Age | Commit message (Collapse) | Author | |
---|---|---|---|
2010-03-10 | i965: Use the PLN instruction when possible in interpolation. | Eric Anholt | |
Saves an instruction in PINTERP, LINTERP, and PIXEL_W from brw_wm_glsl.c For non-GLSL it isn't used yet because the deltas have to be laid out differently. | |||
2010-03-10 | i965: Set up the execution size before relying on it. | Eric Anholt | |
Fixes hangs with texturing in the non-GLSL path since f6d210c284751ac50a8d6358de7e75a1ff1e4ac7 | |||
2010-03-10 | i965: Add support for the CMP opcode in the GLSL path. | Eric Anholt | |
This would be triggered by use of sqrt() along with control flow. Fixes piglit-fs-sqrt-branch and a bug in Yo Frankie!. | |||
2010-03-10 | i965: Print the opcode name for unrecognized opcodes in the GLSL path. | Eric Anholt | |
2010-03-10 | i965: Fix the response len of masked sampler messages for 8-wide dispatch. | Eric Anholt | |
The bad response length would hang the GPU with a masked sample in a shader using control flow. For 8-wide, the response length is always 4, and masked slots are just not written to. brw_wm_glsl.c already allocates registers in the right locations. Fixes piglit glsl-fs-bug25902 (fd.o bug #25902). | |||
2010-03-10 | i965: Print the offset for IFF in disasm | Eric Anholt | |
2010-03-09 | i965: Fix ENDLOOP to only patch up this loop's BREAK and CONT. | Eric Anholt | |
Corresponds to d225a25e21a24508aea3b877c78beb35502e942d and fixes piglit glsl-fs-loop-nested. Bug #25173. | |||
2010-03-09 | i965: Unalias all GLSL source regs from the destination regs used. | Eric Anholt | |
We were doing it ad-hoc before, as instructions with potential aliasing problems were identified. But thanks to swizzling basically anything can have aliasing, so just do it generally at source reg setup time. This is somewhat inefficient, because sometimes an operation doesn't need unaliasing protection if the swizzling is safe, but the unaliasing before didn't cover those cases either. Fixes piglit glsl-fs-loop. | |||
2010-03-09 | i965: Print the offsets for WHILE and BREAK in disasm. | Eric Anholt | |
2010-03-09 | i965: Fix nested loops in the VS. | Eric Anholt | |
We were patching up all the break and continues between the start of our loop and the end of our loop, even if they were breaks/continues for an inner loop. Avoiding patching already patched breaks/continues fixes piglit glsl-vs-loop-nested. | |||
2010-03-09 | i965: Fix up VP constbuf leak on program delete. | Eric Anholt | |
2010-03-08 | i965: Fix up the handling of point sprite coordinate replacement. | Eric Anholt | |
The code was walking over the regs of pairs of attributes and checking whether the attribute with a given reg index had point sprite enabled. So the point sprite setup code was rarely even getting executed. Instead, we need to determine which channels of a reg need point sprite coordinate replacement. In addition, it was multiplying the attribute by 1/w, when it's supposed to cover (0, 1) in each direction regardless of w, and it wasn't filling in the Z and W components of the texcoord as specified. Fixes piglit point-sprite and the spriteblast demo. Bug #24431, #22245. | |||
2010-03-06 | dri: drop MINIGLX_SOURCES (2) | George Sapountzis | |
2010-03-06 | dri: drop MINIGLX_SOURCES | George Sapountzis | |
2010-03-05 | i965: Only use the effective subset of the WM sampler key. | Eric Anholt | |
The whole structure is 836 bytes, but if only the first one or two samplers are used (as is common), the part that matters is only 56 or 108 bytes. By using just that subset as the key (since the key size is also part of the key), we improve firefox-talos-gfx performance by 1%. | |||
2010-03-05 | intel: Remove support for the DRI1 TFP extension. | Eric Anholt | |
2010-03-05 | i965: Remove the paths for making a const surface object for a NULL BO. | Eric Anholt | |
2010-03-05 | i965: Remove the unused SDC BO pointer from the sampler state key. | Eric Anholt | |
Since it's a BO pointer, it already lives outside the key in brw->wm.sdc_bo[] which is used for sampler state lookup and setup. | |||
2010-03-05 | i965: Rename SNB brw_*_key structs to gen6_*_key structs. | Eric Anholt | |
2010-03-05 | i965: Pack gen6 blend_state_key structure. | Eric Anholt | |
2010-03-05 | i965: Try to assign SNB SF inputs to outputs. | Eric Anholt | |
2010-03-05 | i965: Fix the SNB SF input size. | Eric Anholt | |
2010-03-04 | intel: Remove non-kernel-exec-fencing support. | Eric Anholt | |
Shaves 60k off the driver from removing the broken spans code. This means we now require 2.6.29, which seems fair given that it's a year old and we've removed support for non-KMS already in the last release of 2D. | |||
2010-03-03 | i965: Fix up Sandybridge VS sizing. | Eric Anholt | |
2010-03-02 | i965: include macros.h to get CLAMP macro | Brian Paul | |
2010-02-25 | i965: Remove unnecessary headers. | Vinson Lee | |
2010-02-25 | i965: Try to hook up the Sandybridge URB_WRITE SEND message. | Eric Anholt | |
My units still hang when doing this if the VS is enabled. | |||
2010-02-25 | i965: Fix up the VUE handling for SNB, and hopefully clarify comments. | Eric Anholt | |
2010-02-25 | i965: Don't set a nonexistent enable bit in several SNB state pointers. | Eric Anholt | |
The modify bit is now usually in the instruction header. The exception is CC state pointers. | |||
2010-02-25 | i965: Lump SNB in with Ironlake for bigger VUEs. | Eric Anholt | |
This gets the VS to the point of accepting vertices. \o/ | |||
2010-02-25 | i965: Fix the SNB VE valid bit. | Eric Anholt | |
So, when the docs say that 0 means enabled now? That's a lie. | |||
2010-02-25 | i965: Don't include SNB in has_negative_rhw_bug. | Eric Anholt | |
2010-02-25 | i965: Fix the SNB clip near VP API bit. | Eric Anholt | |
2010-02-25 | i965: Fix the SNB URB entry count setup. | Eric Anholt | |
2010-02-25 | i965: Add SNB math opcode support. | Eric Anholt | |
This is untested at this point. | |||
2010-02-25 | i965: Emit SNB FF unit state after the unit's push constants. | Eric Anholt | |
There's a BUN for the WM unit that says WM_STATE must immediately follow PS_CONSTANTS, which this addresses. Presumably other units are roughly the same, too. | |||
2010-02-25 | i965: Set up the SNB sampler state pointers. | Eric Anholt | |
2010-02-25 | i965: Set GS rendering enabled even when the GS stage is disabled. | Eric Anholt | |
This is copying the behavior of other drivers. | |||
2010-02-25 | i965: Add a couple SNB state packets I saw in other batchbuffer dumps. | Eric Anholt | |
2010-02-25 | i965: Re-disable the VS. | Eric Anholt | |
There's stuff that needs to happen in the ISA before we can play with actually executing anything in the VS. | |||
2010-02-25 | i965: Fix up some Sandybridge define checks for the structure rebase. | Eric Anholt | |
2010-02-25 | i965: Move PIPELINE_SELECT to the top of gen6 3d pipeline setup. | Eric Anholt | |
2010-02-25 | i965: Untested Sandybridge WM packets. | Eric Anholt | |
2010-02-25 | i965: Hook up remaining Sandybridge state packets besides WM. | Eric Anholt | |
2010-02-25 | i965: Untested Sandybridge SF setup. | Eric Anholt | |
2010-02-25 | i965: Fixup Sandybridge GS packet from doc updates. | Eric Anholt | |
2010-02-25 | i965: Fix up Sandybridge GS reg definitions | Eric Anholt | |
2010-02-25 | i965: fix typo in SNB VS defines comment | Eric Anholt | |
2010-02-25 | i965: fix typo in SNB GS register defines | Eric Anholt | |
2010-02-25 | i965: Enable clip stats. | Eric Anholt | |