diff --git a/docs/report/1H-codesign-paper/build/main.pdf b/docs/report/1H-codesign-paper/build/main.pdf
index 9c86446..ac74200 100644
Binary files a/docs/report/1H-codesign-paper/build/main.pdf and b/docs/report/1H-codesign-paper/build/main.pdf differ
diff --git a/docs/report/1H-codesign-paper/figures/allreduce_buffer_kind.png b/docs/report/1H-codesign-paper/figures/allreduce_buffer_kind.png
index 19d4cc2..8fb6a71 100644
Binary files a/docs/report/1H-codesign-paper/figures/allreduce_buffer_kind.png and b/docs/report/1H-codesign-paper/figures/allreduce_buffer_kind.png differ
diff --git a/docs/report/1H-codesign-paper/figures/allreduce_comparison.png b/docs/report/1H-codesign-paper/figures/allreduce_comparison.png
index 229dbd3..3475f3b 100644
Binary files a/docs/report/1H-codesign-paper/figures/allreduce_comparison.png and b/docs/report/1H-codesign-paper/figures/allreduce_comparison.png differ
diff --git a/docs/report/1H-codesign-paper/figures/probe_pe_dma_summary.txt b/docs/report/1H-codesign-paper/figures/probe_pe_dma_summary.txt
new file mode 100644
index 0000000..db9b6d1
--- /dev/null
+++ b/docs/report/1H-codesign-paper/figures/probe_pe_dma_summary.txt
@@ -0,0 +1,57 @@
+
+=== H2D Write Latency (IO->HBM, data=32768B) ===
+  Case           Target           Hops     Actual    Ovhd  Drain  Wire  Ovhd%  Drain%     Eff.BW      BN.BW    Util%
+  -------------------------------------------------------------------------------------------------------------------
+  h2d-1hop       cube0.pe0            1     289.53    50.0  256.0  0.18  17.3%  88.4%     113.17      128.0    88.4%
+  h2d-2hop       cube4.pe0            2     326.04    78.0  256.0  0.20  23.9%  78.5%     100.50      128.0    78.5%
+  h2d-3hop       cube8.pe0            3     362.56   106.0  256.0  0.20  29.2%  70.6%      90.38      128.0    70.6%
+  h2d-4hop       cube12.pe0            4     399.06   134.0  256.0  0.21  33.6%  64.1%      82.11      128.0    64.1%
+  [v] Monotonic increase: PASS
+
+  BW Saturation (Util% by data size):
+  Case                           4KB    16KB    64KB   256KB     1MB
+  ------------------------------------------------------------------
+  h2d-1hop                     38.9%   71.8%   91.1%   97.6%   99.4%
+  h2d-2hop                     29.0%   62.1%   86.8%   96.3%   99.1%
+  h2d-3hop                     23.2%   54.7%   82.8%   95.1%   98.7%
+  h2d-4hop                     19.3%   48.8%   79.2%   93.8%   98.4%
+
+=== D2H Read Latency (HBM->IO, data=32768B) ===
+  Case           Source           Hops     Actual    Ovhd  Drain  Wire  Ovhd%  Drain%     Eff.BW      BN.BW    Util%
+  -------------------------------------------------------------------------------------------------------------------
+  d2h-1hop       cube0.pe0            1     571.20    23.0  256.0  0.04   4.0%  44.8%      57.37      128.0    44.8%
+  d2h-2hop       cube4.pe0            2     635.72    51.0  256.0  0.05   8.0%  40.3%      51.54      128.0    40.3%
+  d2h-3hop       cube8.pe0            3     700.24    79.0  256.0  0.06  11.3%  36.6%      46.80      128.0    36.6%
+  d2h-4hop       cube12.pe0            4     764.76   107.0  256.0  0.07  14.0%  33.5%      42.85      128.0    33.5%
+  [v] Monotonic increase: PASS
+
+  BW Saturation (Util% by data size):
+  Case                           4KB    16KB    64KB   256KB     1MB
+  ------------------------------------------------------------------
+  d2h-1hop                      9.2%   28.9%   61.9%   86.7%   96.3%
+  d2h-2hop                      7.8%   25.2%   57.4%   84.4%   95.6%
+  d2h-3hop                      6.7%   22.4%   53.5%   82.2%   94.9%
+  d2h-4hop                      5.9%   20.1%   50.2%   80.1%   94.2%
+  [v] D2H >= H2D (reverse data path): PASS
+
+=== PE DMA Latency (pe_dma -> router -> HBM, data=32768B) ===
+  Case                       Target                         Actual    Ovhd  Drain  Wire  Ovhd%  Drain%     Eff.BW      BN.BW    Util%
+  ----------------------------------------------------------------------------------------------------------------------------
+  pe-local-hbm               c0.pe0->c0.slice0              141.00     2.0  128.0  0.00   1.4%  90.8%     232.40      256.0    90.8%
+  pe-same-half-hbm           c0.pe0->c0.slice1              147.87     4.0  128.0  0.03   2.7%  86.6%     221.60      256.0    86.6%
+  pe-cross-half-hbm          c0.pe0->c0.slice4              161.17    10.0  128.0  0.09   6.2%  79.4%     203.31      256.0    79.4%
+  pe-cross-cube-hbm-best     c0.pe0->c1.slice0              330.52    30.0  256.0  0.01   9.1%  77.5%      99.14      128.0    77.5%
+  pe-cross-cube-hbm-worst    c0.pe0->c15.slice0             677.12   180.0  256.0  0.06  26.6%  37.8%      48.39      128.0    37.8%
+  * Local BN: 256.0 GB/s, Remote BN: 256.0 GB/s
+  [v] Cross-cube best < worst: PASS  (330.52ns < 677.12ns)
+
+  BW Saturation (Util% by data size):
+  Case                           4KB    16KB    64KB   256KB     1MB
+  ------------------------------------------------------------------
+  pe-local-hbm                 88.9%   97.0%   99.2%   99.8%  100.0%
+  pe-same-half-hbm             79.9%   94.1%   98.5%   99.6%   99.9%
+  pe-cross-half-hbm            61.3%   86.4%   96.2%   99.0%   99.8%
+  pe-cross-cube-hbm-best       51.6%   81.0%   94.5%   98.6%   99.6%
+  pe-cross-cube-hbm-worst      15.1%   41.6%   74.0%   91.9%   97.8%
+
+============================================================
diff --git a/docs/report/1H-codesign-paper/sections/02-platform.tex b/docs/report/1H-codesign-paper/sections/02-platform.tex
index 4ccc503..cee8d71 100644
--- a/docs/report/1H-codesign-paper/sections/02-platform.tex
+++ b/docs/report/1H-codesign-paper/sections/02-platform.tex
@@ -8,7 +8,7 @@ execution model it presents to a kernel writer, how its latency model
 turns that execution into a number, and the concrete hardware
 configuration used for every experiment that follows.
 
-\subsection{Why KernBench: source-level kernels without a software stack}
+\subsection{Why KernBench}
 \label{sec:why}
 
 In a production end-to-end (E2E) stack, kernel performance is entangled
@@ -55,7 +55,15 @@ physical distance and bandwidth.}
 Each CUBE contains eight PEs, shared SRAM, HBM controllers, an
 \textsf{M\_CPU} control processor, and an intra-CUBE router mesh
 (Fig.~\ref{fig:cube-arch}). Together these components form the
-execution substrate for all kernels evaluated in this report.
+execution substrate for all kernels evaluated in this report. This
+organization reflects the memory-centric nature of AHBM: each PE is
+paired with a dedicated slice of HBM bandwidth and local on-PE
+storage (TCM), so compute lives next to the data it consumes rather
+than fetching it through a far-away memory controller. The platform's
+performance question is therefore not ``how many FLOPs can the chip
+do'' but ``how well can a kernel keep each compute engine fed from
+its locally-attached memory while moving the unavoidable traffic
+between PEs efficiently.''
 
 \begin{figure}[t]
 \centering
@@ -195,7 +203,10 @@ collective engines hold the request for their service time before
 releasing it downstream. Each of these is attached to a specific node
 or edge in the graph; together they make up the entire latency budget.
 
-\paragraph{Congestion: where bottlenecks emerge.} The simulator's
+\subsubsection{Congestion and contention modeling}
+\label{sec:congestion}
+
+The simulator's
 sharpness comes from how it models contention for those nodes and
 edges. \emph{Every directed edge has a FIFO}: an arriving flit takes
 its bandwidth-limited transfer time on top of whatever earlier flits
@@ -215,9 +226,11 @@ it reveals where the real bottlenecks form and which hardware levers
 actually relieve them---which is exactly the question the codesign
 work in this report turns on.
 
-\paragraph{Control-plane (issue) cost model.} The cost of \emph{issuing}
-a command is modelled structurally rather than with a per-operation
-calibration table. The PE control processor charges, per command,
+\paragraph{Command dispatch overhead model.} The cost incurred by
+the \textsf{PE\_CPU} when it dispatches a command to one of the
+accelerator engines is modelled structurally rather than with a
+per-operation calibration table. The \textsf{PE\_CPU} charges, per
+command,
 \[
   d_{\text{cmd}} = \textsf{FIXED} + b_{\text{logical}} \cdot R,
 \]
@@ -267,14 +280,92 @@ hardware--software design trade-offs (tiling A vs.\ B, topology X
 vs.\ Y, with vs.\ without composite command, mesh vs.\ torus) that
 are the primary objective of this work.
 
+A third source of confidence comes from directly probing the
+simulator's per-traversal behaviour. Running \texttt{kernbench probe}
+on the modelled topology issues a sequence of PE-to-HBM DMA reads at
+progressively greater hop distances and reports the per-component
+overhead, per-edge serialization, and per-PC drain that the model
+charges (Table~\ref{tab:probe-pe-dma}). Three properties stand out.
+First, the reported latency increases \emph{monotonically} with hop
+count---from \SI{141}{\nano\second} at the local HBM slice to
+\SI{677}{\nano\second} at the worst-case remote-CUBE slice---with the
+increment per added hop matching the per-router overhead and the
+UCIe-link cost in Table~\ref{tab:hw}. Second, the bandwidth-saturation
+curves track the wire's serialization model: at \SI{1}{\mebi\byte}
+transfers the local PE DMA reaches \SI{100}{\percent} of the per-edge
+bandwidth limit, while the longest cross-CUBE path saturates at
+\SI{97.8}{\percent}---exactly the gap that the per-edge propagation
+and per-router overhead model would predict. Third, the simulator
+passes the internal-consistency invariants the probe builds in
+(monotonic hop progression; D2H reads at least as long as the
+equivalent H2D writes because of the reverse-path acknowledgement;
+cross-CUBE best less than cross-CUBE worst). These are properties
+that hold \emph{only} when the underlying graph traversal, FIFO
+contention, and propagation models are internally
+self-consistent---a model error in any of them would surface as a
+non-monotonic or under-utilising curve here long before it polluted a
+kernel-level measurement.
+
+\begin{table}[t]
+\centering
+\caption{PE\,$\to$\,HBM DMA latency probe at varying hop distances
+(\SI{32}{\kibi\byte} transfer; output captured from \texttt{kernbench
+probe}). \emph{Util\%} is the achieved bandwidth as a fraction of the
+path's bottleneck-edge bandwidth.}
+\label{tab:probe-pe-dma}
+\small
+\begin{tabular}{@{}lrrr@{}}
+\toprule
+Case & Latency~(\si{\nano\second}) & Util\% (\,32\,KiB) & Util\% (\,1\,MiB) \\
+\midrule
+PE\,$\to$\,local HBM             & 141.0 & 90.8 & 100.0 \\
+PE\,$\to$\,same-half HBM         & 147.9 & 86.6 & ~99.9 \\
+PE\,$\to$\,cross-half HBM        & 161.2 & 79.4 & ~99.8 \\
+PE\,$\to$\,cross-CUBE (best)     & 330.5 & 77.5 & ~99.6 \\
+PE\,$\to$\,cross-CUBE (worst)    & 677.1 & 37.8 & ~97.8 \\
+\bottomrule
+\end{tabular}
+\end{table}
+
 \subsection{Modeled hardware configuration}
 \label{sec:hw}
 
-Table~\ref{tab:hw} summarizes the hardware configuration used for
-every experiment in this report. It is read directly from the
-simulator's topology description; per-experiment workload parameters
-(matrix shapes, collective sizes, sequence lengths) are stated in
-their respective sections rather than here.
+Table~\ref{tab:hw} summarizes the hardware configuration
+used throughout this report. The intent of this
+configuration is not to model a specific product, but to
+represent a realistic memory-centric accelerator and to
+provide a consistent baseline for evaluating hardware--
+software co-design mechanisms.
+
+The compute capability within each CUBE is provisioned
+such that inference workloads can effectively saturate
+the available HBM bandwidth. The aggregate compute
+throughput is therefore balanced against memory-system
+bandwidth rather than being intentionally over- or
+under-provisioned. HBM bandwidth is distributed evenly
+across the PEs within a CUBE, with each PE responsible
+for servicing approximately one-eighth of the CUBE's
+memory bandwidth through its dedicated HBM channels.
+
+The on-chip interconnect is configured using bandwidth
+and latency parameters representative of commercially
+available mesh-network IPs. The goal is not to study a
+particular NoC implementation, but rather to evaluate
+kernel behavior under a realistic baseline communication
+fabric.
+
+For die-to-die communication, UCIe-A bandwidth
+characteristics are used as the reference point for
+inter-CUBE links. Inter-SIP communication is modeled
+using PCIe-class links. Together, these assumptions
+provide a representative communication hierarchy for
+evaluating collective communication and distributed
+kernel execution.
+
+Unless otherwise stated, all experiments use this
+configuration. Workload-specific parameters such as
+matrix dimensions, sequence lengths, and collective
+payload sizes are introduced in their respective sections.
 
 \begin{table}[t]
 \centering
diff --git a/docs/report/1H-codesign-paper/sections/04-allreduce.tex b/docs/report/1H-codesign-paper/sections/04-allreduce.tex
index cc65c28..b63c210 100644
--- a/docs/report/1H-codesign-paper/sections/04-allreduce.tex
+++ b/docs/report/1H-codesign-paper/sections/04-allreduce.tex
@@ -52,11 +52,11 @@ per-PE payload. Lower is better; the torus wins at every size.}
 \toprule
 \textbf{Bytes/PE} & \textbf{2D mesh} & \textbf{Ring 1D} & \textbf{2D torus} \\
 \midrule
-256     & 2667  & 2365  & 1701 \\
-4{,}096  & 4450  & 4082  & 3038 \\
-16{,}384 & 8900  & 8217  & 6403 \\
-65{,}536 & 26705 & 24766 & 19865 \\
-98{,}304 & 38574 & 35798 & 28840 \\
+256     & 4189  & 3883  & 2957 \\
+4{,}096  & 5566  & 5240  & 4031 \\
+16{,}384 & 10016 & 9376  & 7396 \\
+65{,}536 & 27821 & 25925 & 20858 \\
+98{,}304 & 39690 & 36957 & 29833 \\
 \bottomrule
 \end{tabular}
 \end{table}
@@ -78,9 +78,9 @@ achievable-kernel number and a full end-to-end-stack number.}
 \centering
 \includegraphics[width=\linewidth]{allreduce_buffer_kind.png}
 \caption{Effect of IPCQ staging-buffer placement (2D torus). At
-\SI{64}{\kibi\byte}/PE, TCM staging (\SI{19865}{\nano\second}) beats HBM
-(\SI{23081}{\nano\second}) by \textasciitilde\SI{14}{\percent} and SRAM
-(\SI{32201}{\nano\second}) by \textasciitilde\SI{38}{\percent}; at small
+\SI{64}{\kibi\byte}/PE, TCM staging (\SI{20858}{\nano\second}) beats HBM
+(\SI{24074}{\nano\second}) by \textasciitilde\SI{13}{\percent} and SRAM
+(\SI{33194}{\nano\second}) by \textasciitilde\SI{37}{\percent}; at small
 payloads the three are indistinguishable.}
 \label{fig:allreduce-buf}
 \end{figure}
diff --git a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2DMesh_6SiP_2x3.png b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2DMesh_6SiP_2x3.png
index 45d0b2c..b2bc945 100644
Binary files a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2DMesh_6SiP_2x3.png and b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2DMesh_6SiP_2x3.png differ
diff --git a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3.png b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3.png
index eac4f1f..b236535 100644
Binary files a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3.png and b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3.png differ
diff --git a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3_with_TCM_SRAM_HBM.csv b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3_with_TCM_SRAM_HBM.csv
index 013b00d..bef7db7 100644
--- a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3_with_TCM_SRAM_HBM.csv
+++ b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3_with_TCM_SRAM_HBM.csv
@@ -1,13 +1,13 @@
-buffer_kind,sip_topology,n_sips,n_elem,bytes_per_pe,latency_ns
-hbm,torus_2d,6,128,256,2120.040000000012
-hbm,torus_2d,6,1024,2048,2717.2783333333473
-hbm,torus_2d,6,8192,16384,7315.184999999989
-hbm,torus_2d,6,32768,65536,23081.26500000037
-sram,torus_2d,6,128,256,2060.040000000012
-sram,torus_2d,6,1024,2048,2909.2783333333473
-sram,torus_2d,6,8192,16384,9523.184999999869
-sram,torus_2d,6,32768,65536,32201.265000000385
-tcm,torus_2d,6,128,256,1964.040000000012
-tcm,torus_2d,6,1024,2048,2477.2783333333473
-tcm,torus_2d,6,8192,16384,6403.185000000109
-tcm,torus_2d,6,32768,65536,19865.265000000378
+buffer_kind,sip_topology,n_sips,n_elem,bytes_per_pe,latency_ns
+hbm,torus_2d,6,128,256,3113.040000000012
+hbm,torus_2d,6,1024,2048,3710.2783333333527
+hbm,torus_2d,6,8192,16384,8308.184999999929
+hbm,torus_2d,6,32768,65536,24074.26500000037
+sram,torus_2d,6,128,256,3053.040000000012
+sram,torus_2d,6,1024,2048,3902.2783333333573
+sram,torus_2d,6,8192,16384,10516.18499999987
+sram,torus_2d,6,32768,65536,33194.265000000385
+tcm,torus_2d,6,128,256,2957.040000000012
+tcm,torus_2d,6,1024,2048,3470.2783333333527
+tcm,torus_2d,6,8192,16384,7396.18499999999
+tcm,torus_2d,6,32768,65536,20858.265000000378
diff --git a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3_with_TCM_SRAM_HBM.png b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3_with_TCM_SRAM_HBM.png
index 19d4cc2..8fb6a71 100644
Binary files a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3_with_TCM_SRAM_HBM.png and b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_2Dtorus_6SiP_2x3_with_TCM_SRAM_HBM.png differ
diff --git a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_Ring1D_6SiP_1x6.png b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_Ring1D_6SiP_1x6.png
index 1bb1acc..5bf7b4f 100644
Binary files a/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_Ring1D_6SiP_1x6.png and b/src/kernbench/benches/1H_milestone_output/ccl/AllReduce_LRAB_Ring1D_6SiP_1x6.png differ
diff --git a/src/kernbench/benches/1H_milestone_output/ccl/comparison_mesh_vs_ring_vs_2DTorus_vs_theoretical_vs_fsim.png b/src/kernbench/benches/1H_milestone_output/ccl/comparison_mesh_vs_ring_vs_2DTorus_vs_theoretical_vs_fsim.png
index 229dbd3..3475f3b 100644
Binary files a/src/kernbench/benches/1H_milestone_output/ccl/comparison_mesh_vs_ring_vs_2DTorus_vs_theoretical_vs_fsim.png and b/src/kernbench/benches/1H_milestone_output/ccl/comparison_mesh_vs_ring_vs_2DTorus_vs_theoretical_vs_fsim.png differ
diff --git a/src/kernbench/benches/1H_milestone_output/ccl/summary.csv b/src/kernbench/benches/1H_milestone_output/ccl/summary.csv
index 5ecd70a..a701187 100644
--- a/src/kernbench/benches/1H_milestone_output/ccl/summary.csv
+++ b/src/kernbench/benches/1H_milestone_output/ccl/summary.csv
@@ -1,37 +1,37 @@
-algorithm,sip_topology,n_sips,n_elem,bytes_per_pe,bytes_per_sip,latency_ns
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,8,16,256,2666.552500000015
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,32,64,1024,2747.7400000000152
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,64,128,2048,2855.990000000018
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,128,256,4096,3072.490000000019
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,512,1024,16384,3337.1133333333582
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,1024,2048,32768,3708.0333333333692
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,2048,4096,65536,4449.873333333393
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,4096,8192,131072,5933.020000000124
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,8192,16384,262144,8900.379999999863
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,16384,32768,524288,14835.099999999224
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,32768,65536,1048576,26704.540000000765
-lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,49152,98304,1572864,38573.97999999701
-lrab_hierarchical_allreduce,ring_1d,6,8,16,256,2365.255833333347
-lrab_hierarchical_allreduce,ring_1d,6,32,64,1024,2436.9433333333473
-lrab_hierarchical_allreduce,ring_1d,6,64,128,2048,2532.526666666683
-lrab_hierarchical_allreduce,ring_1d,6,128,256,4096,2723.693333333349
-lrab_hierarchical_allreduce,ring_1d,6,512,1024,16384,3048.635000000021
-lrab_hierarchical_allreduce,ring_1d,6,1024,2048,32768,3393.4016666666957
-lrab_hierarchical_allreduce,ring_1d,6,2048,4096,65536,4082.401666666714
-lrab_hierarchical_allreduce,ring_1d,6,4096,8192,131072,5458.80166666677
-lrab_hierarchical_allreduce,ring_1d,6,8192,16384,262144,8216.934999999943
-lrab_hierarchical_allreduce,ring_1d,6,16384,32768,524288,13733.201666665835
-lrab_hierarchical_allreduce,ring_1d,6,32768,65536,1048576,24765.73500000064
-lrab_hierarchical_allreduce,ring_1d,6,49152,98304,1572864,35798.268333331536
-lrab_hierarchical_allreduce,torus_2d,6,8,16,256,1700.6025000000095
-lrab_hierarchical_allreduce,torus_2d,6,32,64,1024,1753.2900000000102
-lrab_hierarchical_allreduce,torus_2d,6,64,128,2048,1823.540000000012
-lrab_hierarchical_allreduce,torus_2d,6,128,256,4096,1964.040000000012
-lrab_hierarchical_allreduce,torus_2d,6,512,1024,16384,2196.8183333333463
-lrab_hierarchical_allreduce,torus_2d,6,1024,2048,32768,2477.2783333333473
-lrab_hierarchical_allreduce,torus_2d,6,2048,4096,65536,3038.1983333333583
-lrab_hierarchical_allreduce,torus_2d,6,4096,8192,131072,4159.5050000000665
-lrab_hierarchical_allreduce,torus_2d,6,8192,16384,262144,6403.185000000109
-lrab_hierarchical_allreduce,torus_2d,6,16384,32768,524288,10890.5449999995
-lrab_hierarchical_allreduce,torus_2d,6,32768,65536,1048576,19865.265000000378
-lrab_hierarchical_allreduce,torus_2d,6,49152,98304,1572864,28839.98500000059
+algorithm,sip_topology,n_sips,n_elem,bytes_per_pe,bytes_per_sip,latency_ns
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,8,16,256,3782.5525000000202
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,32,64,1024,3863.7400000000207
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,64,128,2048,3971.9900000000216
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,128,256,4096,4188.4900000000225
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,512,1024,16384,4453.113333333365
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,1024,2048,32768,4824.033333333375
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,2048,4096,65536,5565.873333333401
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,4096,8192,131072,7049.020000000062
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,8192,16384,262144,10016.379999999745
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,16384,32768,524288,15951.099999999256
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,32768,65536,1048576,27820.540000000765
+lrab_hierarchical_allreduce,mesh_2d_no_wrap,6,49152,98304,1572864,39689.97999999693
+lrab_hierarchical_allreduce,ring_1d,6,8,16,256,3524.2558333333504
+lrab_hierarchical_allreduce,ring_1d,6,32,64,1024,3595.943333333351
+lrab_hierarchical_allreduce,ring_1d,6,64,128,2048,3691.5266666666857
+lrab_hierarchical_allreduce,ring_1d,6,128,256,4096,3882.6933333333527
+lrab_hierarchical_allreduce,ring_1d,6,512,1024,16384,4207.101666666693
+lrab_hierarchical_allreduce,ring_1d,6,1024,2048,32768,4550.801666666699
+lrab_hierarchical_allreduce,ring_1d,6,2048,4096,65536,5240.335000000055
+lrab_hierarchical_allreduce,ring_1d,6,4096,8192,131072,6617.801666666763
+lrab_hierarchical_allreduce,ring_1d,6,8192,16384,262144,9375.934999999827
+lrab_hierarchical_allreduce,ring_1d,6,16384,32768,524288,14892.201666666035
+lrab_hierarchical_allreduce,ring_1d,6,32768,65536,1048576,25924.735000000648
+lrab_hierarchical_allreduce,ring_1d,6,49152,98304,1572864,36957.268333330976
+lrab_hierarchical_allreduce,torus_2d,6,8,16,256,2693.6025000000113
+lrab_hierarchical_allreduce,torus_2d,6,32,64,1024,2746.290000000012
+lrab_hierarchical_allreduce,torus_2d,6,64,128,2048,2816.5400000000127
+lrab_hierarchical_allreduce,torus_2d,6,128,256,4096,2957.040000000012
+lrab_hierarchical_allreduce,torus_2d,6,512,1024,16384,3189.81833333335
+lrab_hierarchical_allreduce,torus_2d,6,1024,2048,32768,3470.2783333333527
+lrab_hierarchical_allreduce,torus_2d,6,2048,4096,65536,4031.1983333333665
+lrab_hierarchical_allreduce,torus_2d,6,4096,8192,131072,5152.5050000000665
+lrab_hierarchical_allreduce,torus_2d,6,8192,16384,262144,7396.18499999999
+lrab_hierarchical_allreduce,torus_2d,6,16384,32768,524288,11883.544999999496
+lrab_hierarchical_allreduce,torus_2d,6,32768,65536,1048576,20858.265000000378
+lrab_hierarchical_allreduce,torus_2d,6,49152,98304,1572864,29832.98500000003
diff --git a/src/kernbench/benches/1H_milestone_output/ccl/topology.png b/src/kernbench/benches/1H_milestone_output/ccl/topology.png
index 40e8719..1990768 100644
Binary files a/src/kernbench/benches/1H_milestone_output/ccl/topology.png and b/src/kernbench/benches/1H_milestone_output/ccl/topology.png differ
diff --git a/src/kernbench/benches/1H_milestone_output/gemm/gemm_mac_utilization_measured.png b/src/kernbench/benches/1H_milestone_output/gemm/gemm_mac_utilization_measured.png
index a896aaa..438d161 100644
Binary files a/src/kernbench/benches/1H_milestone_output/gemm/gemm_mac_utilization_measured.png and b/src/kernbench/benches/1H_milestone_output/gemm/gemm_mac_utilization_measured.png differ
diff --git a/src/kernbench/benches/1H_milestone_output/gemm/gemm_mac_utilization_theoretical_vs_measured.png b/src/kernbench/benches/1H_milestone_output/gemm/gemm_mac_utilization_theoretical_vs_measured.png
index c7075c7..de6e96b 100644
Binary files a/src/kernbench/benches/1H_milestone_output/gemm/gemm_mac_utilization_theoretical_vs_measured.png and b/src/kernbench/benches/1H_milestone_output/gemm/gemm_mac_utilization_theoretical_vs_measured.png differ
diff --git a/src/kernbench/benches/1H_milestone_output/gemm/gemm_stage_breakdown.png b/src/kernbench/benches/1H_milestone_output/gemm/gemm_stage_breakdown.png
index bd82b68..c1201a2 100644
Binary files a/src/kernbench/benches/1H_milestone_output/gemm/gemm_stage_breakdown.png and b/src/kernbench/benches/1H_milestone_output/gemm/gemm_stage_breakdown.png differ
diff --git a/src/kernbench/benches/1H_milestone_output/gemm/gemm_sweep.json b/src/kernbench/benches/1H_milestone_output/gemm/gemm_sweep.json
index 910306a..69eb131 100644
--- a/src/kernbench/benches/1H_milestone_output/gemm/gemm_sweep.json
+++ b/src/kernbench/benches/1H_milestone_output/gemm/gemm_sweep.json
@@ -33,7 +33,7 @@
       "bytes_hbm": 6144,
       "arith_intensity": 10.666666666666666,
       "tile_count_expected": 1,
-      "sim_wall_clock_s": 1.64,
+      "sim_wall_clock_s": 0.297,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -100,7 +100,7 @@
       "bytes_hbm": 6144,
       "arith_intensity": 10.666666666666666,
       "tile_count_expected": 1,
-      "sim_wall_clock_s": 0.696,
+      "sim_wall_clock_s": 0.239,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -167,7 +167,7 @@
       "bytes_hbm": 6144,
       "arith_intensity": 10.666666666666666,
       "tile_count_expected": 1,
-      "sim_wall_clock_s": 0.605,
+      "sim_wall_clock_s": 0.243,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -234,7 +234,7 @@
       "bytes_hbm": 10240,
       "arith_intensity": 12.8,
       "tile_count_expected": 1,
-      "sim_wall_clock_s": 0.599,
+      "sim_wall_clock_s": 0.427,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -301,7 +301,7 @@
       "bytes_hbm": 10240,
       "arith_intensity": 12.8,
       "tile_count_expected": 1,
-      "sim_wall_clock_s": 0.622,
+      "sim_wall_clock_s": 0.336,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -368,7 +368,7 @@
       "bytes_hbm": 10240,
       "arith_intensity": 12.8,
       "tile_count_expected": 1,
-      "sim_wall_clock_s": 0.63,
+      "sim_wall_clock_s": 0.237,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -435,7 +435,7 @@
       "bytes_hbm": 18432,
       "arith_intensity": 14.222222222222221,
       "tile_count_expected": 2,
-      "sim_wall_clock_s": 0.618,
+      "sim_wall_clock_s": 0.322,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -502,7 +502,7 @@
       "bytes_hbm": 18432,
       "arith_intensity": 14.222222222222221,
       "tile_count_expected": 2,
-      "sim_wall_clock_s": 0.642,
+      "sim_wall_clock_s": 0.247,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -569,7 +569,7 @@
       "bytes_hbm": 18432,
       "arith_intensity": 14.222222222222221,
       "tile_count_expected": 2,
-      "sim_wall_clock_s": 0.769,
+      "sim_wall_clock_s": 0.247,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -636,7 +636,7 @@
       "bytes_hbm": 49152,
       "arith_intensity": 21.333333333333332,
       "tile_count_expected": 8,
-      "sim_wall_clock_s": 0.649,
+      "sim_wall_clock_s": 0.359,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -703,7 +703,7 @@
       "bytes_hbm": 49152,
       "arith_intensity": 21.333333333333332,
       "tile_count_expected": 8,
-      "sim_wall_clock_s": 0.639,
+      "sim_wall_clock_s": 0.368,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -770,7 +770,7 @@
       "bytes_hbm": 49152,
       "arith_intensity": 21.333333333333332,
       "tile_count_expected": 8,
-      "sim_wall_clock_s": 0.684,
+      "sim_wall_clock_s": 0.241,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -837,7 +837,7 @@
       "bytes_hbm": 395264,
       "arith_intensity": 15.917098445595855,
       "tile_count_expected": 48,
-      "sim_wall_clock_s": 0.623,
+      "sim_wall_clock_s": 0.318,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -904,7 +904,7 @@
       "bytes_hbm": 395264,
       "arith_intensity": 15.917098445595855,
       "tile_count_expected": 48,
-      "sim_wall_clock_s": 0.763,
+      "sim_wall_clock_s": 0.295,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -971,7 +971,7 @@
       "bytes_hbm": 395264,
       "arith_intensity": 15.917098445595855,
       "tile_count_expected": 48,
-      "sim_wall_clock_s": 0.647,
+      "sim_wall_clock_s": 0.321,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -1038,7 +1038,7 @@
       "bytes_hbm": 36864,
       "arith_intensity": 7.111111111111111,
       "tile_count_expected": 8,
-      "sim_wall_clock_s": 0.637,
+      "sim_wall_clock_s": 0.219,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -1105,7 +1105,7 @@
       "bytes_hbm": 36864,
       "arith_intensity": 7.111111111111111,
       "tile_count_expected": 8,
-      "sim_wall_clock_s": 0.678,
+      "sim_wall_clock_s": 0.337,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -1172,7 +1172,7 @@
       "bytes_hbm": 36864,
       "arith_intensity": 7.111111111111111,
       "tile_count_expected": 8,
-      "sim_wall_clock_s": 0.66,
+      "sim_wall_clock_s": 0.356,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -1239,7 +1239,7 @@
       "bytes_hbm": 36864,
       "arith_intensity": 7.111111111111111,
       "tile_count_expected": 16,
-      "sim_wall_clock_s": 0.658,
+      "sim_wall_clock_s": 0.372,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -1306,7 +1306,7 @@
       "bytes_hbm": 36864,
       "arith_intensity": 7.111111111111111,
       "tile_count_expected": 16,
-      "sim_wall_clock_s": 0.646,
+      "sim_wall_clock_s": 0.245,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -1373,7 +1373,7 @@
       "bytes_hbm": 36864,
       "arith_intensity": 7.111111111111111,
       "tile_count_expected": 16,
-      "sim_wall_clock_s": 0.673,
+      "sim_wall_clock_s": 0.243,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -1440,7 +1440,7 @@
       "bytes_hbm": 1572864,
       "arith_intensity": 170.66666666666666,
       "tile_count_expected": 2048,
-      "sim_wall_clock_s": 0.727,
+      "sim_wall_clock_s": 0.357,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -1507,7 +1507,7 @@
       "bytes_hbm": 1572864,
       "arith_intensity": 170.66666666666666,
       "tile_count_expected": 2048,
-      "sim_wall_clock_s": 0.707,
+      "sim_wall_clock_s": 0.364,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,
@@ -1574,7 +1574,7 @@
       "bytes_hbm": 1572864,
       "arith_intensity": 170.66666666666666,
       "tile_count_expected": 2048,
-      "sim_wall_clock_s": 0.828,
+      "sim_wall_clock_s": 0.239,
       "engines": {
         "pe_dma": {
           "occupancy_ns": 16594.192,