计算Hirerachy最终骨骼矩阵时并行骨骼矩阵计算

是否有办法优化代码?有人试图把这个计算转移到GPU上吗?

void Mesh::ReadNodeHeirarchy(float AnimationTime, const aiNode* pNode, const Matrix4f& ParentTransform)
    { 
        string NodeName(pNode->mName.data);

        const aiAnimation* pAnimation = m_pScene->mAnimations[0];

        Matrix4f NodeTransformation(pNode->mTransformation);

        const aiNodeAnim* pNodeAnim = FindNodeAnim(pAnimation, NodeName);

        if (pNodeAnim) {
            // Interpolate scaling and generate scaling transformation matrix
            aiVector3D Scaling;
            CalcInterpolatedScaling(Scaling, AnimationTime, pNodeAnim);
            Matrix4f ScalingM;
            ScalingM.InitScaleTransform(Scaling.x, Scaling.y, Scaling.z);

            // Interpolate rotation and generate rotation transformation matrix
            aiQuaternion RotationQ;
            CalcInterpolatedRotation(RotationQ, AnimationTime, pNodeAnim); 
            Matrix4f RotationM = Matrix4f(RotationQ.GetMatrix());

            // Interpolate translation and generate translation transformation matrix
            aiVector3D Translation;
            CalcInterpolatedPosition(Translation, AnimationTime, pNodeAnim);
            Matrix4f TranslationM;
            TranslationM.InitTranslationTransform(Translation.x, Translation.y, Translation.z);

            // Combine the above transformations
            NodeTransformation = TranslationM * RotationM * ScalingM;
        }

        Matrix4f GlobalTransformation = ParentTransform * NodeTransformation;

        if (m_BoneMapping.find(NodeName) != m_BoneMapping.end()) {
            uint BoneIndex = m_BoneMapping[NodeName];
            m_BoneInfo[BoneIndex].FinalTransformation = m_GlobalInverseTransform * GlobalTransformation * 
                                                        m_BoneInfo[BoneIndex].BoneOffset;
        }

        for (uint i = 0 ; i < pNode->mNumChildren ; i++) {
            ReadNodeHeirarchy(AnimationTime, pNode->mChildren[i], GlobalTransformation);
        }
    }