1. 25 8月, 2021 1 次提交
  2. 21 6月, 2021 1 次提交
    • L
      Add AXPY oneDNN handler (#33632) · 773aabc7
      lidanqing 提交于
      * Add oneDNN AXPY handler.
      
      * Add fallback for small tensors.
      
      * Fix ifdefs
      
      * Remove unnecessary namespace prefixes and add missing headers.
      
      * Guard handler_axpy with proper ifdefs.
      
      * Compilation of this function is possible only when Paddle is not build
      with CUDA nor HIP.
      
      * Move AXPY handler code to separate files.
      
      * Use oneDNN AXPY handler in SGD op.
      
      * Use axpy handler only when Paddle is built with oneDNN.
      
      * Add test for SUM BF16 with big rows.
      
      * Fix SFINAE rules for elementwise_add_to.
      
      * Add test case for SGD with big rows.
      
      * update
      
      * update
      Co-authored-by: NAdam Osewski <adam.osewski@intel.com>
      773aabc7
  3. 06 5月, 2021 1 次提交
  4. 14 4月, 2021 1 次提交
    • A
      adds new CPU kernel for SGD op supporting BF16 data type (#32162) · 3ac6c189
      Adam Osewski 提交于
      * Initial draft for SGD BG16 kernel.
      
      * Unit tests for SGD with BF16 data type.
      
      * Add VLOG message to SGD BF16 op CPU kernel.
      
      * Enhance error messages and error types.
      
      * Refactor SGD op kernels to leverage some common code.
      
      * Make easier to add new kerne invoke code.
      
      * Fix SGD op kernel for sparse grad.
      
      * Unify quotes style.
      
      * Fix error for ROCM compilation.
      
      * Use specialized PADDLE_ENFORCE_xx functions.
      3ac6c189