summaryrefslogtreecommitdiff
path: root/src/gallium/auxiliary
AgeCommit message (Collapse)Author
2010-05-14tgsi: add a dummy function to silence warningBrian Paul
2010-05-14util: fix copy_rect stride in default transfer_inline_writeKeith Whitwell
2010-05-13rtasm: fix void * / func * casting warningsBrian Paul
2010-05-13draw: silence casting warningsBrian Paul
2010-05-13gallivm: silence uninitialized var warningBrian Paul
2010-05-13gallivm: silence casting warningBrian Paul
2010-05-13gallivm: silence uninitialized var warningBrian Paul
2010-05-13llvmpipe: silence uninitialized var warningsBrian Paul
2010-05-13gallivm: added lp_dump_llvmtype() debug helperBrian Paul
2010-05-13llvmpipe: additional commentsBrian Paul
2010-05-13gallivm: rename a varBrian Paul
2010-05-13util: Fix ptr -> int conversion.José Fonseca
2010-05-13Conditionally revert "gallivm: Use a more compact approach for ↵José Fonseca
lp_build_broadcast_scalar()." This reverts commit a09e46c72461183c879d8472b44fe740ecc79b9f.
2010-05-13gallium: Add tokens for Cygwin.Vinson Lee
2010-05-12rbug: Update and add READMEsJakob Bornecrantz
2010-05-12gallivm: Ensure PIPE_OS_xxx are defined.José Fonseca
2010-05-12gallivm: Use a more compact approach for lp_build_broadcast_scalar().José Fonseca
It produces exactly the same machine code, but it cuts 5% of the number of instructions generated for a typical shader. Also, preserve the scalar when length is 1.
2010-05-12util: Add function to dump PIPE_STENCIL_OP_xxxJosé Fonseca
2010-05-12rbug: Add to all targets that link against traceJakob Bornecrantz
Also added calls to the create function in target helpers and in tr_drm.c the latter being a hack and should be replaced with the wrap screen target helper. But at least this way we don't regress.
2010-05-12gallivm: additional commentsBrian Paul
2010-05-12gallivm: s/bool/booleanBrian Paul
2010-05-12gallivm: rename vars, update comments, etcBrian Paul
2010-05-12gallivm: comment out LLVMUnionTypeKind caseBrian Paul
2010-05-12gallivm: rename texel result paramBrian Paul
Be clear that this parameter returns four texel channel results.
2010-05-12gallivm: add a few commentsBrian Paul
2010-05-12gallivm/llvmpipe: add const qualifiersBrian Paul
2010-05-12gallivm: added lp_typekind_name() util functionBrian Paul
2010-05-12tgsi: also count instructions in tgsi_scan_shader()Brian Paul
2010-05-12softpipe: Adverstise (tgsi_exec's) shader limits.José Fonseca
2010-05-11mesa/st+tgsi: Provide a free callback to match with ureg_get_tokens().José Fonseca
This fixes crashes with the memory debugging routines on Windows. NOTE: This is a candidate for the 7.8 stable branch
2010-05-10gallivm/llvmpipe: move an old comment to a better locationBrian Paul
2010-05-10gallivm: Silent warning.José Fonseca
2010-05-10gallivm: Add missing lvalue.José Fonseca
2010-05-10gallivm: Temporarily disable custom LLVMDumpValue on MSVC.José Fonseca
Seeing very weird crashes during std::cout initialization. The fault probably lies in the way I build LLVM on MSVC, but disable for now to allow more time to investigate.
2010-05-10gallivm: cosf/sinf are macros on MSVC.José Fonseca
So taking the function address does not work.
2010-05-08gallivm: Add an alternative to LLVMDumpValue that works with Windows GUI apps.José Fonseca
2010-05-08gallivm: Fix mipfiltering with negative lod bias.José Fonseca
In particular, don't use the clamped lod to compute level + 1, or lod in [-1, 0] range will actually interpolate with level 1. This makes Mipfilter DCT pass 100%.
2010-05-08gallivm: Actually do floor/ceil/trunc for scalars.José Fonseca
Also start axing the code duplication for scalar case. The olution is to treat the scalar case specially in a few innermost functions, and leave outer functions untouched.
2010-05-08gallivm: Import the code to compute the minimax polynomials.José Fonseca
It's quite a pain to remember the details after a while, and it is quite likely we'll want to use this again, either for different polynomial orders or different functions, so commit it here.
2010-05-08gallivm: Use a minimax polynomial for exp2 in range [0,1] instead [-0.5,5].José Fonseca
The advantage of range[-0.5, 0.5] is that it doesn't require floor (for which intrinsics are only available in SSE4.1). But the EXP opcode pretty much forces us to use floor, and there is a good floor approximation around truncation available anyway. This fixes EXP failures in VShader DCT.
2010-05-08gallivm: Don't hardcode number of args twice.José Fonseca
2010-05-08gallivm: The the JIT engine to use our sinf()/cosf() on Windows.José Fonseca
A quick hack to get the right results, as there are many DCT tests which use these opcodes to generate data to test other opcodes.
2010-05-08gallivm: Fix BREAK/CONT translation.José Fonseca
The cont_mask must be restored and exec mask recomputed in order to decide whether to repeat the loop or not. Unlike the continue mask, the break_mask must be preserved across loop iterations. Fixes several VShader DCT cases, and no regressions with glean.
2010-05-08gallivm: Fix segfaul when inserting allocas in an empty function.José Fonseca
2010-05-08gallivm: Centralize SoA swizzling into a single place.José Fonseca
2010-05-08gallivm: Support predicates.José Fonseca
2010-05-07gallium/draw: additional comments in the clipping codeBrian Paul
2010-05-07tgis: fix SOA aliasing for MUL instruction in SSE codegenBrian Paul
Part of a fix for piglit trinity-fp1 test failure.
2010-05-06gallivm: Require SSE2 for draw_llvm/llvmpipe due to LLVM PR6960.Török Edwin
Note that this also requires X86 for llvm, if llvmpipe/draw_llvm works on PPC then the condition should be extended to include && x86. Signed-off-by: Török Edwin <edwintorok@gmail.com> Signed-off-by: José Fonseca <jfonseca@vmware.com>
2010-05-06tgsi: make SSE ADD instruction SOA-safeBrian Paul
To properly execute an instruction such as "ADD tmp, tmp.wzyx, foo;" with SOA we (sometimes) need to put the results into temporaries before writing the results to the destination register. This patch fixes the ADD instruction but this needs to be done for many more instructions. Helps to fix piglit fp-long-alu test (fd.o bug 27989).