3.0.10

From Msim

(Difference between revisions)
Jump to: navigation, search
(New page: This page refers to the changes made in the 3.0.10 release of M-sim.<br> <br> Release Date:<br> <br> == Syscalls == == EIO Handler == == Floating Point ==)
(Floating Point)
Line 9: Line 9:
== Floating Point ==
== Floating Point ==
 +
The floating point fixes made in this version result in the following:
 +
*Eon's output is different but still within acceptable parameters (all the outputs look like chairs of the appropriate brightness and detail)
 +
*Swim's output is still different but within much closer range than previous releases
 +
*Vpr not runs and generates acceptable output
 +
The following benchmarks still have issues running under M-sim
 +
*Sixtrack - this may not be significant but we have not done a full comparison of the output against the expected output
 +
*Facerec - the output is very different. It may be technically correct but we aren't sure at this point.
 +
 +
=== Fixes ===
 +
In machine.def, the following instructions were changed:
 +
ITOFS
 +
CVTQS
 +
CVTQT
 +
CVTQL
 +
 +
==== Precision Fixes ===
 +
In machine.def, the following instructions were changed to handle precision issues:
 +
SQRTS
 +
ADDS
 +
SUBS
 +
MULS
 +
DIVS
 +
CVTQS
 +
 +
 +
=== Missing ===
 +
CVTST is missing from machine.def. Is this a problem?
 +
 +
=== Excess Instructions ===
 +
The following instructions are not in the Version 4 Alpha Handbook but are in machine.def
 +
ADDLV, ADDLVI
 +
SUBLV, SUBLVI
 +
ADDQV, ADDQVI
 +
SUBQV, SUBQVI

Revision as of 17:01, 8 September 2009

This page refers to the changes made in the 3.0.10 release of M-sim.

Release Date:

Contents

Syscalls

EIO Handler

Floating Point

The floating point fixes made in this version result in the following:

  • Eon's output is different but still within acceptable parameters (all the outputs look like chairs of the appropriate brightness and detail)
  • Swim's output is still different but within much closer range than previous releases
  • Vpr not runs and generates acceptable output

The following benchmarks still have issues running under M-sim

  • Sixtrack - this may not be significant but we have not done a full comparison of the output against the expected output
  • Facerec - the output is very different. It may be technically correct but we aren't sure at this point.

Fixes

In machine.def, the following instructions were changed:

ITOFS
CVTQS
CVTQT
CVTQL

= Precision Fixes

In machine.def, the following instructions were changed to handle precision issues:

SQRTS
ADDS
SUBS
MULS
DIVS
CVTQS


Missing

CVTST is missing from machine.def. Is this a problem?

Excess Instructions

The following instructions are not in the Version 4 Alpha Handbook but are in machine.def

ADDLV, ADDLVI
SUBLV, SUBLVI
ADDQV, ADDQVI
SUBQV, SUBQVI
Personal tools