Create consume_rvalues separate from unwrapping

include/dlaf/common/consume_rvalues.h

@@ -0,0 +1,43 @@
+//
+// Distributed Linear Algebra with Future (DLAF)
+//
+// Copyright (c) 2018-2023, ETH Zurich
+// All rights reserved.
+//
+// Please, refer to the LICENSE file in the root directory.
+// SPDX-License-Identifier: BSD-3-Clause
+//
+#pragma once
+
+/// @file
+
+#include <tuple>
+#include <type_traits>
+#include <utility>
+
+namespace dlaf::common::internal {
+/// ConsumeRvalues is a callable object wrapper that consumes rvalues passed as arguments
+/// after calling the wrapped callable.
+template <typename F>
+struct ConsumeRvalues {
+  std::decay_t<F> f;
+
+  template <typename... Ts>
+  auto operator()(Ts&&... ts) -> decltype(std::move(f)(std::forward<Ts>(ts)...)) {
+    using result_type = decltype(std::move(f)(std::forward<Ts>(ts)...));
+    if constexpr (std::is_void_v<result_type>) {
+      std::move(f)(std::forward<Ts>(ts)...);
+      std::tuple<Ts...>(std::forward<Ts>(ts)...);
+    }
+    else {
+      auto r = std::move(f)(std::forward<Ts>(ts)...);
+      std::tuple<Ts...>(std::forward<Ts>(ts)...);
+      return r;
+    }
+  }
+};
+
+template <typename F>
+ConsumeRvalues(F&&) -> ConsumeRvalues<std::decay_t<F>>;
+
+}

include/dlaf/common/unwrap.h

@@ -58,18 +58,7 @@ struct Unwrapping {
   template <typename... Ts>
   auto operator()(Ts&&... ts)
       -> decltype(std::move(f)(Unwrapper<std::decay_t<Ts>>::unwrap(std::forward<Ts>(ts))...)) {
-    using result_type = decltype(std::move(f)(Unwrapper<std::decay_t<Ts>>::unwrap(std::forward<Ts>(ts))...));
-    if constexpr(std::is_void_v<result_type>)
-    {
-        std::move(f)(Unwrapper<std::decay_t<Ts>>::unwrap(std::forward<Ts>(ts))...);
-        std::tuple<Ts...>(std::forward<Ts>(ts)...);
-    }
-    else
-    {
-        auto r = std::move(f)(Unwrapper<std::decay_t<Ts>>::unwrap(std::forward<Ts>(ts))...);
-        std::tuple<Ts...>(std::forward<Ts>(ts)...);
-        return r;
-    }
+    return std::move(f)(Unwrapper<std::decay_t<Ts>>::unwrap(std::forward<Ts>(ts))...);
   }
 };
 

include/dlaf/sender/transform.h

@@ -11,6 +11,7 @@
 
 #include <pika/execution.hpp>
 
+#include <dlaf/common/consume_rvalues.h>
 #include <dlaf/common/unwrap.h>
 #include <dlaf/init.h>
 #include <dlaf/schedulers.h>
@@ -43,7 +44,7 @@ enum class TransformDispatchType { Plain, Blas, Lapack };
 // allows choosing the priority.
 //
 // At its core, transform is a convenience wrapper around
-// sender | transfer(with_priority(scheduler, priority)) | then(unwrapping(f)).
+// sender | transfer(with_priority(scheduler, priority)) | then(ConsumeRvalues(unwrapping(f))).
 
 /// Lazy transform. This does not submit the work and returns a sender.
 template <TransformDispatchType Tag = TransformDispatchType::Plain, Backend B = Backend::MC,
@@ -56,8 +57,11 @@ template <TransformDispatchType Tag = TransformDispatchType::Plain, Backend B =
   auto scheduler = getBackendScheduler<B>(policy.priority());
   auto transfer_sender = transfer(std::forward<Sender>(sender), std::move(scheduler));
 
+  using dlaf::common::internal::ConsumeRvalues;
+  using dlaf::common::internal::Unwrapping;
+
   if constexpr (B == Backend::MC) {
-    return then(std::move(transfer_sender), dlaf::common::internal::Unwrapping{std::forward<F>(f)});
+    return then(std::move(transfer_sender), ConsumeRvalues{Unwrapping{std::forward<F>(f)}});
   }
   else if constexpr (B == Backend::GPU) {
 #if defined(DLAF_WITH_GPU)
@@ -67,16 +71,15 @@ template <TransformDispatchType Tag = TransformDispatchType::Plain, Backend B =
 
     if constexpr (Tag == TransformDispatchType::Plain) {
       return then_with_stream(std::move(transfer_sender),
-                              dlaf::common::internal::Unwrapping{std::forward<F>(f)});
+                              ConsumeRvalues{Unwrapping{std::forward<F>(f)}});
     }
     else if constexpr (Tag == TransformDispatchType::Blas) {
-      return then_with_cublas(std::move(transfer_sender),
-                              dlaf::common::internal::Unwrapping{std::forward<F>(f)},
+      return then_with_cublas(std::move(transfer_sender), ConsumeRvalues{Unwrapping{std::forward<F>(f)}},
                               CUBLAS_POINTER_MODE_HOST);
     }
     else if constexpr (Tag == TransformDispatchType::Lapack) {
       return then_with_cusolver(std::move(transfer_sender),
-                                dlaf::common::internal::Unwrapping{std::forward<F>(f)});
+                                ConsumeRvalues{Unwrapping{std::forward<F>(f)}});
     }
     else {
       DLAF_STATIC_FAIL(

include/dlaf/sender/transform_mpi.h

@@ -11,6 +11,7 @@
 
 #include <type_traits>
 
+#include <dlaf/common/consume_rvalues.h>
 #include <dlaf/common/pipeline.h>
 #include <dlaf/common/unwrap.h>
 #include <dlaf/communication/communicator.h>
@@ -88,7 +89,7 @@ template <typename F, typename Sender,
   namespace ex = pika::execution::experimental;
 
   return ex::transfer(std::forward<Sender>(sender), dlaf::internal::getMPIScheduler()) |
-         ex::then(MPICallHelper{std::forward<F>(f)});
+         ex::then(dlaf::common::internal::ConsumeRvalues{MPICallHelper{std::forward<F>(f)}});
 }
 
 /// Fire-and-forget transformMPI. This submits the work and returns void.