@@ -155,48 +155,45 @@ <h1><a class="anchor" id="autotoc_md63"></a>
155155< tr class ="markdownTableRowEven ">
156156< 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 ="markdownTableBodyRight "> 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 "> 1.1 </ 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 ="markdownTableBodyRight "> 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 "> 1.1 </ 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 ="markdownTableBodyRight "> 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 "> 1.4 </ 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 P100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 2.35 </ td > < td class ="markdownTableBodyLeft "> NVHPC 23.5 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
164+ < td class ="markdownTableBodyRight "> NVIDIA P100 </ td > < td class ="markdownTableBodyRight "> 1 GPU </ td > < td class ="markdownTableBodyRight "> 2.4 </ td > < td class ="markdownTableBodyLeft "> NVHPC 23.5 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
165165< tr class ="markdownTableRowOdd ">
166+ < td class ="markdownTableBodyRight "> AMD EPYC 9534 (Genoa) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 2.7 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
167+ < tr class ="markdownTableRowEven ">
166168< 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 >
169+ < tr class ="markdownTableRowOdd ">
170+ < td class ="markdownTableBodyRight "> NVIDIA Grace CPU (Arm, Neoverse V2) </ td > < td class ="markdownTableBodyRight "> 72/72 cores </ td > < td class ="markdownTableBodyRight "> 3.7 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
167171< tr class ="markdownTableRowEven ">
168172< 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 >
169173< tr class ="markdownTableRowOdd ">
170- < td class ="markdownTableBodyRight "> Apple M1 Max </ td > < td class ="markdownTableBodyRight "> 8/10 cores </ td > < td class ="markdownTableBodyRight "> 14.3 </ td > < td class ="markdownTableBodyLeft "> GNU 14.1 .0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
174+ < td class ="markdownTableBodyRight "> AMD EPYC 7763 (Milan) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 4.1 </ td > < td class ="markdownTableBodyLeft "> GNU 11.4 .0 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
171175< tr class ="markdownTableRowEven ">
172- < td class ="markdownTableBodyRight "> IBM Power9 </ td > < td class ="markdownTableBodyRight "> 20/21 cores </ td > < td class ="markdownTableBodyRight "> 21.2 </ td > < td class ="markdownTableBodyLeft "> GNU 9.1.0 </ td > < td class ="markdownTableBodyLeft "> OLCF Summit </ td > </ tr >
173- </ table >
174- < p > Processors To-do:</ p >
175- < table class ="markdownTable ">
176- < tr class ="markdownTableHead ">
177- < 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 >
176+ < td class ="markdownTableBodyRight "> AMD EPYC 7713 (Milan) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> 5.0 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
178177< tr class ="markdownTableRowOdd ">
179- < td class ="markdownTableBodyRight "> AMD EPYC 9534 (Genoa ) </ td > < td class ="markdownTableBodyRight "> 64/64 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
178+ < td class ="markdownTableBodyRight "> Intel Xeon Gold 6454S (Sapphire Rapids ) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 5.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
180179< tr class ="markdownTableRowEven ">
181- < td class ="markdownTableBodyRight "> AMD EPYC 7763 (Milan ) </ td > < td class ="markdownTableBodyRight "> 24/64 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> GNU 11.4 .0 </ td > < td class ="markdownTableBodyLeft "> NCSA Delta </ td > </ tr >
180+ < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8462Y+ (Sapphire Rapids ) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 6.2 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3 .0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
182181< tr class ="markdownTableRowOdd ">
183- < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8462Y+ (Sapphire Rapids ) </ td > < td class ="markdownTableBodyRight "> 16 /32 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
182+ < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8352Y (Ice Lake ) </ td > < td class ="markdownTableBodyRight "> 32 /32 cores </ td > < td class ="markdownTableBodyRight "> 6.6 </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
184183< tr class ="markdownTableRowEven ">
185- < td class ="markdownTableBodyRight "> Intel Xeon Gold 6454S (Sapphire Rapids ) </ td > < td class ="markdownTableBodyRight "> 16/32 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
184+ < td class ="markdownTableBodyRight "> Ampere Altra Max Q80-28 (Arm, Neoverse-N1 ) </ td > < td class ="markdownTableBodyRight "> 80/80 cores </ td > < td class ="markdownTableBodyRight "> 6.8 </ td > < td class ="markdownTableBodyLeft "> GNU 12.2.0 </ td > < td class ="markdownTableBodyLeft "> OLCF Wombat </ td > </ tr >
186185< tr class ="markdownTableRowOdd ">
187- < td class ="markdownTableBodyRight "> NVIDIA Grace CPU (Arm, Neoverse V2 ) </ td > < td class ="markdownTableBodyRight "> 18/72 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.1 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
186+ < td class ="markdownTableBodyRight "> AMD EPYC 7513 (Milan ) </ td > < td class ="markdownTableBodyRight "> 32/32 cores </ td > < td class ="markdownTableBodyRight "> 7.4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
188187< tr class ="markdownTableRowEven ">
189- < td class ="markdownTableBodyRight "> AMD EPYC 7452 (Rome) </ td > < td class ="markdownTableBodyRight "> 16 /32 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
188+ < td class ="markdownTableBodyRight "> AMD EPYC 7452 (Rome) </ td > < td class ="markdownTableBodyRight "> 32 /32 cores </ td > < td class ="markdownTableBodyRight "> 8.4 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3.0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
190189< tr class ="markdownTableRowOdd ">
191- < td class ="markdownTableBodyRight "> Intel Xeon Platinum 8352Y (Ice Lake) </ td > < td class ="markdownTableBodyRight "> 12/32 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> NVHPC 24.5 </ td > < td class ="markdownTableBodyLeft "> GT Rogues Gallery </ td > </ tr >
190+ < td class ="markdownTableBodyRight "> Apple M1 Max </ td > < td class ="markdownTableBodyRight "> 8/10 cores </ td > < td class ="markdownTableBodyRight "> 14 </ td > < td class ="markdownTableBodyLeft "> GNU 14.1.0 </ td > < td class ="markdownTableBodyLeft "> N/A </ td > </ tr >
192191< tr class ="markdownTableRowEven ">
193- < td class ="markdownTableBodyRight "> AMD EPYC 7713 (Milan ) </ td > < td class ="markdownTableBodyRight "> 32/64 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> GNU 12.1 .0 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
192+ < td class ="markdownTableBodyRight "> Intel Xeon Gold 6226 (Cascade Lake ) </ td > < td class ="markdownTableBodyRight "> 12/12 cores </ td > < td class ="markdownTableBodyRight "> 17 </ td > < td class ="markdownTableBodyLeft "> GNU 12.3 .0 </ td > < td class ="markdownTableBodyLeft "> GT ICE </ td > </ tr >
194193< tr class ="markdownTableRowOdd ">
195- < td class ="markdownTableBodyRight "> Intel Xeon Gold 6226 (Cascade Lake) </ td > < td class ="markdownTableBodyRight "> 12/12 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> Intel oneAPI 2022.1 </ td > < td class ="markdownTableBodyLeft "> GT Phoenix </ td > </ tr >
194+ < td class ="markdownTableBodyRight "> IBM Power9 </ td > < td class ="markdownTableBodyRight "> 20/21 cores </ td > < td class ="markdownTableBodyRight "> 21 </ td > < td class ="markdownTableBodyLeft "> GNU 9.1.0 </ td > < td class ="markdownTableBodyLeft "> OLCF Summit </ td > </ tr >
196195< tr class ="markdownTableRowEven ">
197- < td class ="markdownTableBodyRight "> Ampere Altra Max (Arm, Neoverse-N1) </ td > < td class ="markdownTableBodyRight "> 8/80 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> GNU 12.2.0 </ td > < td class ="markdownTableBodyLeft "> OLCF Wombat </ td > </ tr >
198- < tr class ="markdownTableRowOdd ">
199- < td class ="markdownTableBodyRight "> Intel Xeon E5-2650V4 (Broadwell) </ td > < td class ="markdownTableBodyRight "> 8/12 cores </ td > < td class ="markdownTableBodyRight "> n/a </ td > < td class ="markdownTableBodyLeft "> NVHPC 23.5 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
196+ < td class ="markdownTableBodyRight "> Intel Xeon E5-2650V4 (Broadwell) </ td > < td class ="markdownTableBodyRight "> 12/12 cores </ td > < td class ="markdownTableBodyRight "> 27 </ td > < td class ="markdownTableBodyLeft "> NVHPC 23.5 </ td > < td class ="markdownTableBodyLeft "> GT CSE Internal </ td > </ tr >
200197</ table >
201198< 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 >
202199< h1 > < a class ="anchor " id ="autotoc_md64 "> </ a >
0 commit comments