@@ -145,43 +145,45 @@ <h1><a class="anchor" id="autotoc_md63"></a>
145145</ ul >
146146< table class ="markdownTable ">
147147< tr class ="markdownTableHead ">
148- < th class ="markdownTableHeadRight "> Hardware </ th > < th class ="markdownTableHeadRight "> </ th > < th class ="markdownTableHeadCenter "> Grind Time </ th > < th class ="markdownTableHeadLeft "> Compiler </ th > < th class ="markdownTableHeadLeft "> Computer </ th > </ tr >
148+ < th class ="markdownTableHeadRight "> Hardware </ th > < th class ="markdownTableHeadRight "> </ th > < th class ="markdownTableHeadRight "> Grind Time </ th > < th class ="markdownTableHeadLeft "> Compiler </ th > < th class ="markdownTableHeadLeft "> Computer </ th > </ tr >
149149< tr class ="markdownTableRowOdd ">
150- < td class ="markdownTableBodyRight "> NVIDIA GH200 (GPU only) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyCenter "> 0.32 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
150+ < td class ="markdownTableBodyRight "> NVIDIA GH200 (GPU only) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 0.32 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
151151< tr class ="markdownTableRowEven ">
152- < td class ="markdownTableBodyRight "> NVIDIA H100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyCenter "> 0.45 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
152+ < td class ="markdownTableBodyRight "> NVIDIA H100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 0.45 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
153153< tr class ="markdownTableRowOdd ">
154- < td class ="markdownTableBodyRight "> NVIDIA A100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyCenter "> 0.62 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
154+ < td class ="markdownTableBodyRight "> NVIDIA A100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 0.62 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
155155< tr class ="markdownTableRowEven ">
156- < td class ="markdownTableBodyRight "> NVIDIA V100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyCenter "> 0.99 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
156+ < td class ="markdownTableBodyRight "> NVIDIA V100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 0.99 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
157157< tr class ="markdownTableRowOdd ">
158- < td class ="markdownTableBodyRight "> NVIDIA A30 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyCenter "> 1.06 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
158+ < td class ="markdownTableBodyRight "> NVIDIA A30 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 1.06 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
159159< tr class ="markdownTableRowEven ">
160- < td class ="markdownTableBodyRight "> AMD MI250X </ td > < td class ="markdownTableBodyRight "> 1 < b > GCD</ b > </ td > < td class ="markdownTableBodyCenter "> 1.09 </ td > < td class ="markdownTableBodyLeft "> CCE 16.0.1 </ td > < td class ="markdownTableBodyLeft "> OLCF Frontier </ td > </ tr >
160+ < td class ="markdownTableBodyRight "> AMD MI250X </ td > < td class ="markdownTableBodyRight "> 1 < b > GCD</ b > </ td > < td class ="markdownTableBodyRight "> 1.09 </ td > < td class ="markdownTableBodyLeft "> CCE 16.0.1 </ td > < td class ="markdownTableBodyLeft "> OLCF Frontier </ td > </ tr >
161161< tr class ="markdownTableRowOdd ">
162- < td class ="markdownTableBodyRight "> AMD MI100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyCenter "> 1.38 </ td > < td class ="markdownTableBodyLeft "> CCE 16.0.1 </ td > < td class ="markdownTableBodyLeft "> Cray internal system </ td > </ tr >
162+ < td class ="markdownTableBodyRight "> AMD MI100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 1.38 </ td > < td class ="markdownTableBodyLeft "> CCE 16.0.1 </ td > < td class ="markdownTableBodyLeft "> Cray internal system </ td > </ tr >
163163< tr class ="markdownTableRowEven ">
164- < td class ="markdownTableBodyRight "> NVIDIA A40 (SP GPU) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyCenter "> 3.3 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
164+ < td class ="markdownTableBodyRight "> NVIDIA A40 (SP GPU) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 3.3 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
165165< tr class ="markdownTableRowOdd ">
166- < td class ="markdownTableBodyRight "> NVIDIA RTX6000 (SP GPU) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyCenter "> 3.9 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
166+ < td class ="markdownTableBodyRight "> NVIDIA RTX6000 (SP GPU) </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 3.9 </ td > < td class ="markdownTableBodyLeft "> NVHPC 22.11 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
167167< tr class ="markdownTableRowEven ">
168- < td class ="markdownTableBodyRight "> Apple M1 Max </ td > < td class ="markdownTableBodyRight "> 8/10 cores </ td > < td class ="markdownTableBodyCenter "> 72 </ td > < td class ="markdownTableBodyLeft "> GNU 14.1.0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
168+ < td class ="markdownTableBodyRight "> Apple M1 Max </ td > < td class ="markdownTableBodyRight "> 8/10 cores </ td > < td class ="markdownTableBodyRight "> 72 </ td > < td class ="markdownTableBodyLeft "> GNU 14.1.0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
169169< tr class ="markdownTableRowOdd ">
170- < td class ="markdownTableBodyRight "> AMD EPYC 9534 (Genoa) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyCenter "> 96 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
170+ < td class ="markdownTableBodyRight "> AMD EPYC 9534 (Genoa) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 96 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
171171< tr class ="markdownTableRowEven ">
172- < td class ="markdownTableBodyRight "> AMD EPYC 7763 (Milan) </ td > < td class ="markdownTableBodyRight "> 24/64 cores </ td > < td class ="markdownTableBodyCenter "> 108 </ td > < td class ="markdownTableBodyLeft "> GNU 11.4.0 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
172+ < td class ="markdownTableBodyRight "> AMD EPYC 7763 (Milan) </ td > < td class ="markdownTableBodyRight "> 24/64 cores </ td > < td class ="markdownTableBodyRight "> 108 </ td > < td class ="markdownTableBodyLeft "> GNU 11.4.0 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
173173< tr class ="markdownTableRowOdd ">
174- < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8462Y+ (Sapphire Rapids) </ td > < td class ="markdownTableBodyRight "> 16/32 cores </ td > < td class ="markdownTableBodyCenter "> 110 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
174+ < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8462Y+ (Sapphire Rapids) </ td > < td class ="markdownTableBodyRight "> 16/32 cores </ td > < td class ="markdownTableBodyRight "> 110 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
175175< tr class ="markdownTableRowEven ">
176- < td class ="markdownTableBodyRight "> Intel Xeon Gold 6454S (Sapphire Rapids) </ td > < td class ="markdownTableBodyRight "> 16/32 cores </ td > < td class ="markdownTableBodyCenter "> 111 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
176+ < td class ="markdownTableBodyRight "> Intel Xeon Gold 6454S (Sapphire Rapids) </ td > < td class ="markdownTableBodyRight "> 16/32 cores </ td > < td class ="markdownTableBodyRight "> 111 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
177177< tr class ="markdownTableRowOdd ">
178- < td class ="markdownTableBodyRight "> NVIDIA Grace CPU (Arm, Neoverse V2) </ td > < td class ="markdownTableBodyRight "> 18/72 cores </ td > < td class ="markdownTableBodyCenter "> 116 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
178+ < td class ="markdownTableBodyRight "> NVIDIA Grace CPU (Arm, Neoverse V2) </ td > < td class ="markdownTableBodyRight "> 18/72 cores </ td > < td class ="markdownTableBodyRight "> 116 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
179179< tr class ="markdownTableRowEven ">
180- < td class ="markdownTableBodyRight "> AMD EPYC 7452 (Rome) </ td > < td class ="markdownTableBodyRight "> 16/32 cores </ td > < td class ="markdownTableBodyCenter "> 126 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
180+ < td class ="markdownTableBodyRight "> AMD EPYC 7452 (Rome) </ td > < td class ="markdownTableBodyRight "> 16/32 cores </ td > < td class ="markdownTableBodyRight "> 126 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
181181< tr class ="markdownTableRowOdd ">
182- < td class ="markdownTableBodyRight "> AMD EPYC 7713 (Milan ) </ td > < td class ="markdownTableBodyRight "> 32/64 cores </ td > < td class ="markdownTableBodyCenter " > 137 </ td > < td class ="markdownTableBodyLeft "> GNU 12.1.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
182+ < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8352Y (Ice Lake ) </ td > < td class ="markdownTableBodyRight "> 12/32 cores </ td > < td class ="markdownTableBodyRight " > 128 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
183183< tr class ="markdownTableRowEven ">
184- < td class ="markdownTableBodyRight "> Intel Xeon Gold 6226 (Cascade Lake) </ td > < td class ="markdownTableBodyRight "> 12/12 cores </ td > < td class ="markdownTableBodyCenter "> 152 </ td > < td class ="markdownTableBodyLeft "> Intel oneAPI 2022.1 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
184+ < td class ="markdownTableBodyRight "> AMD EPYC 7713 (Milan) </ td > < td class ="markdownTableBodyRight "> 32/64 cores </ td > < td class ="markdownTableBodyRight "> 137 </ td > < td class ="markdownTableBodyLeft "> GNU 12.1.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
185+ < tr class ="markdownTableRowOdd ">
186+ < td class ="markdownTableBodyRight "> Intel Xeon Gold 6226 (Cascade Lake) </ td > < td class ="markdownTableBodyRight "> 12/12 cores </ td > < td class ="markdownTableBodyRight "> 152 </ td > < td class ="markdownTableBodyLeft "> Intel oneAPI 2022.1 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
185187</ table >
186188< p > < b > All grind times are in nanoseconds (ns) per grid point (gp) per equation (eq) per right-hand side (rhs) evaluation, so X ns/gp/eq/rhs. Lower is better.</ b > </ p >
187189< h1 > < a class ="anchor " id ="autotoc_md64 "> </ a >
0 commit comments