From 7ea6e417d430bc5ef5b9311bf414154a035a90ac Mon Sep 17 00:00:00 2001 From: Luke Kenneth Casson Leighton Date: Sat, 28 Sep 2019 05:56:07 +0100 Subject: [PATCH] draft update --- updates/020_2019aug28_intriguing_ideas.mdwn | 37 ++++++++++++--------- 1 file changed, 21 insertions(+), 16 deletions(-) diff --git a/updates/020_2019aug28_intriguing_ideas.mdwn b/updates/020_2019aug28_intriguing_ideas.mdwn index 589bf09..e975613 100644 --- a/updates/020_2019aug28_intriguing_ideas.mdwn +++ b/updates/020_2019aug28_intriguing_ideas.mdwn @@ -36,28 +36,33 @@ range of architectures and requirements: all the way from small embedded softcores, to embedded GPUs for use in mobile processors, to HPC servers to high end Machine Learning and Robotics applications. -One interesting thing that has to be made clear - the lesson from Nyuzi -and Larrabee - is that a good Vector Processor does **not** automatically -make a good 3D GPU. Jeff Bush designed Nyuzi very specifically to -replicate the Larrabee team's work. By deliberately not including custom -3D Hardware Accelerated Opcodes, Nyuzi has only 25% the performance of a modern -GPU consuming the same amount of power. Put another way: if you want to use -a pure Vector Engine to get the same performance as a commercially-competitive -GPU, you need *four times* the power consumption and four times the silicon -area. - -Thus we simply cannot use the upcoming RISC-V Vector Extension, or even -SimpleV, and expect to automatically have a commercially competitive -3D GPU. It takes texture opcodes, Z-Buffers, pixel conversion, Linear -Interpolation, Trascendentals (sin, cos, exp, log), and much more, all -of which has to be designed, thought through, implemented *and then used -behind a suitable API*. +One interesting thing that has to be made clear - the lesson from +Nyuzi and Larrabee - is that a good Vector Processor does **not** +automatically make a good 3D GPU. Jeff Bush designed Nyuzi very +specifically to replicate the Larrabee team's work: in particular, their +use of a recursive software-based tiling algorithm. By deliberately +not including custom 3D Hardware Accelerated Opcodes, Nyuzi has only +25% the performance of a modern GPU consuming the same amount of power. +Put another way: if you want to use a pure Vector Engine to get the same +performance as a commercially-competitive GPU, you need *four times* +the power consumption and four times the silicon area. + +Thus we simply cannot use an off-the-shelf Vector extension such as the +upcoming RISC-V Vector Extension, or even SimpleV, and expect to +automatically have a commercially competitive 3D GPU. It takes texture +opcodes, Z-Buffers, pixel conversion, Linear Interpolation, Trascendentals +(sin, cos, exp, log), and much more, all of which has to be designed, +thought through, implemented *and then used behind a suitable API*. In addition, given that the Alliance is to meet the needs of "unusual" markets, it is no good creating an ISA that has such a high barrier to entry and such a power-performance penalty that it inherently excludes the very implementors it is targetted at, particularly in Embedded markets. +These are the challenges to be discussed at the upcoming first +[meetup](https://www.meetup.com/Bay-Area-RISC-V-Meetup/events/264231095/) +at Western Digital's Milpitas HQ. + https://youtu.be/HeVz-z4D8os # Reconfigureable Pipelines -- 2.30.2