Regenerate latency plots/diagrams for post-Phase-2c model

Allreduce + pe2pe + ipcq + pe_view auto-regenerated by test sweeps
running against the new chunk-streaming wire timing (per-flit
wormhole) — absolute numbers shift upward to reflect bottleneck-link
transit charged once per flit (instead of the previous cut-through
subtraction at HBM CTRL).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

docs/diagrams/allreduce_latency_plots/summary.csv

@@ -1,37 +1,37 @@
-algorithm,sip_topology,n_sips,n_elem,bytes_per_pe,bytes_per_sip,latency_ns
-intercube_allreduce,mesh_2d_no_wrap,6,8,16,256,2626.302499999998
-intercube_allreduce,mesh_2d_no_wrap,6,32,64,1024,2634.7399999999952
-intercube_allreduce,mesh_2d_no_wrap,6,64,128,2048,2645.9899999999925
-intercube_allreduce,mesh_2d_no_wrap,6,128,256,4096,2668.489999999987
-intercube_allreduce,mesh_2d_no_wrap,6,512,1024,16384,2812.489999999987
-intercube_allreduce,mesh_2d_no_wrap,6,1024,2048,32768,3010.489999999987
-intercube_allreduce,mesh_2d_no_wrap,6,2048,4096,65536,3406.489999999987
-intercube_allreduce,mesh_2d_no_wrap,6,4096,8192,131072,4198.489999999965
-intercube_allreduce,mesh_2d_no_wrap,6,8192,16384,262144,5782.489999999969
-intercube_allreduce,mesh_2d_no_wrap,6,16384,32768,524288,8950.489999999925
-intercube_allreduce,mesh_2d_no_wrap,6,32768,65536,1048576,15286.48999999986
-intercube_allreduce,mesh_2d_no_wrap,6,49152,98304,1572864,21622.489999999932
-intercube_allreduce,ring_1d,6,8,16,256,2302.9849999999933
-intercube_allreduce,ring_1d,6,32,64,1024,2310.8599999999906
-intercube_allreduce,ring_1d,6,64,128,2048,2321.359999999988
-intercube_allreduce,ring_1d,6,128,256,4096,2342.3599999999824
-intercube_allreduce,ring_1d,6,512,1024,16384,2479.3599999999824
-intercube_allreduce,ring_1d,6,1024,2048,32768,2669.3599999999824
-intercube_allreduce,ring_1d,6,2048,4096,65536,3049.3599999999824
-intercube_allreduce,ring_1d,6,4096,8192,131072,3809.3599999999715
-intercube_allreduce,ring_1d,6,8192,16384,262144,5329.359999999979
-intercube_allreduce,ring_1d,6,16384,32768,524288,8369.35999999992
-intercube_allreduce,ring_1d,6,32768,65536,1048576,14449.359999999899
-intercube_allreduce,ring_1d,6,49152,98304,1572864,20529.35999999997
-intercube_allreduce,torus_2d,6,8,16,256,1644.2899999999936
-intercube_allreduce,torus_2d,6,32,64,1024,1651.0399999999909
-intercube_allreduce,torus_2d,6,64,128,2048,1660.0399999999881
-intercube_allreduce,torus_2d,6,128,256,4096,1678.0399999999827
-intercube_allreduce,torus_2d,6,512,1024,16384,1795.0399999999827
-intercube_allreduce,torus_2d,6,1024,2048,32768,1957.0399999999827
-intercube_allreduce,torus_2d,6,2048,4096,65536,2281.0399999999827
-intercube_allreduce,torus_2d,6,4096,8192,131072,2929.039999999979
-intercube_allreduce,torus_2d,6,8192,16384,262144,4225.039999999986
-intercube_allreduce,torus_2d,6,16384,32768,524288,6817.039999999943
-intercube_allreduce,torus_2d,6,32768,65536,1048576,12001.03999999992
-intercube_allreduce,torus_2d,6,49152,98304,1572864,17185.039999999994
+algorithm,sip_topology,n_sips,n_elem,bytes_per_pe,bytes_per_sip,latency_ns
+intercube_allreduce,mesh_2d_no_wrap,6,8,16,256,2666.5524999999725
+intercube_allreduce,mesh_2d_no_wrap,6,32,64,1024,2747.7399999999725
+intercube_allreduce,mesh_2d_no_wrap,6,64,128,2048,2855.98999999998
+intercube_allreduce,mesh_2d_no_wrap,6,128,256,4096,3072.4899999999725
+intercube_allreduce,mesh_2d_no_wrap,6,512,1024,16384,3336.579999999951
+intercube_allreduce,mesh_2d_no_wrap,6,1024,2048,32768,3707.49999999992
+intercube_allreduce,mesh_2d_no_wrap,6,2048,4096,65536,4449.339999999875
+intercube_allreduce,mesh_2d_no_wrap,6,4096,8192,131072,5933.020000000055
+intercube_allreduce,mesh_2d_no_wrap,6,8192,16384,262144,8900.380000000157
+intercube_allreduce,mesh_2d_no_wrap,6,16384,32768,524288,14835.099999997583
+intercube_allreduce,mesh_2d_no_wrap,6,32768,65536,1048576,26704.540000017492
+intercube_allreduce,mesh_2d_no_wrap,6,49152,98304,1572864,38573.980000026335
+intercube_allreduce,ring_1d,6,8,16,256,2365.2558333333036
+intercube_allreduce,ring_1d,6,32,64,1024,2436.9433333333036
+intercube_allreduce,ring_1d,6,64,128,2048,2532.526666666643
+intercube_allreduce,ring_1d,6,128,256,4096,2723.6933333333036
+intercube_allreduce,ring_1d,6,512,1024,16384,3042.0349999999544
+intercube_allreduce,ring_1d,6,1024,2048,32768,3390.201666666597
+intercube_allreduce,ring_1d,6,2048,4096,65536,4079.7349999998714
+intercube_allreduce,ring_1d,6,4096,8192,131072,5458.801666666721
+intercube_allreduce,ring_1d,6,8192,16384,262144,8216.93500000014
+intercube_allreduce,ring_1d,6,16384,32768,524288,13733.201666664638
+intercube_allreduce,ring_1d,6,32768,65536,1048576,24765.735000014545
+intercube_allreduce,ring_1d,6,49152,98304,1572864,35798.268333355256
+intercube_allreduce,torus_2d,6,8,16,256,1700.6024999999754
+intercube_allreduce,torus_2d,6,32,64,1024,1753.2899999999754
+intercube_allreduce,torus_2d,6,64,128,2048,1823.539999999979
+intercube_allreduce,torus_2d,6,128,256,4096,1964.0399999999754
+intercube_allreduce,torus_2d,6,512,1024,16384,2196.2849999999653
+intercube_allreduce,torus_2d,6,1024,2048,32768,2476.74499999995
+intercube_allreduce,torus_2d,6,2048,4096,65536,3037.664999999919
+intercube_allreduce,torus_2d,6,4096,8192,131072,4159.50500000003
+intercube_allreduce,torus_2d,6,8192,16384,262144,6403.185000000081
+intercube_allreduce,torus_2d,6,16384,32768,524288,10890.544999998769
+intercube_allreduce,torus_2d,6,32768,65536,1048576,19865.265000008738
+intercube_allreduce,torus_2d,6,49152,98304,1572864,28839.985000013185