Fig. 4From: Parasail: SIMD C library for global, semi-global, and local pairwise sequence alignmentsPerformance with different scoring systems for global alignments. The speed in billion cell updates per second (GCUPS) (logarithmic scale) is shown for striped SSE4.1 vectors (red), prefix scan SSE4.1 vectors (orange), striped AVX2 vectors (black), and prefix scan AVX2 vectors (green), as well as libssa using SSE4.1 (purple) and AVX2 (gray), using different scoring systems. Note that the libssa results completely overlap. All combinations of scoring matrices and gap penalties accepted by BLAST were tested. The matrix name is indicated above each graph, while the open and extension gap penalties are indicated on the x-axis. The query sequence was P07327 and 24 threads were runningBack to article page