1Michael Wong Distinguished Engineer ● Chair of SYCL Heterogeneous Programming Language ● ISO C++ Directions Group past Chair ● Past CEO OpenMP ● ISOCPP.org Director, VP http://isocpp.org/wiki/ leading team developing HIP & CUDA backends for DPC++ Background in C++ programming models for heterogeneous systems Worked on ComputeCpp (SYCL) since its inception Contributor to the Khronos SYCL standard AI/Tensor HW Other BackendsSYCL 2020 is here! Open Standard for Single Source C++ Parallel Heterogeneous Programming SYCL 2020 is released after 3 years of intense work Significant adoption in Embedded

FPGAs AMD GPUs Any CPU SYCL enables Khronos to influence ISO C++ to (eventually) support heterogeneous compute SYCL, OpenCL and SPIR-V, as open industry standards, enable flexible integration and more) Any CPU Experimental SYCL enables Khronos to influence ISO C++ to (eventually) support heterogeneous compute SYCL, OpenCL and SPIR-V, as open industry standards, enable flexible integration and MobileyeSYCL IR ON COMPILER EXPLORERhttps://godbolt.org/z/jdhKr7e5rExpressiveness and simplicity for heterogeneous programming in modern C++ New Features Unified Shared Memory | Parallel Reductions | Subgroup

Continuous Innovation to Address User Pain Points Multi-language runtime environment Heterogeneous communication in the service center Microservice authentication Distributed system configuration suche as Istio/Promethues/Skywalking/… - Compatible with heterogeneous infrastructure suche as K8S/BareMetal/docker/VM/… Mesher - Heterogeneous,multilingual,non-intrusive microservice framework [Website] [Website] http://servicecomb.apache.org [Github ] https://github.com/apache?q=servicecomb Syncer - Heterogeneous popular service center integration practice • Quick Start https://github.com/apache/service

numbers or text (strings), as well as homogeneous, fixed-size containers (called arrays in C), and heterogeneous fixed-size containers (called structs in C). A different approach is taken by languages like the code. This is particularly valuable when collaborating with others, as it ensures clear communication and consistency in coding style, fostering a more effective development environment.[30] We defines the HSlice object, called a heterogeneous slice, for which the lower and upper bound can have different data types: type HSlice*[T, U] = object ## "Heterogeneous" slice type. a*: T

numbers or text (strings), as well as homogeneous, fixed-size containers (called arrays in C), and heterogeneous fixed-size containers (called structs in C). A different approach is taken by languages like the code. This is particularly valuable when collaborating with others, as it ensures clear communication and consistency in coding style, fostering a more effective development environment.[30] We defines the HSlice object, called a heterogeneous slice, for which the lower and upper bound can have different data types: type HSlice*[T, U] = object ## "Heterogeneous" slice type. a*: T

numbers or text (strings), as well as homogeneous, fixed-size containers (called arrays in C), and heterogeneous fixed- size containers (called structs in C). A different approach is taken by languages like the code. This is particularly valuable when collaborating with others, as it ensures clear communication and consistency in coding style, fostering a more effective devel­ opment environment. [1] defines the HSlice object, called a heterogeneous slice, for which the lower and upper bound can have different data types: type HSlice*[T, U] = object ## "Heterogeneous" slice type. a*: T

numbers or text (strings), as well as homogeneous, fixed-size containers (called arrays in C), and heterogeneous fixed- size containers (called structs in C). A different approach is taken by languages like the code. This is particularly valuable when collaborating with others, as it ensures clear communication and consistency in coding style, fostering a more effective devel­ opment environment. [1] defines the HSlice object, called a heterogeneous slice, for which the lower and upper bound can have different data types: type HSlice*[T, U] = object ## "Heterogeneous" slice type. a*: T

numbers or text (strings), as well as homogeneous, fixed-size containers (called arrays in C), and heterogeneous fixed- size containers (called structs in C). A different approach is taken by languages like the code. This is particularly valuable when collaborating with others, as it ensures clear communication and consistency in coding style, fostering a more effective devel­ opment environment. [1] defines the HSlice object, called a heterogeneous slice, for which the lower and upper bound can have different data types: type HSlice*[T, U] = object ## "Heterogeneous" slice type. a*: T

numbers or text (strings), as well as homogeneous, fixed-size containers (called arrays in C), and heterogeneous fixed- size containers (called structs in C). A different approach is taken by languages like the code. This is particularly valuable when collaborating with others, as it ensures clear communication and consistency in coding style, fostering a more effective devel­ opment environment. [1] defines the HSlice object, called a heterogeneous slice, for which the lower and upper bound can have different data types: type HSlice*[T, U] = object ## "Heterogeneous" slice type. a*: T

numbers or text (strings), as well as homogeneous, fixed-size containers (called arrays in C), and heterogeneous fixed- size containers (called structs in C). A different approach is taken by languages like the code. This is particularly valuable when collaborating with others, as it ensures clear communication and consistency in coding style, fostering a more effective devel­ opment environment. [1] defines the HSlice object, called a heterogeneous slice, for which the lower and upper bound can have different data types: type HSlice*[T, U] = object ## "Heterogeneous" slice type. a*: T