| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
| |
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
| |
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
| |
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
| |
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
| |
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
| |
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
|
|
| |
Fix issue where temporary allocas were getting hoisted to function entry
unnecessarily. We now explicitly mark temporary allocas and skip hoisting
during the hoist pass. Shuold reduce stack usage.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
Enable generalized fetch jit with 8 or 16 wide SIMD target. Still some
work needed to remove some simd8 double pumping for 16-wide target.
Also removed unused non-gather load vertices path.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
|
| |
Small cleanup. Remove convenience types from JitManager and standardize
on the Builder's convenience types.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
| |
Move x86 intrinsic lowering to a separate pass. Builder now instantiates
generic intrinsics for features not supported by llvm. The separate x86
lowering pass is responsible for lowering to valid x86 for the target
SIMD architecture. Currently it's a port of existing code to get it
up and running quickly. Will eventually support optimized x86 for AVX,
AVX2 and AVX512.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
|
|
| |
Replace sqrt, maskload, fp min/max, cttz, ctlz with llvm equivalent.
Replace AVX maskedstore intrinsic with LLVM intrinsic. Add helper llvm
macros for stacksave, stackrestore, popcnt.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
| |
Provide access functions for mpPrivateContext in Builder.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
| |
Move mpPrivateContext to compensate
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
|
| |
Move them to their own file (builder_mem.{h|cpp}). Add builder_mem.cpp
to the build system.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
|
| |
Now also takes in an additional parameter (draw context) for future
expansion.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
| |
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
|
| |
Widen fetch shader to SIMD16, enable SIMD16 types in the jitter,
and provide utility EXTRACT/INSERT SIMD8 <-> SIMD16 utility functions.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
| |
Not used yet.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
| |
Don't create/use cpp files, header only now.
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
| |
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
|
|
| |
- Move most jitter functionality into SwrJit namespace
- Avoid global "using namespace llvm" in headers
Signed-off-by: Tim Rowley <[email protected]>
|
| |
|
|
| |
Reviewed-by: Bruce Cherniak <[email protected]>
|
| |
|
|
|
| |
Also, cached the simd width since we don't have to keep querying
the JitManager for it.
|
|
|
Acked-by: Roland Scheidegger <[email protected]>
Acked-by: Jose Fonseca <[email protected]>
|
