By: lurker (lurker9000.delete@this.realemail.mail), October 31, 2015 8:07 am
Room: Moderated Discussions
juanrga (nospam.delete@this.juanrga.com) on October 31, 2015 6:58 am wrote:
>
> I tried to explain that what matters is not the total number of memory units
> but the ratio between different execution units, the ISA, and the workloads.
>
> As explained before 2AGU+4ALU looks fine for ARM mobile SoC. 2AGU+4ALU looks unbalanced for x86 server SoC.
>
> Same stuff about HPC. A third AGU is not obligatory for HPC. Intel's Borkar just gave a recent
> talk about his vision for a future supercomputer much faster than actual. The HPC core that he
> proposes has only one AGU, and that is fine because his core has a 1:1 ratio for FP:mem.
>
> Fujitsu presented this year the new CPU that will replace the old CPU in the successful
> K-computer. This new CPU, the XIfx, is exclusively optimized for HPC and each
> core has 2 AGUs. Again fine because it has a 1:1 ratio for FP:mem...
>
> But this discussion about HPC is rather irrelevant, because we know
> that AMD will not use CPUs for HPC. AMD will propose HSA APUs.
>
> About markets Zen can win back easier. I know none. I am rather convinced that HPC Zen-based APUs
> will fail. Zen on AM4 APUs for desktop/mobile will be too late and competing against Kabylake/Cannonlake.
> Zen AM4 for CPUs will be competing with Skylake-E CPUs for a niche market: HEDT. And I guess Zen on
> servers will be crushed by both sides: ARM (Qualcomm, Broadcom, APM,...) and x86 (Intel).
I wouldn't be so negative before it's even released(or before we have some sort of performance indicators for it). There's a bunch of engineers with a lot of experience at AMD after all, I'm sure there's a reason why it's 2AGU+4ALU and not 3+3 or 2+3. What's the point of 4ALUs if one or two of them will remain idle? I'd imagine that extra ALUs, even when not fully utilized, would suck up a lot of power and generate more heat. Wouldn't getting rid of it, or at least disabling it, give better performance/watt?
>
> I tried to explain that what matters is not the total number of memory units
> but the ratio between different execution units, the ISA, and the workloads.
>
> As explained before 2AGU+4ALU looks fine for ARM mobile SoC. 2AGU+4ALU looks unbalanced for x86 server SoC.
>
> Same stuff about HPC. A third AGU is not obligatory for HPC. Intel's Borkar just gave a recent
> talk about his vision for a future supercomputer much faster than actual. The HPC core that he
> proposes has only one AGU, and that is fine because his core has a 1:1 ratio for FP:mem.
>
> Fujitsu presented this year the new CPU that will replace the old CPU in the successful
> K-computer. This new CPU, the XIfx, is exclusively optimized for HPC and each
> core has 2 AGUs. Again fine because it has a 1:1 ratio for FP:mem...
>
> But this discussion about HPC is rather irrelevant, because we know
> that AMD will not use CPUs for HPC. AMD will propose HSA APUs.
>
> About markets Zen can win back easier. I know none. I am rather convinced that HPC Zen-based APUs
> will fail. Zen on AM4 APUs for desktop/mobile will be too late and competing against Kabylake/Cannonlake.
> Zen AM4 for CPUs will be competing with Skylake-E CPUs for a niche market: HEDT. And I guess Zen on
> servers will be crushed by both sides: ARM (Qualcomm, Broadcom, APM,...) and x86 (Intel).
I wouldn't be so negative before it's even released(or before we have some sort of performance indicators for it). There's a bunch of engineers with a lot of experience at AMD after all, I'm sure there's a reason why it's 2AGU+4ALU and not 3+3 or 2+3. What's the point of 4ALUs if one or two of them will remain idle? I'd imagine that extra ALUs, even when not fully utilized, would suck up a lot of power and generate more heat. Wouldn't getting rid of it, or at least disabling it, give better performance/watt?