Search

When lifting an object, individuals scale lifting forces based on long-term priors relating external object properties (such as material and size) to object weight. When experiencing objects that are poorly predicted by priors, people rapidly form and update sensorimotor memories that can be used to predict an object's atypical size-weight relation in support of predictively scaling lift forces. With extensive experience in lifting such objects, long-term priors, assessed with weight judgments, are gradually updated. The aim of the present study was to understand the formation and updating of these memory processes. Participants lifted, over multiple days, a set of black cubes with a normal size-weight mapping and green cubes with an inverse size-weight mapping. Sensorimotor memory was assessed with lifting forces, and priors associated with the black and green cubes were assessed with the size-weight illusion (SWI). Interference was observed in terms of adaptation of the SWI, indicating that priors were not independently adjusted. Half of the participants rapidly learned to scale lift forces appropriately, whereas reduced learning was observed in the others, suggesting that individual differences may be affecting sensorimotor memory abilities. A follow-up experiment showed that lifting forces are not accurately scaled to objects when concurrently performing a visuomotor association task, suggesting that sensorimotor memory formation involves cognitive resources to instantiate the mapping between object identity and weight, potentially explaining the results of experiment 1. These results provide novel insight into the formation and updating of sensorimotor memories and provide support for the independent adjustment of sensorimotor memory and priors.

The ability to predict accurately the weights of objects is essential for skilled and dexterous manipulation. A potentially important source of information about object weight is through the observation of other people lifting objects. Here, we tested the hypothesis that when watching an actor lift an object, people naturally learn the object's weight and use this information to scale forces when they subsequently lift the object themselves. Participants repeatedly lifted an object in turn with an actor. Object weight unpredictably changed between 2 and 7 N every 5th to 9th of the actor's lifts, and the weight lifted by the participant always matched that previously lifted by the actor. Even though the participants were uninformed about the structure of the experiment, they appropriately adapted their lifting force in the first trial after a weight change. Thus, participants updated their internal representation about the object's weight, for use in action, when watching a single lift performed by the actor. This ability presumably involves the comparison of predicted and actual sensory information related to actor's actions, a comparison process that is also fundamental in action., This work was supported by a grant from the Canadian Institutes of Health Research, the Swedish Research Council Project 08667, and the Strategic Research Program in Neuroscience at the Karolinska Institute.

Skilled object lifting requires the prediction of object weight. When lifting new objects, such prediction is based on well-learned size-weight and material-density correlations, or priors. However, if the prediction is erroneous, people quickly learn the weight of the particular object and can use this knowledge, referred to as sensorimotor memory, when lifting the object again. In the present study, we explored how sensorimotor memory, gained when lifting a given object, interacts with well-learned material-density priors when predicting the weight of a larger but otherwise similar-looking object. Different groups of participants 1st lifted 1 of 4 small objects 10 times. These included a pair of wood-filled objects and a pair of brass-filled objects where 1 of each pair was covered in a wood veneer and the other was covered in a brass veneer. All groups then lifted a larger, brass-filled object with the same covering as the small object they had lifted. For each lift, we determined the initial peak rate of change of vertical load-force rate and the load-phase duration, which provide estimates of predicted object weight. Analysis of the 10th lift of the small cube revealed no effects of surface material, indicating participants learned the appropriate forces required to lift the small cube regardless of object appearance. However, both surface material and core material of the small cube affected the 1st lift of the large block. We conclude that sensorimotor memory related to object density can contribute to weight prediction when lifting novel objects but also that long-term priors related to material properties can influence the prediction.

Presented at The Second ACM SIGPLAN Workshop on Transactional Computing (TRANSACT 07), Portland, Oregon, August 16, 2007., Transactional memory (TM) is a scalable and concurrent way to build atomic sections. One aspect of TM that remains unclear is how side-effecting operations – that is, those which cannot be transparently undone by a TM system – should be handled. This uncertainty poses a significant barrier to the general applicability and acceptance of TM. Further, the absence of transactional workloads makes it difficult to study this aspect In this paper, we characterize the usage of I/O, and in particular system calls, within critical sections in two large applications, exploring both the actions performed and the characteristics of the critical sections in which they are performed. Shared memory programs employing critical sections are the closest approximation available to transactional workloads, so using this characterization, we attempt to reason about how the behavior we observed relates to the previous proposals for handling side-effecting operations within transactions. We find that the large majority of syscalls performed within critical sections can be handled with a range of existing techniques in a way transparent to the application developer. We also find that while sideeffecting critical sections are rare, they tend to be quite longlasting, and that many of these critical sections perform their first syscall (and thus become side-effecting) relatively early in their execution. Finally, we show that while these longlived, side-effecting critical sections tend to execute concurrently with many critical sections on other threads, we observe little concurrency between side-effecting critical sections.

Transactional Memory (TM) is a compel ling alternative to locks as a general-purpose concurrency control mechanism, but it is yet unclear whether TM should be implemented as a software or hardware construct. While hardware approaches offer higher performance and can be used in conjunction with legacy languages/code, software approaches are more flexible and currently offer more functionality. In this paper, we try to bridge, in part, the functionality gap between software and hardware TMs by demonstrating how two software TM ideas can be adapted to work in a hardware TM system. Specifically, we demonstrate: 1) a process to efficiently support transaction waiting — both intentional waiting and waiting for a conflicting transaction to complete — by de-scheduling the transacting thread, and 2) the concept of pausing and an implementation of compensation to allow non-idempotent system calls, I/O, and access to high contention data within a long-running transaction. Both mechanisms can be implemented with minimal extensions to an existing hardware TM proposal.

Transactional Memory (TM) is a compel ling alternative to locks as a general-purpose concurrency control mechanism, but it is yet unclear whether TM should be implemented as a software or hardware construct. While hardware approaches offer higher performance and can be used in conjunction with legacy languages/code, software approaches are more flexible and currently offer more functionality. In this paper, we try to bridge, in part, the functionality gap between software and hardware TMs by demonstrating how two software TM ideas can be adapted to work in a hardware TM system. Specifically, we demonstrate: 1) a process to efficiently support transaction waiting — both intentional waiting and waiting for a conflicting transaction to complete — by de-scheduling the transacting thread, and 2) the concept of pausing and an implementation of compensation to allow non-idempotent system calls, I/O, and access to high contention data within a long-running transaction. Both mechanisms can be implemented with minimal extensions to an existing hardware TM proposal.

Presented at The Second ACM SIGPLAN Workshop on Transactional Computing (TRANSACT 07), Portland, Oregon, August 16, 2007., Transactional memory (TM) is a scalable and concurrent way to build atomic sections. One aspect of TM that remains unclear is how side-effecting operations – that is, those which cannot be transparently undone by a TM system – should be handled. This uncertainty poses a significant barrier to the general applicability and acceptance of TM. Further, the absence of transactional workloads makes it difficult to study this aspect In this paper, we characterize the usage of I/O, and in particular system calls, within critical sections in two large applications, exploring both the actions performed and the characteristics of the critical sections in which they are performed. Shared memory programs employing critical sections are the closest approximation available to transactional workloads, so using this characterization, we attempt to reason about how the behavior we observed relates to the previous proposals for handling side-effecting operations within transactions. We find that the large majority of syscalls performed within critical sections can be handled with a range of existing techniques in a way transparent to the application developer. We also find that while sideeffecting critical sections are rare, they tend to be quite longlasting, and that many of these critical sections perform their first syscall (and thus become side-effecting) relatively early in their execution. Finally, we show that while these longlived, side-effecting critical sections tend to execute concurrently with many critical sections on other threads, we observe little concurrency between side-effecting critical sections.

Transactional Memory (TM) is a compel ling alternative to locks as a general-purpose concurrency control mechanism, but it is yet unclear whether TM should be implemented as a software or hardware construct. While hardware approaches offer higher performance and can be used in conjunction with legacy languages/code, software approaches are more flexible and currently offer more functionality. In this paper, we try to bridge, in part, the functionality gap between software and hardware TMs by demonstrating how two software TM ideas can be adapted to work in a hardware TM system. Specifically, we demonstrate: 1) a process to efficiently support transaction waiting — both intentional waiting and waiting for a conflicting transaction to complete — by de-scheduling the transacting thread, and 2) the concept of pausing and an implementation of compensation to allow non-idempotent system calls, I/O, and access to high contention data within a long-running transaction. Both mechanisms can be implemented with minimal extensions to an existing hardware TM proposal.

Presented at The Second ACM SIGPLAN Workshop on Transactional Computing (TRANSACT 07), Portland, Oregon, August 16, 2007., Transactional memory (TM) is a scalable and concurrent way to build atomic sections. One aspect of TM that remains unclear is how side-effecting operations – that is, those which cannot be transparently undone by a TM system – should be handled. This uncertainty poses a significant barrier to the general applicability and acceptance of TM. Further, the absence of transactional workloads makes it difficult to study this aspect In this paper, we characterize the usage of I/O, and in particular system calls, within critical sections in two large applications, exploring both the actions performed and the characteristics of the critical sections in which they are performed. Shared memory programs employing critical sections are the closest approximation available to transactional workloads, so using this characterization, we attempt to reason about how the behavior we observed relates to the previous proposals for handling side-effecting operations within transactions. We find that the large majority of syscalls performed within critical sections can be handled with a range of existing techniques in a way transparent to the application developer. We also find that while sideeffecting critical sections are rare, they tend to be quite longlasting, and that many of these critical sections perform their first syscall (and thus become side-effecting) relatively early in their execution. Finally, we show that while these longlived, side-effecting critical sections tend to execute concurrently with many critical sections on other threads, we observe little concurrency between side-effecting critical sections.