New Features:

Implement FMA

SIMD operations are optimized with FMA instructions to reduce operations and increasee accuracy. The gennerated CPU instructions are reduced. All matrix and related-vector operations are optimized.

FMA must be enable for these optimizations (with -mfma flag on GCC and Clang, /arch:AVX2 /O1-2 on MSVC)

• optimize mat4 SSE operations with FMA
• optimize mat3 SSE operations with FMA
• optimize mat2 SSE operations with FMA
• optimize affine mat SSE operations with FMA
• optimize vec4 muladd and muladds operations with FMA

New glmm functions (SSE + NEON):

• glmm_vhadd() - broadcast-ed hadd
• glmm_fmadd(a, b, c) - fused multiply add
• glmm_fnmadd(a, b, c) - fused negative multiply add
• glmm_fmsub(a, b, c) - fused multiply sub
• glmm_fnmsub(a, b, c) - fused negative multiply sub

New glmm functions (AVX):

• glmm256_fmadd(a, b, c) - fused multiply add AVX
• glmm256_fnmadd(a, b, c) - fused negative multiply add AVX
• glmm256_fmsub(a, b, c) - fused multiply sub AVX
• glmm256_fnmsub(a, b, c) - fused negative multiply sub AVX
• glm_mat4_scale_avx(mat4 m, float s) - scale matrix with scalar (if AVX enabled)

CMake

• #183: add CMake interface library target ( thanks to @legends2k )

Use as header-only library with your CMake project

This requires no building or installation of cglm.

• Example:

cmake_minimum_required(VERSION 3.8.2)

project(<Your Project Name>)

add_executable(${PROJECT_NAME} src/main.c)
target_link_libraries(${LIBRARY_NAME} PRIVATE
  cglm_headers)

add_subdirectory(external/cglm/ EXCLUDE_FROM_ALL)