// ParallelDevice, and in turn runs one operation per component device with
  // its corresponding inputs from the input ParallelTensors. Wraps the
  // resulting per-device and per-output TFE_TensorHandles into one
  // ParallelTensor per output of the original operation.
  //
  // Attributes are forwarded to executed operations unmodified.
  //
  // The returned optional has a value if and only if `status` evaluates to

int TF_CheckpointReaderHasTensor(TF_CheckpointReader* reader,
                                 const char* name) {
  return reader->HasTensor(name);
}

const char* TF_CheckpointReaderGetVariable(TF_CheckpointReader* reader,
                                           int index) {
  return reader->variable_list[index].c_str();
}

int TF_CheckpointReaderSize(TF_CheckpointReader* reader) {

index fcf956a..e2c5d29 100644
--- a/sysdeps/ieee754/dbl-64/k_rem_pio2.c
+++ b/sysdeps/ieee754/dbl-64/k_rem_pio2.c
@@ -172,7 +172,8 @@ int __kernel_rem_pio2(double *x, double *y, int e0, int nx, int prec, const int3
 
     /* compute q[0],q[1],...q[jk] */
 	for (i=0;i<=jk;i++) {
-	    for(j=0,fw=0.0;j<=jx;j++) fw += x[j]*f[jx+i-j]; q[i] = fw;
+	    for(j=0,fw=0.0;j<=jx;j++) fw += x[j]*f[jx+i-j];

// Macro to verify that the field `struct_size` of STRUCT_OBJ is initialized.
// `struct_size` is used for struct member compatibility check between core TF
// and plug-ins with the same C API minor version. More info here:
// https://github.com/tensorflow/community/blob/master/rfcs/20200612-stream-executor-c-api/C_API_versioning_strategy.md
#define TF_VALIDATE_STRUCT_SIZE(STRUCT_NAME, STRUCT_OBJ, SIZE_VALUE_NAME) \

                                                 const TF_DataType* values,
                                                 int num_values);
TF_CAPI_EXPORT extern void TFE_OpSetAttrShapeList(
    TFE_Op* op, const char* attr_name, const int64_t** dims,
    const int* num_dims, int num_values, TF_Status* out_status);
TF_CAPI_EXPORT extern void TFE_OpSetAttrFunctionList(TFE_Op* op,

tensorflow::ServerDef GetServerDef(const std::string& job_name, int num_tasks) {
  tensorflow::ServerDef server_def;
  server_def.set_protocol("grpc");
  server_def.set_job_name(job_name);
  server_def.set_task_index(0);
  tensorflow::ClusterDef* cluster_def = server_def.mutable_cluster();
  tensorflow::JobDef* job_def = cluster_def->add_job();
  job_def->set_name(job_name);
  for (int i = 0; i < num_tasks; i++) {
    int port = tensorflow::testing::PickUnusedPortOrDie();

namespace tensorflow {

// Register the POSIX filesystems statically.
// Return value will be unused
bool StaticallyRegisterLocalFilesystems() {
  TF_FilesystemPluginInfo info;
  TF_InitPlugin(&info);
  Status status = filesystem_registration::RegisterFilesystemPluginImpl(&info);
  if (!status.ok()) {
    VLOG(0) << "Static POSIX filesystem could not be registered: " << status;
    return false;
  }
  return true;
}

**Standalone code to reproduce the issue**
Provide a reproducible test case that is the bare minimum necessary to generate
the problem. If possible, please share a link to or attach code demonstrating
the problem.

**Any other info / logs**
Include any logs or source code that would be helpful to diagnose the problem.
If including tracebacks, please include the full traceback. Large logs and files

- Model produces correct results, but it is slower than expected.

### 4. (optional) RNN conversion support
If converting TF RNN to TFLite fused RNN ops, please prefix [RNN] in the title.

### 5. (optional) Any other info / logs

// data.
bool IsValidStrideCompactRowMajorData(int64_t* shape_arr, int64_t* stride_arr,
                                      int ndim) {
  bool valid = true;
  int64_t expected_stride = 1;
  for (int i = ndim - 1; i >= 0; --i) {
    // Empty tensors are always compact regardless of strides.
    if (shape_arr[i] == 0) return true;