v0.4.6

BinomialGPU v0.4.6

Diff since v0.4.5

Merged pull requests:

• Try package on CUDA.jl v4 (#26) (@simsurace)

v0.4.5

BinomialGPU v0.4.5

Diff since v0.4.4

Closed issues:

• Kernel grid-stride-loops might be wrong (#24)

Merged pull requests:

• Use correct window sizes for grid-stride loop (#25) (@simsurace)

v0.4.4

BinomialGPU v0.4.4

Diff since v0.4.3

Merged pull requests:

• Optimizations (#23) (@simsurace)

v0.4.3

BinomialGPU v0.4.3

Diff since v0.4.2

Merged pull requests:

• Fix inversion bug (#22) (@simsurace)

v0.4.2

BinomialGPU v0.4.2

Diff since v0.4.1

Merged pull requests:

• Fix kernel type stability (#21) (@simsurace)

v0.4.1

BinomialGPU v0.4.1

Diff since v0.4.0

Merged pull requests:

• Switch to new specification for test dependencies (#20) (@simsurace)

v0.4.0

BinomialGPU v0.4.0

Diff since v0.3.0

Closed issues:

• Performance is better with 256 threads than with the maximal number of threads (#2)

Merged pull requests:

• Out-of-place interface (#19) (@simsurace)

v0.3.0

BinomialGPU v0.3.0

Diff since v0.2.6

Closed issues:

• Try new rand(Float32) in kernel (#7)
• Benchmark is almost twice as fast in 1.5.4 than Julia 1.6-rc2 (#8)

Merged pull requests:

• Incorporate CUDA.rand() (#14) (@simsurace)
• CompatHelper: bump compat for "BenchmarkTools" to "1.0" (#15) (@github-actions[bot])
• Change to native rand (#18) (@simsurace)

v0.2.6

BinomialGPU v0.2.6

Diff since v0.2.5

Merged pull requests:

• CompatHelper: bump compat for "BenchmarkTools" to "0.7" (#12) (@github-actions[bot])
• CompatHelper: bump compat for "CUDA" to "3.0" (#13) (@github-actions[bot])

v0.2.5

BinomialGPU v0.2.5

Diff since v0.2.4