[caffe2][dnnlowp] Remove openmp usage in quantize dnnlowp op

Summary: It creates cpu overload issues when openmp gets enabled and OMP_NUM_THREADS=1 is not set.

Test Plan: buck test //caffe2/caffe2/quantization/server:quantize_dnnlowp_op_test

Reviewed By: jspark1105

Differential Revision: D24437305

fbshipit-source-id: 426209fc33ce0d4680c478f584716837ee62cb5e

caffe2/quantization/server/quantize_dnnlowp_op.cc

@@ -1,10 +1,6 @@
 #include "quantize_dnnlowp_op.h"
 #include "dnnlowp_op.h"
 
-#ifdef _OPENMP
-#include <omp.h>
-#endif
-
 #include "caffe2/core/tensor_int8.h"
 #include "caffe2/quantization/server/int8_gen_quant_params.h"
 #include "caffe2_dnnlowp_utils.h"
@@ -67,16 +63,7 @@ bool QuantizeDNNLowPOp<T>::RunOnDevice() {
   const float* in_data = Input(0).template data<float>();
   T* out_data = output->t.template mutable_data<T>();
 
-#ifdef _OPENMP
-#pragma omp parallel
-#endif
-  {
-    int i_begin, i_end;
-    tie(i_begin, i_end) = Get1DPartition(
-        Input(0).numel(), dnnlowp_get_num_threads(), dnnlowp_get_thread_num());
-    fbgemm::Quantize<T>(
-        in_data + i_begin, out_data + i_begin, i_end - i_begin, in_qparams);
-  }
+  fbgemm::Quantize<T>(in_data, out_data, Input(0).numel(), in_qparams);
 
   PropagateOutputTensorQuantizationParams(this, 0, in_qparams);