skip to navigation
skip to content

PeachPy 0.0.1

Portable Efficient Assembly Codegen in Higher-level Python

PEACH-Py is a Python framework for writing high-performance assembly kernels. PEACH-Py is developed to simplify writing optimized assembly kernels while preserving all optimization opportunities of traditional assembly. Some PEACH-Py features:

  • Automatic register allocation
  • Stack frame management, including re-aligning of stack frame as needed
  • Generating versions of a function for different calling conventions from the same source (e.g. functions for Microsoft x64 ABI and System V x86-64 ABI can be generated from the same source)
  • Allows to define constants in the place where they are used (just like in high-level languages)
  • Tracking of instruction extensions used in the function.
  • Multiplexing of multiple instruction streams (helpful for software pipelining)


from peachpy.x64 import *

# Use 'x64-ms' for Microsoft x64 ABI
abi = peachpy.c.ABI('x64-sysv')
assembler = Assembler(abi)

# Implement function void add_1(const uint32_t *src, uint32_t *dst, size_t length)
src_argument = peachpy.c.Parameter("src", peachpy.c.Type("const uint32_t*"))
dst_argument = peachpy.c.Parameter("dst", peachpy.c.Type("uint32_t*"))
len_argument = peachpy.c.Parameter("length", peachpy.c.Type("size_t"))

# This optimized kernel will target Intel Nehalem processors. Any instructions which are not
# supported on Intel Nehalem (e.g. AVX instructions) will generate an error. If you don't have
# a particular target in mind, use "Unknown"
with Function(assembler, "add_1", (src_argument, dst_argument, len_argument), "Nehalem"):
    # Load arguments into registers
    srcPointer = GeneralPurposeRegister64()
    LOAD.PARAMETER( srcPointer, src_argument )

    dstPointer = GeneralPurposeRegister64()
    LOAD.PARAMETER( dstPointer, dst_argument )

    length = GeneralPurposeRegister64()
    LOAD.PARAMETER( length, len_argument )

    # Main processing loop. Length must be a multiple of 4.
    LABEL( 'loop' )

    x = SSERegister()
    MOVDQU( x, [srcPointer] )
    ADD( srcPointer, 16 )

    # Add 1 to x
    PADDD( x, Constant.uint32x4(1) )

    MOVDQU( [dstPointer], x )
    ADD( dstPointer, 16 )

    SUB( length, 4 )
    JNZ( 'loop' )


print assembler
File Type Py Version Uploaded on Size (md5) Source 2013-11-24 114KB