlier.James Benton1-56/+106
This allows us to calculate the triangle's area using fixed point, previously it was cacluated in floating point space. It was possible that a triangle which had negative area in floating point space had a positive area in fixed point space. Fixes fdo 40920. Reviewed-by: Jose Fonseca <jfonseca@vmware.com> Reviewed-by: Brian Paul <brianp@vmware.com>
2012-05-14radeon/llvm: Coding style fixes for R600CodeEmitter.cppTom Stellard1-148/+90
2012-05-14radeon/llvm: Lower bitcast instructions to copiesTom Stellard1-0/+10
2012-05-13radeonsi: remove slab allocator for pipe_resource (used mainly for user buffers)Marek Olšák3-41/+3
2012-05-13r600g: remove slab allocator for pipe_resource (used mainly for user buffers)Marek Olšák3-41/+4
2012-05-12r600g: handle R16G16B16_FLOAT and R32G32B32_FLOAT in translate_colorswap (EG)Marek Olšák1-0/+2
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-05 22:15:25 +0000