/agenda
Using Linaro Forge to optimize performance when migrating workloads between hardware architectures
Moving workloads from x86_64 to the Arm architecture can be challenging. The main porting challenge is to make effective use of architectural features such as SVE2, Cache accesses and SIMD Vectorisation, which requires performance insights to determine how well these hardware features are being utilised. Compilers and libraries offer varying degrees of performance improvements by making effective use of the underlying hardware architecture, but they do not always get it right, which can cause performance degradation during the initial porting phase. Linaro Forge provides the performance insights to quickly identify performance hot spots that helps to determine if the code is utilising the hardware effectively. This in turn enables the user to tune their application for optimal performance on the hardware that their code is being migrated to.
Schedule
Using Linaro Forge to optimize performance when migrating workloads between hardware architectures
Moving workloads from x86_64 to the Arm architecture can be challenging. The main porting challenge is to make effective use of architectural features such as SVE2, Cache accesses and SIMD Vectorisation, which requires performance insights to determine how well these hardware features are being utilised. Compilers and libraries offer varying degrees of performance improvements by making effective use of the underlying hardware architecture, but they do not always get it right, which can cause performance degradation during the initial porting phase. Linaro Forge provides the performance insights to quickly identify performance hot spots that helps to determine if the code is utilising the hardware effectively. This in turn enables the user to tune their application for optimal performance on the hardware that their code is being migrated to.