File	Date	Author	Commit
core	2024-11-20	VectorChief	[48d553] add support for 128-bit ARM SVE (x1/x2)
data	2024-01-31	VectorChief	[25ae0b] update copyright to next year
dump	2013-07-21	VectorChief	[256333] memory heap and file logging
root	2024-04-24	VectorChief	[006388] bump default threads number from 120 to 480
test	2024-11-20	VectorChief	[48d553] add support for 128-bit ARM SVE (x1/x2)
COPYING	2024-01-31	VectorChief	[25ae0b] update copyright to next year
INSTALL	2023-05-03	VectorChief	[de25fe] add notes for QEMU 8.0.0 and MIPS cross-compiler
README	2021-12-23	VectorChief	[d807a6] update project description
ROADMAP	2023-04-12	VectorChief	[672d32] update roadmap for 0.7.x series
VERSION	2023-04-12	VectorChief	[9bd7a0] v0.7.1d "GIzmo+1d": macOS M1, VS2022, Ubuntu 22.04

Read Me

QuadRay engine is a realtime raytracing project aimed at full SIMD utilization
on ARM, MIPS, POWER and x86 architectures. The efficient use of SIMD is achieved
by processing four rays at a time to match SIMD register width (hence the name).
The rendering core of the engine is written in a unified SIMD assembler
allowing single assembler code to be compatible with different processor
architectures, thus reducing the need to maintain multiple parallel versions.

Initial documentation for the assembler is provided in core/config/rtdocs.h.

At present, Intel SSE/SSE2/SSE4 and AVX/AVX2/AVX-512 (32/64-bit x86 ISAs),
ARMv7 NEON/NEONv2, ARMv8 AArch32 and AArch64 NEON, SVE (32/64-bit ARM ISAs),
MIPS 32/64-bit r5/r6 MSA and POWER 32/64-bit VMX/VSX (little/big-endian ISAs)
are mostly implemented (w/ horizontal reductions and byte/half SIMD+BASE ops)
although scalar improvements, wider SIMD vectors with zeroing/merging predicates
in 3/4-operand instructions, cross-precision fp-converters on modern CPU targets
are planned as extensions to current 2/3-operand SPMD-driven vertical SIMD ISA.

The project has a test framework for Linux/GCC/Clang and Windows/VC++/TDM64-GCC.
Support for macOS is provided via Command Line Tools with GCC and Clang options.
Instructions for resolving dependencies and building the binaries
for supported platforms can be found in the accompanying INSTALL file.

RooT demo features:
 - Move/rotate camera with W,A,S,D + arrow keys
 - Print state (to dump) of all objects in the scene (on F1/'I')
 - Runtime toggling of antialiasing (on F2/'2')
 - Runtime cycling through cameras (on F3/'3')
 - Runtime saving (to dump) of BMP screenshots (on F4/'4')
 - Runtime toggling of FPS logging (on F5/'L')
 - Runtime switching of SIMD targets (F6/'6', F7/'7', F8/'8')
 - Runtime scene selection (F11/'1'), hide nums (F12/'5')
 - Multi-threading support with core count (df: 120 threads)
 - Multi-group affinity for Windows threading (> 64 threads)
 - Fullscreen support on Linux, macOS and Windows (-w 0)
 - Offscreen rendering support for benchmarking (-o or '0'/'O')
 - Pause mode (-p or 'P'), update/render stages (-u n or '9'/'U')
 - Quake mode (-q or 'Q'/'T'), frames in update (-m n or 'E'/'Y')
 - Refer to VERSION file (section 0.6.7) for cli options

QuadRay core features:
 - Full set of plane + quadric solvers
 - Custom clipping (with surface), boolean ops
 - Full geometry transform (hierarchical)
 - Basic RGB texturing for planes, no UV-mapping yet
 - Ambient + diffuse + specular + attenuation lights
 - All lights are colored points with infinite range
 - Hard shadows (opaque) from all light sources
 - Reflections/refractions + translucency, Fresnel (df: off)
 - Fullscreen 2x/4x antialiasing, Gamma correction (df: off)
 - Tiled scanline rendering, custom tree-like accelerators
 - Statically-linkable data format (C/C++ structs)
 - Programmable animators for all objects (below root)
 - 8 registers deep SIMD rendering pipeline (core/tracer)
 - Preliminary support for path-tracer with SIMD buffers
 - Written in UniSIMD assembler