[PATCH 1/2] Misc. typos

From 68d431b4c14ad60a778ee93c1f59ecc4b931950e Mon Sep 17 00:00:00 2001
Found via `codespell -q 3 -I ../eigen-word-whitelist.txt` where the whitelists consists of:
```
als
ans
cas
dum
lastr
lowd
nd
overfl
pres
preverse
substraction
te
uint
whch
```
---
 CMakeLists.txt                                | 26 +++++++++----------
 Eigen/src/Core/GenericPacketMath.h            |  2 +-
 Eigen/src/SparseLU/SparseLU.h                 |  2 +-
 bench/bench_norm.cpp                          |  2 +-
 doc/HiPerformance.dox                         |  2 +-
 doc/QuickStartGuide.dox                       |  2 +-
 .../Eigen/CXX11/src/Tensor/TensorChipping.h   |  6 ++---
 .../Eigen/CXX11/src/Tensor/TensorDeviceGpu.h  |  2 +-
 .../src/Tensor/TensorForwardDeclarations.h    |  4 +--
 .../src/Tensor/TensorGpuHipCudaDefines.h      |  2 +-
 .../Eigen/CXX11/src/Tensor/TensorReduction.h  |  2 +-
 .../CXX11/src/Tensor/TensorReductionGpu.h     |  2 +-
 .../test/cxx11_tensor_concatenation.cpp       |  2 +-
 unsupported/test/cxx11_tensor_executor.cpp    |  2 +-
 14 files changed, 29 insertions(+), 29 deletions(-)

unsupported/Eigen/CXX11/src/Tensor/TensorChipping.h

@@ -244,7 +244,7 @@ struct TensorEvaluator<const TensorChippingOp<DimId, ArgType>, Device>
       return rslt;
     } else if ((static_cast<int>(Layout) == static_cast<int>(ColMajor) && m_dim.actualDim() == NumInputDims - 1) ||
          (static_cast<int>(Layout) == static_cast<int>(RowMajor) && m_dim.actualDim() == 0)) {
-      // m_stride is aways greater than index, so let's avoid the integer division.
+      // m_stride is always greater than index, so let's avoid the integer division.
       eigen_assert(m_stride > index);
       return m_impl.template packet<LoadMode>(index + m_inputOffset);
     } else {
@@ -377,7 +377,7 @@ struct TensorEvaluator<const TensorChippingOp<DimId, ArgType>, Device>
       inputIndex = index * m_inputStride + m_inputOffset;
     } else if ((static_cast<int>(Layout) == static_cast<int>(ColMajor) && m_dim.actualDim() == NumInputDims - 1) ||
                (static_cast<int>(Layout) == static_cast<int>(RowMajor) && m_dim.actualDim() == 0)) {
-      // m_stride is aways greater than index, so let's avoid the integer
+      // m_stride is always greater than index, so let's avoid the integer
       // division.
       eigen_assert(m_stride > index);
       inputIndex = index + m_inputOffset;
@@ -462,7 +462,7 @@ struct TensorEvaluator<TensorChippingOp<DimId, ArgType>, Device>
       }
     } else if ((static_cast<int>(this->Layout) == static_cast<int>(ColMajor) && this->m_dim.actualDim() == NumInputDims-1) ||
          (static_cast<int>(this->Layout) == static_cast<int>(RowMajor) && this->m_dim.actualDim() == 0)) {
-      // m_stride is aways greater than index, so let's avoid the integer division.
+      // m_stride is always greater than index, so let's avoid the integer division.
       eigen_assert(this->m_stride > index);
       this->m_impl.template writePacket<StoreMode>(index + this->m_inputOffset, x);
     } else {

unsupported/Eigen/CXX11/src/Tensor/TensorDeviceGpu.h

@@ -12,7 +12,7 @@
 
 // This header file container defines fo gpu* macros which will resolve to
 // their equivalent hip* or cuda* versions depending on the compiler in use
-// A separte header (included at the end of this file) will undefine all 
+// A separate header (included at the end of this file) will undefine all 
 #include "TensorGpuHipCudaDefines.h"
 
 namespace Eigen {

unsupported/Eigen/CXX11/src/Tensor/TensorForwardDeclarations.h

@@ -25,9 +25,9 @@ template<typename T> struct MakePointer {
 };
 
 // The PointerType class is a container of the device specefic pointer
-// used for refering to a Pointer on TensorEvaluator class. While the TensorExpression
+// used for referring to a Pointer on TensorEvaluator class. While the TensorExpression
 // is a device-agnostic type and need MakePointer class for type conversion,
-// the TensorEvaluator calss can be specialized for a device, hence it is possible
+// the TensorEvaluator calls can be specialized for a device, hence it is possible
 // to construct different types of temproray storage memory in TensorEvaluator
 // for different devices by specializing the following PointerType class.
 template<typename T, typename Device> struct PointerType : MakePointer<T>{};

unsupported/Eigen/CXX11/src/Tensor/TensorGpuHipCudaDefines.h

@@ -16,7 +16,7 @@
 // for some reason gets sent to the gcc/host compiler instead of the gpu/nvcc/hipcc compiler
 // When compiling such files, gcc will end up trying to pick up the CUDA headers by 
 // default (see the code within "unsupported/Eigen/CXX11/Tensor" that is guarded by EIGEN_USE_GPU)
-// This will obsviously not work when trying to compile tensorflow on a sytem with no CUDA
+// This will obsviously not work when trying to compile tensorflow on a system with no CUDA
 // To work around this issue for HIP systems (and leave the default behaviour intact), the
 // HIP tensorflow build defines EIGEN_USE_HIP when compiling all source files, and 
 // "unsupported/Eigen/CXX11/Tensor" has been updated to use HIP header when EIGEN_USE_HIP is

unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h

@@ -965,7 +965,7 @@ struct TensorEvaluator<const TensorReductionOp<Op, Dims, ArgType, MakePointer_>,
           }
         }
 
-        // Intialize output coefficient reducers.
+        // Initialize output coefficient reducers.
         for (int i = 0; i < num_reducers; ++i) {
           new (&reducers[i]) BlockReducer(m_reducer);
         }

unsupported/Eigen/CXX11/src/Tensor/TensorReductionGpu.h

@@ -771,7 +771,7 @@ struct OuterReducer<Self, Op, GpuDevice> {
     // terminate called after throwing an instance of 'std::runtime_error'
     //   what():  No device code available for function: _ZN5Eigen8internal20OuterReductionKernelIL...
     //
-    // dont know why this happens (and why is it a runtime error instead of a compile time errror)
+    // don't know why this happens (and why is it a runtime error instead of a compile time error)
     //
     // this will be fixed by HIP PR#457
     EIGEN_DEVICE_FUNC