Transmeta Efficeon

The Efficeon processor is Transmeta's second-generation 256-bit VLIW design released in 2004 which employs a software engine (Code Morphing Software, aka CMS) to convert code written for x86 processors to the native instruction set of the chip. Like its predecessor, the Transmeta Crusoe (a 128-bit VLIW architecture), Efficeon stresses computational efficiency, low power consumption, and a low thermal footprint.

A Transmeta Efficieon processor

Efficeon most closely mirrors the feature set of Intel Pentium 4 processors, although, like AMD Opteron processors, it supports a fully integrated memory controller, a HyperTransport IO bus, and the NX bit, or no-execute x86 extension to PAE mode. NX bit support is available starting with CMS version 6.0.4.

Efficeon's computational performance relative to mobile CPUs like the Intel Pentium M is thought to be lower, although little appears to be published about the relative performance of these competing processors.

Efficeon came in two package types: a 783- and a 592-contact ball grid array. Its power consumption is moderate (with some consuming as little as 3 watts at 1 GHz and 7 watts at 1.5 GHz), so it can be passively cooled.

Two generations of this chip were produced. The first generation (TM8600) was manufactured using a TSMC 0.13 micrometre process and produced at speeds up to 1.2 GHz. The second generation (TM8800 and TM8820) was manufactured using a Fujitsu 90 nm process and produced at speeds ranging from 1 GHz to 1.7 GHz.

Internally, the Efficeon has two arithmetic logic units, two load/store/add units, two execute units, two floating-point/MMX/SSE/SSE2 units, one branch prediction unit, one alias unit, and one control unit. The VLIW core can execute a 256-bit VLIW instruction per cycle, which is called a molecule and has room to store eight 32-bit instructions (called atoms) per cycle.

The Efficeon has a 128 KB L1 instruction cache, a 64 KB L1 data cache and a 1 MB L2 cache. All caches are on die.

Additionally the Efficeon CMS (code morphing software) reserves a small portion of main memory (typically 32 MB) for its translation cache of dynamically translated x86 instructions.