Skip to content

Instantly share code, notes, and snippets.

@rkfg

rkfg/gist:f548ba7e79c181641e9ef971f4251f30

Created March 17, 2017 18:26
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save rkfg/f548ba7e79c181641e9ef971f4251f30 to your computer and use it in GitHub Desktop.
Save rkfg/f548ba7e79c181641e9ef971f4251f30 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
gistfile1.txt
Preliminary scalar launch params: gridSize: [1], blockSize: [32], base shmem: [344], blocksPerMP: [0], problemLength: [18], effectiveBlockLimit: [480]
AF6 opNum:[16], launchDims.x: [1], launchDims.y: [32]
ShapeInfo: [2, 1, 18, 1, 1, 0, 1, 102, ]
F6 opNum:[16]
Preliminary scalar launch params: gridSize: [978], blockSize: [64], base shmem: [344], blocksPerMP: [32], problemLength: [360630], effectiveBlockLimit: [480]
F6 opNum:[16]
Preliminary scalar launch params: gridSize: [978], blockSize: [64], base shmem: [344], blocksPerMP: [32], problemLength: [360630], effectiveBlockLimit: [480]
F6 opNum:[16]
Preliminary scalar launch params: gridSize: [40], blockSize: [32], base shmem: [344], blocksPerMP: [2], problemLength: [1280], effectiveBlockLimit: [480]
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [40], blockSize: [32], base shmem: [344], blocksPerMP: [2], problemLength: [1280], effectiveBlockLimit: [480]
F4 opNum:[57]
Preliminary scalar launch params: gridSize: [40], blockSize: [32], base shmem: [344], blocksPerMP: [2], problemLength: [1280], effectiveBlockLimit: [480]
F6 opNum:[16]
Preliminary scalar launch params: gridSize: [40], blockSize: [32], base shmem: [344], blocksPerMP: [2], problemLength: [1280], effectiveBlockLimit: [480]
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [40], blockSize: [32], base shmem: [344], blocksPerMP: [2], problemLength: [1280], effectiveBlockLimit: [480]
F6 opNum:[16]
Preliminary scalar launch params: gridSize: [40], blockSize: [32], base shmem: [344], blocksPerMP: [2], problemLength: [1280], effectiveBlockLimit: [480]
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [960], blockSize: [64], base shmem: [344], blocksPerMP: [32], problemLength: [25644800], effectiveBlockLimit: [480]
F3 opNum:[0]
Launch context: numBlocks: [1280], numThreads: [256], countMap: [15], shmemThreshold: [163840], desiredShared: [1927], elementSize: [4]
MAB: [476], memory_floor: [344], memory_limit: [344], reductionPerBlock: [0]
Preliminary reduce launch params: gridSize: [1280], blockSize: [32], base shmem: [344], reduction_per_block: [0], blocksPerMP: [85]
Reduce LaunchParams: xLength: [327680], numTads: [1280], tadLength: [256], launchDims.x: [1280], launchDims.y: [32], launchDims.z: [344]
F19 opNum:[10]
Preliminary scalar launch params: gridSize: [974], blockSize: [64], base shmem: [344], blocksPerMP: [32], problemLength: [327680], effectiveBlockLimit: [480]
Launch context: numBlocks: [1280], numThreads: [256], countMap: [15], shmemThreshold: [163840], desiredShared: [1927], elementSize: [4]
MAB: [476], memory_floor: [344], memory_limit: [344], reductionPerBlock: [0]
Preliminary reduce launch params: gridSize: [1280], blockSize: [32], base shmem: [344], reduction_per_block: [0], blocksPerMP: [85]
Reduce LaunchParams: xLength: [327680], numTads: [1280], tadLength: [256], launchDims.x: [1280], launchDims.y: [32], launchDims.z: [344]
F6 opNum:[16]
Preliminary scalar launch params: gridSize: [974], blockSize: [64], base shmem: [344], blocksPerMP: [32], problemLength: [327680], effectiveBlockLimit: [480]
21:23:53,521 INFO ~ Number of threads used for BLAS: 0
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [960], blockSize: [64], base shmem: [344], blocksPerMP: [32], problemLength: [4194304], effectiveBlockLimit: [480]
F6 opNum:[16]
Preliminary scalar launch params: gridSize: [256], blockSize: [32], base shmem: [344], blocksPerMP: [17], problemLength: [8192], effectiveBlockLimit: [480]
F19 opNum:[46]
Preliminary scalar launch params: gridSize: [512], blockSize: [32], base shmem: [344], blocksPerMP: [34], problemLength: [131072], effectiveBlockLimit: [480]
Launch context: numBlocks: [4096], numThreads: [32], countMap: [15], shmemThreshold: [163840], desiredShared: [600], elementSize: [4]
MAB: [476], memory_floor: [344], memory_limit: [344], reductionPerBlock: [0]
Preliminary reduce launch params: gridSize: [4096], blockSize: [32], base shmem: [344], reduction_per_block: [0], blocksPerMP: [273]
Reduce LaunchParams: xLength: [131072], numTads: [4096], tadLength: [32], launchDims.x: [4096], launchDims.y: [32], launchDims.z: [344]
F19 opNum:[15]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
Launch context: numBlocks: [1024], numThreads: [32], countMap: [15], shmemThreshold: [163840], desiredShared: [2409], elementSize: [4]
MAB: [476], memory_floor: [344], memory_limit: [344], reductionPerBlock: [0]
Preliminary reduce launch params: gridSize: [1024], blockSize: [32], base shmem: [344], reduction_per_block: [0], blocksPerMP: [68]
Reduce LaunchParams: xLength: [32768], numTads: [1024], tadLength: [32], launchDims.x: [1024], launchDims.y: [32], launchDims.z: [344]
F4 opNum:[17]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F19 opNum:[10]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
Launch context: numBlocks: [1024], numThreads: [32], countMap: [15], shmemThreshold: [163840], desiredShared: [2409], elementSize: [4]
MAB: [476], memory_floor: [344], memory_limit: [344], reductionPerBlock: [0]
Preliminary reduce launch params: gridSize: [1024], blockSize: [32], base shmem: [344], reduction_per_block: [0], blocksPerMP: [68]
Reduce LaunchParams: xLength: [32768], numTads: [1024], tadLength: [32], launchDims.x: [1024], launchDims.y: [32], launchDims.z: [344] [7577/64056]
F4 opNum:[17]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F19 opNum:[10]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[6]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F19 opNum:[46]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[6]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F19 opNum:[46]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[17]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
Launch context: numBlocks: [1024], numThreads: [32], countMap: [15], shmemThreshold: [163840], desiredShared: [2409], elementSize: [4]
MAB: [476], memory_floor: [344], memory_limit: [344], reductionPerBlock: [0]
Preliminary reduce launch params: gridSize: [1024], blockSize: [32], base shmem: [344], reduction_per_block: [0], blocksPerMP: [68]
Reduce LaunchParams: xLength: [32768], numTads: [1024], tadLength: [32], launchDims.x: [1024], launchDims.y: [32], launchDims.z: [344]
F4 opNum:[17]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F19 opNum:[10]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F19 opNum:[15]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[6]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F19 opNum:[46]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F6 opNum:[16]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F6 opNum:[16]
Preliminary scalar launch params: gridSize: [256], blockSize: [32], base shmem: [344], blocksPerMP: [17], problemLength: [8192], effectiveBlockLimit: [480]
F19 opNum:[46]
Preliminary scalar launch params: gridSize: [512], blockSize: [32], base shmem: [344], blocksPerMP: [34], problemLength: [131072], effectiveBlockLimit: [480]
Launch context: numBlocks: [4096], numThreads: [32], countMap: [15], shmemThreshold: [163840], desiredShared: [600], elementSize: [4]
MAB: [476], memory_floor: [344], memory_limit: [344], reductionPerBlock: [0]
Preliminary reduce launch params: gridSize: [4096], blockSize: [32], base shmem: [344], reduction_per_block: [0], blocksPerMP: [273]
Reduce LaunchParams: xLength: [131072], numTads: [4096], tadLength: [32], launchDims.x: [4096], launchDims.y: [32], launchDims.z: [344]
F19 opNum:[15]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
Launch context: numBlocks: [1024], numThreads: [32], countMap: [15], shmemThreshold: [163840], desiredShared: [2409], elementSize: [4]
MAB: [476], memory_floor: [344], memory_limit: [344], reductionPerBlock: [0]
Preliminary reduce launch params: gridSize: [1024], blockSize: [32], base shmem: [344], reduction_per_block: [0], blocksPerMP: [68]
Reduce LaunchParams: xLength: [32768], numTads: [1024], tadLength: [32], launchDims.x: [1024], launchDims.y: [32], launchDims.z: [344]
F4 opNum:[17]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F19 opNum:[10]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F4 opNum:[16]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
Launch context: numBlocks: [1024], numThreads: [32], countMap: [15], shmemThreshold: [163840], desiredShared: [2409], elementSize: [4]
MAB: [476], memory_floor: [344], memory_limit: [344], reductionPerBlock: [0]
Preliminary reduce launch params: gridSize: [1024], blockSize: [32], base shmem: [344], reduction_per_block: [0], blocksPerMP: [68]
Reduce LaunchParams: xLength: [32768], numTads: [1024], tadLength: [32], launchDims.x: [1024], launchDims.y: [32], launchDims.z: [344]
F4 opNum:[17]
Preliminary scalar launch params: gridSize: [512], blockSize: [64], base shmem: [344], blocksPerMP: [34], problemLength: [32768], effectiveBlockLimit: [480]
F19 opNum:[10]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment