Repository navigation

feat: specialize primitive sums for constant and run-end arrays #10535

Job	Run time
Detect CUDA changes	6s
Benchmark with Codspeed (Shard #1)	4m 47s
Benchmark with Codspeed (avx512)	3m 23s
Benchmark with Codspeed (neon)	4m 20s
Benchmark with Codspeed (avx2)	3m 22s
Benchmark with Codspeed (Shard #2)	9m 15s
Benchmark with Codspeed (Shard #5)	5m 43s
Benchmark with Codspeed (Shard #3)	4m 15s
Benchmark with Codspeed (Shard #9)	4m 39s
Benchmark with Codspeed (Shard #8)	3m 44s
Benchmark with Codspeed (Shard #6)	3m 27s
Benchmark with Codspeed (Shard #4)	4m 15s
Benchmark with Codspeed (Shard #7)	4m 12s
Build Codspeed CUDA benchmarks	0s
Benchmark with Codspeed (CUDA Shard #${{ matrix.shard }} - ${{ matrix.name }})	-1s
	55m 27s