- (Updated on December 20) The following table and screenshots provide details of Ariane133 GF12 implementation when AutoDMP is used to generate the macro placement.
<table>
<thead>
<tr>
<thcolspan="10">Ariane-GF12-68% AutoDMP [results are normalized as described <a href=“#GF12_Normalization”>here</a>]</th>
- (Updated on December 20) The following table and screenshots provide details of BlackParrot (Quad-Core) GF12 implementation when AutoDMP is used to generate the macro placement.
<table>
<thead>
<tr>
<thcolspan="10">BlackParrot-GF12-68% AutoDMP [results are normalized as described <a href=“#GF12_Normalization”>here</a>]</th>
- The following table and screenshots provide details of MemPool Group GF12 implementation when CMP is used to generate the macro placement.
- The following table and screenshots provide details of MemPool Group GF12 implementation when CMP is used to generate the macro placement.
<table>
<table>
<thead>
<thead>
...
@@ -5138,7 +5294,7 @@ We thank NVIDIA Research for access to AutoDMP, an autotuned DREAMPlace-based ma
...
@@ -5138,7 +5294,7 @@ We thank NVIDIA Research for access to AutoDMP, an autotuned DREAMPlace-based ma
<table>
<table>
<thead>
<thead>
<tr>
<tr>
<thcolspan="10">Ariane133-NG45-68%-1.3ns AutoDMP (<ahref="../../Flows/NanGate45/ariane133/README.md#flow-2-result-for-the-macro-placement-generated-by-cadence-concurrent-macro-placer">Link</a> to CMP result) (<ahref="../../Flows/NanGate45/ariane133/README.md#macro-placement-generated-by-circuit-training-ct">Link</a> to CT result)</th>
<thcolspan="10">Ariane133-NG45-68%-1.3ns AutoDMP (<ahref="../../Flows/NanGate45/ariane133/README.md#macro-placement-generated-by-circuit-training-ct">Link</a> to CT result) (<ahref="../../Flows/NanGate45/ariane133/README.md#flow-2-result-for-the-macro-placement-generated-by-cadence-concurrent-macro-placer">Link</a> to CMP result)</th>
</tr>
</tr>
</thead>
</thead>
<tbody>
<tbody>
...
@@ -5284,6 +5440,11 @@ We thank NVIDIA Research for access to AutoDMP, an autotuned DREAMPlace-based ma
...
@@ -5284,6 +5440,11 @@ We thank NVIDIA Research for access to AutoDMP, an autotuned DREAMPlace-based ma