BLIS

BLIS is a portable software framework for instantiating high-performance BLAS-like dense linear algebra libraries. The framework was designed to isolate essential kernels of computation that, when optimized, enable optimized implementations of most of its commonly used and computationally intensive operations. Select kernels have been optimized for the AMD EPYCTM processor family. The optimizations are done for single and double precision routines.

Highlights of AMD BLIS 2.2

  • Improved performance for Level-1 BLAS routines for single and double precision.
  • Improved performance of SGEMV and DGEMV for large sizes.
  • Improved performance of Small/Skinny GEMM,TRSM kernels
  • GEMM Selective packing feature is now multithread enabled.
  • Logging/Tracing capabilities

The package containing BLIS Library binaries which includes optimizations for the AMD EPYCTM processor family, examples and documentation are available in the Downloads section below.

Source code is available on GitHub https://github.com/amd/blis.

libFLAME

libFLAME is a portable library for dense matrix computations, providing much of the functionality present in LAPACK. It includes a compatibility layer, FLAPACK, which includes complete LAPACK implementation. The library provides scientific and numerical computing communities with a modern, high-performance dense linear algebra library that is extensible, easy to use, and available under an open source license. libFLAME is a C-only implementation and does not depend on any external FORTRAN libraries including LAPACK. There is an optional backward compatibility layer, lapack2flame that maps LAPACK routine invocations to their corresponding native C implementations in libFLAME. This allows legacy applications to start taking advantage of libFLAME with virtually no changes to their source code.

In combination with AMD optimized BLIS library, libFLAME enables running high performing LAPACK functionalities on AMD platforms. The performance of libFLAME on AMD platforms can be improved by just linking with the AMD optimized BLIS.

Highlights of AMD libFLAME 2.2

  • Upgraded to LAPACK 3.9.0 specification

The package containing libFLAME binaries, examples and documentation are available in the Downloads section below

Source code is available on GitHub https://github.com/amd/libflame.

Download:

Refer here for older versions

File Name Version Size Launch Date OS Bitness Description
AOCC Compiled Binary Packages

File Name

Version

2.2

Size

5.89 MB

Launch Date

06/30/2020

OS

Ubuntu, SLES, CentOS, RHEL

Bitness

64-bit

Description

AOCC compiled BLIS Library binary package sha256 Checksum : 2def5e495bf48534361e67bfe26ee4143c51d87e633fe0127f1ead4b526437db

File Name

Version

2.2

Size

12MB

Launch Date

06/30/2020

OS

Ubuntu, SLES, CentOS, RHEL

Bitness

64-bit

Description

AOCC compiled libFLAME Library binary package sha256 Checksum: 3dda0e9592bcea4fde45742a70fc568737b431f1b2ff5c133a9944d7b9c03564

File Name

Version

2.2

Size

72KB

Launch Date

06/30/2020

OS

Ubuntu, SLES, CentOS, RHEL

Bitness

64-bit

Description

AOCC compiled HPL benchmark binary optimized for AMD EPYC processor that uses multi-threaded AMD BLIS library sha256 Checksum: d2d945e21a089575e6f5f8cf53671c83a45efd8f21ea7d092e72b2c3558fed97
GCC Compiled Binary Packages

File Name

Version

2.2

Size

6.98 MB

Launch Date

06/30/2020

OS

Ubuntu, SLES, CentOS, RHEL

Bitness

64-bit

Description

GCC compiled BLIS Library binary package sha256 Checksum : e9bd8bc808a3cb8b84ff46f1f3c12c214c2699c80b82d43e3bedf24b9bb79ac6

File Name

Version

2.2

Size

14.4MB

Launch Date

06/30/2020

OS

Ubuntu, SLES, CentOS, RHEL

Bitness

64-bit

Description

GCC compiled libFLAME Library binary package sha256 Checksum: 13e3eb9e174ff3c9f44f33e8c9b2bf9d7513ea5840109a4d37a2fa4f769f3451

File Name

Version

2.2

Size

112KB

Launch Date

06/30/2020

OS

Ubuntu, SLES, CentOS, RHEL

Bitness

64-bit

Description

GCC compiled HPL benchmark binary optimized for AMD EPYC processor that uses multi-threaded AMD BLIS library sha256 Checksum: 054e5db91fdc012608ae20ad6c3b84a9f693bc536c1c1689a70828c75fbe2a0d