Samsung To Keep Using AMD’s RDNA GPUs For Exynos SoCs
Although Samsung’s Xclipse 920 integrated graphics processing unit based on AMD’s RDNA 2 architecture has not lived up to expectations, the consumer electronics giant will continue to use AMD’s RDNA architectures for its future built-in GPUs, the company disclosed on Thursday (opens in new tab).
“We plan to continue to implement other features in the RDNA series by working closely with AMD going forward,” said (opens in new tab) Sungboem Park, a vice president of Samsung who oversees GPU development. “In general, mobile tends to lag around five years or so behind consoles when it comes to graphics technology, however, we were able to incorporate the latest console technologies in the Exynos 2200 mobile processor quickly through our collaboration with AMD.
AMD’s Radeon RX 6000 family of GPUs based on the RDNA 2 architecture is without any doubts the company’s most competitive GPU lineup in many years, even though ray tracing is not its strongest side.
But the Xclipse 920 graphics processor based on the same architecture did not really shine in Samsung’s Exynos 2200 system-on-chip for smartphones either in compute or graphics workloads. Which is why Samsung inked a deal with Qualcomm to use its Snapdragon SoCs with Adreno graphics for its upcoming Galaxy S-series handsets globally, as the head of Qualcomm recently revealed (ComputerBase first noticed this). Ironically, Qualcomm’s Adreno (which is an ambigram of Radeon) development has been led by Eric Demers, who previously worked as GPU architect at AMD, ATI, and ArtX.
“We are very pleased to report that Qualcomm and Samsung have entered a new multiyear agreement starting in 2023, expanding the use of Snapdragon platforms for future premiums Samsung Galaxy products globally,” said Cristiano Amon, chief executive of Qualcomm during the company’s Q3 earnings call.
At present, Samsung uses Qualcomm’s premium Snapdragon SoCs for its Galaxy S smartphones sold in Asia and the U.S., its own Exynos SoCs are used in models sold Europe. The new deal allows Samsung to use Exynos for European Galaxy S smartphones, but it does not necessarily oblige the company to do so. Therefore, if Samsung has an Exynos SoC with a competitive CPU and GPU implementation, it might use it instead of Exynos.
But Samsung is certainly playing it safe with its choice of SoCs and GPUs as it also intends to use Snapdragons for other mobile products as well, according to Qualcomm.
“In addition to Galaxy smartphones, the agreement includes PCs, tablets, extended reality and more,” said Amon.
While AMD’s RDNA architectures are feature rich and scalable in terms of performance, power, and die size, actual implementation matters a lot. A GPU realization depends on multiple factors, including experience of its engineering team in general and with a particular GPU architecture in particular, design decisions, cost, and process technology. Therefore, Samsung might build a competitive RDNA-based integrated GPU sometimes in the future, but its engineers need to gain general GPU development experience first, and the only way to get it is to keep designing graphics processors.
Although Samsung’s Xclipse 920 integrated graphics processing unit based on AMD’s RDNA 2 architecture has not lived up to expectations, the consumer electronics giant will continue to use AMD’s RDNA architectures for its future built-in GPUs, the company disclosed on Thursday (opens in new tab).
“We plan to continue to implement other features in the RDNA series by working closely with AMD going forward,” said (opens in new tab) Sungboem Park, a vice president of Samsung who oversees GPU development. “In general, mobile tends to lag around five years or so behind consoles when it comes to graphics technology, however, we were able to incorporate the latest console technologies in the Exynos 2200 mobile processor quickly through our collaboration with AMD.
AMD’s Radeon RX 6000 family of GPUs based on the RDNA 2 architecture is without any doubts the company’s most competitive GPU lineup in many years, even though ray tracing is not its strongest side.
But the Xclipse 920 graphics processor based on the same architecture did not really shine in Samsung’s Exynos 2200 system-on-chip for smartphones either in compute or graphics workloads. Which is why Samsung inked a deal with Qualcomm to use its Snapdragon SoCs with Adreno graphics for its upcoming Galaxy S-series handsets globally, as the head of Qualcomm recently revealed (ComputerBase first noticed this). Ironically, Qualcomm’s Adreno (which is an ambigram of Radeon) development has been led by Eric Demers, who previously worked as GPU architect at AMD, ATI, and ArtX.
“We are very pleased to report that Qualcomm and Samsung have entered a new multiyear agreement starting in 2023, expanding the use of Snapdragon platforms for future premiums Samsung Galaxy products globally,” said Cristiano Amon, chief executive of Qualcomm during the company’s Q3 earnings call.
At present, Samsung uses Qualcomm’s premium Snapdragon SoCs for its Galaxy S smartphones sold in Asia and the U.S., its own Exynos SoCs are used in models sold Europe. The new deal allows Samsung to use Exynos for European Galaxy S smartphones, but it does not necessarily oblige the company to do so. Therefore, if Samsung has an Exynos SoC with a competitive CPU and GPU implementation, it might use it instead of Exynos.
But Samsung is certainly playing it safe with its choice of SoCs and GPUs as it also intends to use Snapdragons for other mobile products as well, according to Qualcomm.
“In addition to Galaxy smartphones, the agreement includes PCs, tablets, extended reality and more,” said Amon.
While AMD’s RDNA architectures are feature rich and scalable in terms of performance, power, and die size, actual implementation matters a lot. A GPU realization depends on multiple factors, including experience of its engineering team in general and with a particular GPU architecture in particular, design decisions, cost, and process technology. Therefore, Samsung might build a competitive RDNA-based integrated GPU sometimes in the future, but its engineers need to gain general GPU development experience first, and the only way to get it is to keep designing graphics processors.
Denial of responsibility! Techno Blender is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – [email protected]. The content will be deleted within 24 hours.