当前位置: 首页>>代码示例>>Python>>正文


Python elementwise.get_binary_op_kernel函数代码示例

本文整理汇总了Python中pycuda.elementwise.get_binary_op_kernel函数的典型用法代码示例。如果您正苦于以下问题:Python get_binary_op_kernel函数的具体用法?Python get_binary_op_kernel怎么用?Python get_binary_op_kernel使用的例子?那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。


在下文中一共展示了get_binary_op_kernel函数的3个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: func

    def func(self, other):
        if not self.flags.forc:
            raise RuntimeError("only contiguous arrays may "
                    "be used as arguments to this operation")

        if isinstance(other, GPUArray):
            assert self.shape == other.shape

            if not other.flags.forc:
                raise RuntimeError("only contiguous arrays may "
                        "be used as arguments to this operation")

            result = self._new_like_me()
            func = elementwise.get_binary_op_kernel(
                    self.dtype, other.dtype, result.dtype,
                    operator)
            func.prepared_async_call(self._grid, self._block, None,
                    self.gpudata, other.gpudata, result.gpudata,
                    self.mem_size)

            return result
        else:  # scalar operator
            result = self._new_like_me()
            func = elementwise.get_scalar_op_kernel(
                    self.dtype, result.dtype, operator)
            func.prepared_async_call(self._grid, self._block, None,
                    self.gpudata, other, result.gpudata,
                    self.mem_size)
            return result
开发者ID:Benli11,项目名称:pycuda,代码行数:29,代码来源:gpuarray.py

示例2: _elwise_multiply

    def _elwise_multiply(self, other, out, stream=None):
        if not self.flags.forc:
            raise RuntimeError("only contiguous arrays may " "be used as arguments to this operation")

        func = elementwise.get_binary_op_kernel(self.dtype, other.dtype, out.dtype, "*")
        func.prepared_async_call(
            self._grid, self._block, stream, self.gpudata, other.gpudata, out.gpudata, self.mem_size
        )

        return out
开发者ID:abergeron,项目名称:pycuda,代码行数:10,代码来源:gpuarray.py

示例3: _div

    def _div(self, other, out, stream=None):
        """Divides an array by another array."""

        if not self.flags.forc or not other.flags.forc:
            raise RuntimeError("only contiguous arrays may " "be used as arguments to this operation")

        assert self.shape == other.shape

        func = elementwise.get_binary_op_kernel(self.dtype, other.dtype, out.dtype, "/")
        func.prepared_async_call(
            self._grid, self._block, stream, self.gpudata, other.gpudata, out.gpudata, self.mem_size
        )

        return out
开发者ID:abergeron,项目名称:pycuda,代码行数:14,代码来源:gpuarray.py


注:本文中的pycuda.elementwise.get_binary_op_kernel函数示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。