[PowerPC] Fixed build issue for vsx vec256 complexfloat and scaled_mm_out_cpu (#155255)

Pytorch build is failing on power system from this commit ec24f8f58a

***Build Failure Logs***

**Error related to mkldnn**
```
pytorch/aten/src/ATen/native/Blas.cpp:302:26: error: ‘cpuinfo_has_x86_amx_int8’ was not declared in this scope
  302 |     if ((!mixed_dtype && cpuinfo_has_x86_amx_int8()) ||
      |                          ^~~~~~~~~~~~~~~~~~~~~~~~
pytorch/aten/src/ATen/native/Blas.cpp:303:25: error: ‘cpuinfo_has_x86_amx_fp16’ was not declared in this scope
  303 |         (mixed_dtype && cpuinfo_has_x86_amx_fp16())) {
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~

```

**Error related to vec256 complex float redefinition**
```
aten/src/ATen/cpu/vec/vec256/vsx/vec256_complex_float_vsx.h:19:7: error: specialization of ‘at::vec::DEFAULT::Vectorized<c10::complex<float> >’ after instantiation
   19 | class Vectorized<ComplexFlt> {
      |       ^~~~~~~~~~~~~~~~~~~~~~
aten/src/ATen/cpu/vec/vec256/vsx/vec256_complex_float_vsx.h:19:7: error: redefinition of ‘class at::vec::DEFAULT::Vectorized<c10::complex<float> >’

aten/src/ATen/cpu/vec/vec256/vsx/vec256_complex_float_vsx.h:633:18: error: ‘const class at::vec::DEFAULT::Vectorized<c10::complex<float> >’ has no member named ‘abs_2_’
  633 |   auto abs_a = a.abs_2_();
      |                  ^~~~~~
aten/src/ATen/cpu/vec/vec256/vsx/vec256_complex_float_vsx.h:634:18: error: ‘const class at::vec::DEFAULT::Vectorized<c10::complex<float> >’ has no member named ‘abs_2_’
  634 |   auto abs_b = b.abs_2_();
      |                  ^~~~~~

/aten/src/ATen/cpu/vec/vec256/vsx/vec256_complex_float_vsx.h:666:17: error: ‘const class at::vec::DEFAULT::Vectorized<c10::complex<float> >’ has no member named ‘vec0’
  666 |       vec_add(a.vec0(), b.vec0()), vec_add(a.vec1(), b.vec1())};
aten/src/ATen/cpu/vec/vec256/vsx/vec256_complex_float_vsx.h:673:17: error: ‘const class at::vec::DEFAULT::Vectorized<c10::complex<float> >’ has no member named ‘vec0’
  673 |       vec_sub(a.vec0(), b.vec0()), vec_sub(a.vec1(), b.vec1())};
      |                 ^~~~
aten/src/ATen/cpu/vec/vec256/vsx/vec256_complex_float_vsx.h:680:27: error: ‘const class at::vec::DEFAULT::Vectorized<c10::complex<float> >’ has no member named ‘vec0’
  680 |       vec_and(a.vec0(), b.vec0()), vec_and(a.vec1(), b.vec1())};
```

***With  this changes build logs***
```
Building wheel torch-2.8.0a0+gita3098a7
-- Building version 2.8.0a0+gita3098a7
-- Checkout nccl release tag: v2.26.5-1
cmake -GNinja -DBLAS=OpenBLAS -DBUILD_PYTHON=True -DBUILD_TEST=True -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/home/avanish/OfficeWork2025/JuneWork/pytorch_5Jun/pack/torch_night_5Jun/pytorch/torch -DCMAKE_PREFIX_PATH=/home/avanish/OfficeWork2025/JuneWork/pyenv/pytorch_5Jun/lib/python3.12/site-packages -DPython_EXECUTABLE=/home/avanish/OfficeWork2025/JuneWork/pyenv/pytorch_5Jun/bin/python -DTORCH_BUILD_VERSION=2.8.0a0+gita3098a7 -DUSE_MKLDNN=ON -DUSE_MKLDNN_CBLAS=ON -DUSE_NUMPY=True -DUSE_OPENMP=ON /home/avanish/OfficeWork2025/JuneWork/pytorch_5Jun/pack/torch_night_5Jun/pytorch
cmake --build . --target install --config Release
running build_ext
-- Building with NumPy bindings
-- Not using cuDNN
-- Not using CUDA
-- Not using XPU
-- Using MKLDNN
-- Not using Compute Library for the Arm architecture with MKLDNN
-- Using CBLAS in MKLDNN
-- Not using NCCL
-- Building with distributed package:
  -- USE_TENSORPIPE=True
  -- USE_GLOO=True
  -- USE_MPI=False
-- Building Executorch
-- Not using ITT
Copying functorch._C from functorch/functorch.so to /home/avanish/OfficeWork2025/JuneWork/pytorch_5Jun/pack/torch_night_5Jun/pytorch/build/lib.linux-ppc64le-cpython-312/functorch/_C.cpython-312-powerpc64le-linux-gnu.so
copying functorch/functorch.so -> /home/avanish/OfficeWork2025/JuneWork/pytorch_5Jun/pack/torch_night_5Jun/pytorch/build/lib.linux-ppc64le-cpython-312/functorch/_C.cpython-312-powerpc64le-linux-gnu.so
building 'torch._C' extension
creating build/temp.linux-ppc64le-cpython-312/torch/csrc

```

This patch will fix the pytorch build issue on power, and i am able to build successfully.

Hi @malfet  @albanD

Please review this PR for pytorch build issue that we are observing on power.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/155255
Approved by: https://github.com/albanD, https://github.com/malfet

aten/src/ATen/cpu/vec/vec256/vsx/vec256_complex_double_vsx.h

@@ -478,7 +478,7 @@ class Vectorized<ComplexDbl> {
     this->store(tmp1);
     b.store(tmp2);
 
-    for (const auto i : c10::irange(Vectorized<c10::complex<float>>::size())) {
+    for (const auto i : c10::irange(Vectorized<c10::complex<double>>::size())) {
       out[i] = tmp1[i] / tmp2[i];
     }
     return loadu(out);

aten/src/ATen/native/Blas.cpp

@@ -296,7 +296,7 @@ _scaled_mm_out_cpu(const Tensor& mat1, const Tensor& mat2,
           std::optional<c10::ScalarType> out_dtype,
           bool use_fast_accum,
           Tensor& out) {
-#if AT_MKLDNN_ENABLED()
+#if AT_MKLDNN_ENABLED() && !defined(__powerpc__)
   if (at::globalContext().userEnabledMkldnn()) {
     bool mixed_dtype = mat1.scalar_type() != mat2.scalar_type();
     if ((!mixed_dtype && cpuinfo_has_x86_amx_int8()) ||

cmake/Modules/FindMKLDNN.cmake

@@ -85,8 +85,12 @@ IF(NOT MKLDNN_FOUND)
   ENDIF(NOT APPLE AND NOT WIN32 AND NOT BUILD_LITE_INTERPRETER)
 
   IF(EXISTS "${MKLDNN_ROOT}/include/oneapi/dnnl/dnnl_ukernel.hpp")
-    MESSAGE("-- Will build oneDNN UKERNEL")
+    IF(CPU_POWER)
-    SET(DNNL_EXPERIMENTAL_UKERNEL ON CACHE BOOL "" FORCE)
+      SET(DNNL_EXPERIMENTAL_UKERNEL OFF CACHE BOOL "" FORCE)
+    ELSE()
+      MESSAGE("-- Will build oneDNN UKERNEL")
+      SET(DNNL_EXPERIMENTAL_UKERNEL ON CACHE BOOL "" FORCE)
+    ENDIF()
   ENDIF(EXISTS "${MKLDNN_ROOT}/include/oneapi/dnnl/dnnl_ukernel.hpp")
 
   FIND_PACKAGE(BLAS)