[QNN EP] Add dynamic option to set HTP performance mode (#26135)

### Description
Add a new EP Dynamic option to set HTP performance mode after session creation.

---------

Co-authored-by: quic-ashwshan <quic_ashwshan@quicinc.com>

Author: quic-tirupath

include/onnxruntime/core/session/onnxruntime_session_options_config_keys.h

@@ -408,3 +408,10 @@ static const char* const kOrtSessionOptionsDisableModelCompile = "session.disabl
 // Note: UNSUPPORTED models always fail regardless of this setting.
 static const char* const kOrtSessionOptionsFailOnSuboptimalCompiledModel =
     "session.fail_on_suboptimal_compiled_model";
+
+// THIS OPTION IS NOT A REGULAR SESSION OPTION SINCE IT CAN BE MODIFIED AT ANY TIME
+// Meant to be used with SetEpDynamicOptions
+// options for HTP performance mode: "burst", "balanced", "default", "high_performance",
+// "high_power_saver", "low_balanced", "extreme_power_saver", "low_power_saver", "power_saver",
+// "sustained_high_performance". Default to "default".
+static const char* const kOrtEpDynamicOptionsQnnHtpPerformanceMode = "ep.dynamic.qnn_htp_performance_mode";

onnxruntime/core/providers/qnn/qnn_execution_provider.cc

@@ -1576,6 +1576,17 @@ Status QNNExecutionProvider::SetEpDynamicOptions(gsl::span<const char* const> ke
         LOGS_DEFAULT(ERROR) << "Invalid EP Workload Type: " << value;
         return ORT_MAKE_STATUS(ONNXRUNTIME, INVALID_ARGUMENT, "Invalid EP Workload Type.");
       }
+    } else if (key == kOrtEpDynamicOptionsQnnHtpPerformanceMode) {
+      auto backend_type = qnn_backend_manager_->GetQnnBackendType();
+      if (qnn::QnnBackendType::HTP != backend_type && qnn::QnnBackendType::DSP != backend_type) {
+        return Status::OK();
+      }
+      qnn::HtpPerformanceMode htp_performance_mode = qnn::HtpPerformanceMode::kHtpDefault;
+      ParseHtpPerformanceMode(value, htp_performance_mode);
+      if (GetPerThreadContext().IsHtpPowerConfigIdValid()) {
+        ORT_RETURN_IF_ERROR(qnn_backend_manager_->SetHtpPowerConfig(GetPerThreadContext().GetHtpPowerConfigId(),
+                                                                    htp_performance_mode));
+      }
     } else {
       LOGS_DEFAULT(ERROR) << "EP Dynamic Option \"" << key << "\" is not currently supported.";
       return ORT_MAKE_STATUS(ONNXRUNTIME, INVALID_ARGUMENT, "Unsupported EP Dynamic Option");

onnxruntime/test/providers/qnn/qnn_ep_context_test.cc

@@ -2076,6 +2076,21 @@ TEST_F(QnnHTPBackendTests, QnnEpDynamicOptions) {
   } catch (const std::exception& e) {
     EXPECT_STREQ("Unsupported EP Dynamic Option", e.what());
   }
+
+  const char* const htp_perf_mode_type[] = {"ep.dynamic.qnn_htp_performance_mode"};
+  const char* const eps_type[] = {"extreme_power_saver"};
+  const char* const shp_type[] = {"sustained_high_performance"};
+  session.SetEpDynamicOptions(htp_perf_mode_type, shp_type, 1);
+  ort_output = session.Run(Ort::RunOptions{}, input_names_c.data(), ort_inputs.data(), ort_inputs.size(),
+                           output_names_c.data(), 1);
+
+  session.SetEpDynamicOptions(htp_perf_mode_type, eps_type, 1);
+  ort_output = session.Run(Ort::RunOptions{}, input_names_c.data(), ort_inputs.data(), ort_inputs.size(),
+                           output_names_c.data(), 1);
+
+  session.SetEpDynamicOptions(htp_perf_mode_type, shp_type, 1);
+  ort_output = session.Run(Ort::RunOptions{}, input_names_c.data(), ort_inputs.data(), ort_inputs.size(),
+                           output_names_c.data(), 1);
 }
 
 // Implementation of OrtOutStreamWriteFunc that writes the compiled model to a file.