## Posts

### Running Spark Rapids on OpenShift

### Decision Making Considered Harmful - The Branch Prediction Incident of August 2020

### Some Unit Signature Results for Matrix Inversions

### A Unit Analysis of Linear Regression

### Unit Analysis for Linear Algebra

### Your Data Type is a Unit

### Unit Types for Avro Schema: Integrating Avro with Coulomb

### Preventing Configuration Errors With Unit Types

### Algorithmic Unit Analysis

### The Smooth-Max Minimum Incident of December 2018

### The Backtracking ULP Incident of 2018

### Equality Constraints for Cubic B-Splines

### Putting Cubic B-Splines into Standard Polynomial Form

### Solving Feasible Points With Smooth-Max

### Computing Smooth Max and its Gradients Without Over- and Underflow

### The Gradient and Hessian of the Smooth Max Over Functions

### Rethinking the Concept of Release Versioning

### Converging Monoid Addition for T-Digest

### Encoding Map-Reduce As A Monoid With Left Folding

### Supporting Competing APIs in Scala -- Can Better Package Factoring Help?

### Using Minimum Description Length to Optimize the 'K' in K-Medoids

### Approximating a PDF of Distances With a Gamma Distribution

### Computing Derivatives of the Gamma Function

### Exploring the Effects of Dimensionality on a PDF of Distances

### Measuring Decision Tree Split Quality with Test Statistic P-Values

### Random Forest Clustering of Machine Package Configurations in Apache Spark

### Computing Simplex Vertex Locations From Pairwise Object Distances

### Efficient Multiplexing for Spark RDDs

### The 'prepare' operation considered harmful in Algebird aggregation

### Very Fast Reservoir Sampling

### A Library of Binary Tree Algorithms as Mixable Scala Traits

### Lightweight Non-Negative Numerics for Better Scala Type Signatures

### The Reservoir Sampling Gap Distribution

### Generalizing Kendall's Tau

### Parallel K-Medoids Using Scala ParSeq

### Hygienic Closures for Scala Function Serialization

### Monadic 'break' and 'continue' for Scala Sequence Comprehensions

### Faster Random Samples With Gap Sampling

### The Scala Iterator 'drop' Method Generates a Matryoshka Class Nesting

### Implementing Parallel Prefix Scan as a Spark RDD Transform

### Implementing an RDD scanLeft Transform With Cascade RDDs

### Deferring Spark Actions to Lazy Transforms With the Promise RDD

### Some Implications of Supporting the Scala drop Method for Spark RDDs

### A Bi-directional Variation of the O(NP) Edit Distance Algorithm

### The Impact of Negotiator Cycle Cadence on Slot Loading

### Smooth Gradients for Cubic Hermite Splines

### Examining the Modulus of Random Variables

### The Mean of the Modulus Does Not Equal the Modulus of the Mean

### A Demonstration of Negotiator-Side Resource Consumption

### Rethinking the Semantics of Group Quotas and Slot Weights: Computing Claim Capacity from Consumption Policy

### Rethinking the Semantics of Group Quotas and Slot Weights: Claim Capacity Model

### Rethinking the Semantics of Group Quotas and Slot Weights for Heterogeneous and Multidimensional Compute Resources

### Using Accounting Groups With Wallaby

### Randomized Sleep Jobs in HTCondor Using Delayed Evaluation

### Hosting a Blog Feed Aggregator With Octopress

### Improved Parse Checking for ClassAd Log Files in Condor

### Driving a Condor Job Renice Policy with Accounting Groups

### LIFO and FIFO Preemption Policies for a Condor Pool

### Configuring Minimum and Maximum Resources for Mission Critical Jobs in a Condor Pool

### Deriving an Incremental Form of the Polynomial Regression Equations

### Easy Histograms and Tables from Condor Jobs and Slots

### Maintaining Accounting Group Quotas With Preemption Policy

### The Joy of Anonymized Data

### Pretty Good Random Sampling from Database Queries

### Interaction between mktime() and tm_isdst - a compute cycle landmine

### Don't try to stop me. I'm on a rampage.

subscribe via RSS