stu mckenna b6010254ab - Write VectorVM code in LittleEndian as opposed to BigEndian, this avoids runtime byte swapping ...

- Read ByteCode directly if unalgned loads are supported to condense 3 opts into 1 when reading a uint16
- Pre-calculate instance loops for VECTOR_WIDTH_FLOATS to avoid each vector op having to round / divide instance counts
- Added runtime optimization of the VM script, this currently boils down to a function call per VM invoke + storing the data required
- Use vm.OptimizeVMByteCode to enable optimized code generation
- Use vm.UseOptimizedVMByteCode to enable running optimized code rather the traditional byte code

[FYI] simon.tovey,rob.krajcarski,shaun.kime
#rnx


#ROBOMERGE-SOURCE: CL 9962648 via CL 9964955
#ROBOMERGE-BOT: (v560-9963197)

[CL 9965540 by stu mckenna in Main branch]

2019-11-03 14:40:53 -05:00

..

Private

- Write VectorVM code in LittleEndian as opposed to BigEndian, this avoids runtime byte swapping

2019-11-03 14:40:53 -05:00

Public

- Storing compact form of databuffer layout in single array to reduce cache misses in register setup.

2019-09-19 12:36:11 -04:00

ShaderFormatVectorVM.Build.cs

Merging //UE4/Dev-Main@4662404 to Dev-Rendering (//UE4/Dev-Rendering)

2019-01-03 19:16:26 -05:00