Biallelic loss-of-function (LOF) mutations of the NCF4 gene, encoding the p40 phox subunit of the phagocyte NADPH oxidase, have been described in only 1 patient. We report on 24 p40 phox -deficient patients from 12 additional families in 8 countries. These patients display 8 different in-frame or out-of-frame mutations of NCF4 that are homozygous in 11 of the families and compound heterozygous in another. When overexpressed in NB4 neutrophil-like cells and EBV-transformed B cells in vitro, the mutant alleles were found to be LOF, with the exception of the p.R58C and c.120_134del alleles, which were hypomorphic. Particle-induced NADPH oxidase activity was severely impaired in the patients' neutrophils, whereas PMAinduced dihydrorhodamine-1,2,3 (DHR) oxidation, which is widely used as a diagnostic test for chronic granulomatous disease (CGD), was normal or mildly impaired in the patients. Moreover, the NADPH oxidase activity of EBV-transformed B cells was also severely impaired, whereas that of mononuclear phagocytes was normal. Finally, the killing of Candida albicans and Aspergillus fumigatus hyphae by neutrophils was conserved in these patients, unlike in patients with CGD. The patients suffer from hyperinflammation and peripheral infections, but they do not have any of the invasive bacterial or fungal infections seen in CGD. Inherited p40 phox deficiency underlies a distinctive condition, resembling a mild, atypical form of CGD. phox -deficient patient is compound heterozygous for a premature stop codon and a missense mutation in the PX domain that compromises binding to PI(3)P, which results in the impairment of neutrophil phagocytosis-induced oxidase activity (26). As in classic CGD neutrophils, intracellular oxidant production after stimulation with serum-opsonized zymosan (SOZ), IgG beads, or serumopsonized Staphylococcus aureus is impaired in the patient's neutrophils, and S. aureus killing is also defective (20,26,30). However, in this patient, unlike in classic CGD patients, the production of O 2 -by neutrophils in response to stimulation with PMA or formyl-methionyl-leucyl-phenylalanine (fMLF) is normal (26). The killing of S. aureus by neutrophils is also impaired in p40 phox deficiency and classic CGD are largely unknown. Here, we describe the characteristics of 24 patients from 12 families in 8 countries with biallelic mutations of NCF4. The Journal of Clinical Investigation R E S E A R C H A R T I C L E

Abstract-We present Task Superscalar, an abstraction of instruction-level out-of-order pipeline that operates at the tasklevel. Like ILP pipelines, which uncover parallelism in a sequential instruction stream, task superscalar uncovers tasklevel parallelism among tasks generated by a sequential thread. Utilizing intuitive programmer annotations of task inputs and outputs, the task superscalar pipeline dynamically detects intertask data dependencies, identifies task-level parallelism, and executes tasks out-of-order.Furthermore, we propose a design for a distributed task superscalar pipeline frontend, that can be embedded into any manycore fabric, and manages cores as functional units.We show that our proposed mechanism is capable of driving hundreds of cores simultaneously with non-speculative tasks, which allows our pipeline to sustain work windows consisting of tens of thousands of tasks. We further show that our pipeline can maintain a decode rate faster than 60ns per task and dynamically uncover data dependencies among as many as ∼50,000 in-flight tasks, using 7MB of on-chip eDRAM storage. This configuration achieves speedups of 95-255x (average 183x) over sequential execution for nine scientific benchmarks, running on a simulated CMP with 256 cores.Task superscalar thus enables programmers to exploit manycore systems effectively, while simultaneously simplifying their programming model.

The SARC architecture is composed of multiple processor types and a set of user-managed direct memory access (DMA) engines that let the runtime scheduler overlap data transfer and computation. The runtime system automatically allocates tasks on the heterogeneous cores and schedules the data transfers through the DMA engines. SARC's programming model supports various highly parallel applications, with matching support from specialized accelerator processors. On-chip parallel computation shows great promise for scaling raw processing performance within a given power budget. However, chip multiprocessors (CMPs) often struggle with programmability and scalability issues such as cache coherency and off-chip memory bandwidth and latency.

No abstract