use short lib path, XT libs, lint (#7898)

Summary:
Pull Request resolved: #7898

titled, will combine with stacked

resolve build-jarvis-xtensa-dsp error in previous diff

https://www.internalfb.com/sandcastle/workflow/2612087783880687743

Reviewed By: hsharma35

Differential Revision: D68457025

Author: zonglinpeng

backends/cadence/hifi/kernels/targets.bzl

@@ -2,12 +2,17 @@ load("@fbsource//tools/build_defs:platform_defs.bzl", "CXX")
 load("@fbsource//xplat/executorch/build:runtime_wrapper.bzl", "runtime")
 
 def define_common_targets():
+    common_deps = [
+        "//executorch/runtime/kernel:kernel_includes",
+    ]
+
     runtime.cxx_library(
         name = "kernels",
         srcs = ["kernels.cpp"],
         exported_headers = [
             "kernels.h",
         ],
+        deps = common_deps,
         visibility = [
             "//executorch/backends/cadence/...",
         ],

backends/cadence/hifi/operators/op_atan2.cpp

@@ -6,12 +6,11 @@
  * LICENSE file in the root directory of this source tree.
  */
 
-#include <cmath>
 #include <executorch/backends/cadence/hifi/kernels/kernels.h>
 #include <executorch/kernels/portable/cpu/util/broadcast_util.h>
 #include <executorch/kernels/portable/cpu/util/elementwise_util.h>
 #include <executorch/runtime/kernel/kernel_includes.h>
-
+#include <cmath>
 
 using executorch::aten::ScalarType;
 using executorch::aten::Tensor;

backends/cadence/hifi/operators/op_permute_copy.cpp

@@ -93,9 +93,9 @@ Tensor& permute_copy_out(
     WORD32 p_permute_vec[kNnlibMaxDim];
 
     for (int i = 0; i < num_inp_dims; i++) {
-       p_inp_shape[i] = in.size(i);
-       p_out_shape[i] = in.size(dims[i]);
-       p_permute_vec[i] = dims[i];
+      p_inp_shape[i] = in.size(i);
+      p_out_shape[i] = in.size(dims[i]);
+      p_permute_vec[i] = dims[i];
     }
 
     if (in_type == ScalarType::Float) {

backends/cadence/hifi/operators/op_where.cpp

@@ -28,7 +28,7 @@ namespace impl {
 namespace HiFi {
 namespace native {
 
-Tensor& where_out(
+Tensor& where_self_out(
     RuntimeContext& ctx,
     const Tensor& cond,
     const Tensor& a,

backends/cadence/hifi/third-party/nnlib/xa_nn_elm_clamp_f32_broadcast.c

@@ -19,12 +19,11 @@
 * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 ******************************************************************************/
-#include "nnlib-hifi4/xa_nnlib/include/xa_type_def.h"
-#include "nnlib-hifi4/xa_nnlib/algo/common/include/xa_nnlib_common_fpu.h"
-#include "nnlib-hifi4/xa_nnlib/algo/common/include/xa_nn_common.h"
-#include "nnlib-hifi4/xa_nnlib/algo/common/include/xa_nnlib_err_chk.h"
-#include "nnlib-hifi4/xa_nnlib/algo/kernels/basic/hifi4/xa_nn_basic_state.h"
-#include "nnlib-hifi4/xa_nnlib/include/nnlib/xa_nnlib_kernels_api.h"
+#include "xa_type_def.h"
+#include "xa_nnlib_common_fpu.h"
+#include "xa_nn_common.h"
+#include "xa_nnlib_err_chk.h"
+#include "xa_nnlib_kernels_api.h"
 
 
 #if !HAVE_VFPU

backends/cadence/hifi/third-party/nnlib/xa_nn_elm_minimum_maximum_f32.c

@@ -843,4 +843,3 @@ WORD32 xa_nn_elm_minimum_broadcast_4D_f32xf32_f32(FLOAT32 * __restrict__ p_out,
 }
 
 #endif
-