options

gmx_mpi - 2024-08-05 19:41:40 - MAQAO 2.20.7

Help is available by moving the cursor above any symbol or by checking MAQAO website.

Optimizer

Loop IDAnalysisPenalty Score
Loop 3476 - libgromacs_mpi.so.9.0.0+Execution Time: 12 % - Vectorization Ratio: 93.08 % - Vector Length Use: 86.63 %
Loop Computation Issues+256
+[SA] Presence of expensive FP instructions - Perform hoisting, change algorithm, use SVML or proper numerical library or perform value profiling (count the number of distinct input values). There are 64 issues (= instructions) costing 4 points each.256
Number of RCP instructions: 32
Number of RSQRT instructions: 32
Data Access Issues+39
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 17 issues (= instructions) costing 1 point each.17
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 14
[SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points.2
Vectorization Roadblocks+20
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
Inefficient Vectorization+19
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 17 issues (= instructions) costing 1 point each.17
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 14
[SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points.2
Loop 3602 - libgromacs_mpi.so.9.0.0+Execution Time: 8 % - Vectorization Ratio: 94.66 % - Vector Length Use: 88.17 %
Loop Computation Issues+256
+[SA] Presence of expensive FP instructions - Perform hoisting, change algorithm, use SVML or proper numerical library or perform value profiling (count the number of distinct input values). There are 64 issues (= instructions) costing 4 points each.256
Number of RCP instructions: 32
Number of RSQRT instructions: 32
Data Access Issues+37
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 15 issues (= instructions) costing 1 point each.15
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 12
[SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points.2
Vectorization Roadblocks+20
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
Inefficient Vectorization+17
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 15 issues (= instructions) costing 1 point each.15
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 12
[SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points.2
Loop 3480 - libgromacs_mpi.so.9.0.0+Execution Time: 3 % - Vectorization Ratio: 93.62 % - Vector Length Use: 87.68 %
Loop Computation Issues+256
+[SA] Presence of expensive FP instructions - Perform hoisting, change algorithm, use SVML or proper numerical library or perform value profiling (count the number of distinct input values). There are 64 issues (= instructions) costing 4 points each.256
Number of RCP instructions: 32
Number of RSQRT instructions: 32
Data Access Issues+39
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 17 issues (= instructions) costing 1 point each.17
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 14
[SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points.2
Vectorization Roadblocks+20
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
Inefficient Vectorization+19
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 17 issues (= instructions) costing 1 point each.17
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 14
[SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points.2
Loop 3606 - libgromacs_mpi.so.9.0.0+Execution Time: 2 % - Vectorization Ratio: 94.96 % - Vector Length Use: 88.85 %
Loop Computation Issues+256
+[SA] Presence of expensive FP instructions - Perform hoisting, change algorithm, use SVML or proper numerical library or perform value profiling (count the number of distinct input values). There are 64 issues (= instructions) costing 4 points each.256
Number of RCP instructions: 32
Number of RSQRT instructions: 32
Data Access Issues+37
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 15 issues (= instructions) costing 1 point each.15
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 12
[SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points.2
Vectorization Roadblocks+20
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
Inefficient Vectorization+17
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 15 issues (= instructions) costing 1 point each.15
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 12
[SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points.2
Loop 3483 - libgromacs_mpi.so.9.0.0+Execution Time: 2 % - Vectorization Ratio: 93.37 % - Vector Length Use: 89.22 %
Loop Computation Issues+384
+[SA] Presence of expensive FP instructions - Perform hoisting, change algorithm, use SVML or proper numerical library or perform value profiling (count the number of distinct input values). There are 96 issues (= instructions) costing 4 points each.384
Number of RCP instructions: 64
Number of RSQRT instructions: 32
Data Access Issues+43
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 21 issues (= instructions) costing 1 point each.21
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 18
[SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points.2
Vectorization Roadblocks+20
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
Inefficient Vectorization+23
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 21 issues (= instructions) costing 1 point each.21
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 18
[SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points.2
Loop 18915 - libgromacs_mpi.so.9.0.0+Execution Time: 1 % - Vectorization Ratio: 57.14 % - Vector Length Use: 45.46 %
Loop Computation Issues+2
[SA] Presence of a large number of scalar integer instructions - Simplify loop structure, perform loop splitting or perform unroll and jam. This issue costs 2 points.2
Control Flow Issues+84
[SA] Too many paths (78 paths) - Simplify control structure. There are 78 issues ( = paths) costing 1 point each with a malus of 4 points.82
[SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points.2
Data Access Issues+49
+[SA] Presence of expensive instructions (GATHER/SCATTER) - Use array restructuring. There are 4 issues (= instructions) costing 4 points each.16
Number of ZMM GATHER/SCATTER instructions: 4
+[SA] Presence of special instructions executing on a single port (COMPRESS/EXPAND, BLEND/MERGE, SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 31 issues (= instructions) costing 1 point each.31
Number of ZMM COMPRESS/EXPAND instructions: 2
Number of XMM BLEND/MERGE instructions: 1
Number of XMM SHUFFLE/PERM instructions: 6
Number of ZMM SHUFFLE/PERM instructions: 14
Number of XMM BROADCAST instructions: 1
Number of YMM BROADCAST instructions: 1
Number of ZMM BROADCAST instructions: 6
[SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points.2
Vectorization Roadblocks+84
[SA] Too many paths (78 paths) - Simplify control structure. There are 78 issues ( = paths) costing 1 point each with a malus of 4 points.82
[SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points.2
Inefficient Vectorization+49
[SA] Presence of expensive instructions (GATHER/SCATTER) - Use array restructuring. There are 4 issues (= instructions) costing 4 points each.16
+[SA] Presence of special instructions executing on a single port (COMPRESS/EXPAND, BLEND/MERGE, SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 31 issues (= instructions) costing 1 point each.31
Number of ZMM COMPRESS/EXPAND instructions: 2
Number of XMM BLEND/MERGE instructions: 1
Number of XMM SHUFFLE/PERM instructions: 6
Number of ZMM SHUFFLE/PERM instructions: 14
Number of XMM BROADCAST instructions: 1
Number of YMM BROADCAST instructions: 1
Number of ZMM BROADCAST instructions: 6
[SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points.2
Loop 3609 - libgromacs_mpi.so.9.0.0+Execution Time: 1 % - Vectorization Ratio: 93.33 % - Vector Length Use: 89.17 %
Loop Computation Issues+384
+[SA] Presence of expensive FP instructions - Perform hoisting, change algorithm, use SVML or proper numerical library or perform value profiling (count the number of distinct input values). There are 96 issues (= instructions) costing 4 points each.384
Number of RCP instructions: 64
Number of RSQRT instructions: 32
Data Access Issues+43
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 21 issues (= instructions) costing 1 point each.21
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 18
[SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points.2
Vectorization Roadblocks+20
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each.8
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 3 issues ( = indirect data accesses) costing 4 point each.12
Inefficient Vectorization+23
+[SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 21 issues (= instructions) costing 1 point each.21
Number of ZMM SHUFFLE/PERM instructions: 3
Number of ZMM BROADCAST instructions: 18
[SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points.2
Loop 5329 - libgromacs_mpi.so.9.0.0+Execution Time: 0 % - Vectorization Ratio: 87.21 % - Vector Length Use: 80.95 %
Control Flow Issues+4
[SA] Several paths (4 paths) - Simplify control structure or force the compiler to use masked instructions. There are 4 issues ( = paths) costing 1 point each.4
Data Access Issues+16
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 1 issues ( = data accesses) costing 2 point each.2
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 2 issues ( = indirect data accesses) costing 4 point each.8
+[SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 6 issues (= instructions) costing 1 point each.6
Number of ZMM BROADCAST instructions: 6
Vectorization Roadblocks+14
[SA] Several paths (4 paths) - Simplify control structure or force the compiler to use masked instructions. There are 4 issues ( = paths) costing 1 point each.4
[SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 1 issues ( = data accesses) costing 2 point each.2
[SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 2 issues ( = indirect data accesses) costing 4 point each.8
Inefficient Vectorization+6
+[SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 6 issues (= instructions) costing 1 point each.6
Number of ZMM BROADCAST instructions: 6
Loop 19123 - libgromacs_mpi.so.9.0.0+Execution Time: 0 % - Vectorization Ratio: 62.02 % - Vector Length Use: 19.86 %
Loop Computation Issues+2
[SA] Presence of a large number of scalar integer instructions - Simplify loop structure, perform loop splitting or perform unroll and jam. This issue costs 2 points.2
Control Flow Issues+321
[SA] Too many paths (315 paths) - Simplify control structure. There are 315 issues ( = paths) costing 1 point each with a malus of 4 points.319
[SA] Non innermost loop (InBetween) - Collapse loop with innermost ones. This issue costs 2 points.2
Data Access Issues+16
+[SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 14 issues (= instructions) costing 1 point each.14
Number of XMM BROADCAST instructions: 14
[SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points.2
Vectorization Roadblocks+321
[SA] Too many paths (315 paths) - Simplify control structure. There are 315 issues ( = paths) costing 1 point each with a malus of 4 points.319
[SA] Non innermost loop (InBetween) - Collapse loop with innermost ones. This issue costs 2 points.2
Inefficient Vectorization+16
+[SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 14 issues (= instructions) costing 1 point each.14
Number of XMM BROADCAST instructions: 14
[SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points.2
Loop 5212 - libgromacs_mpi.so.9.0.0+Execution Time: 0 % - Vectorization Ratio: 12.69 % - Vector Length Use: 11.37 %
Loop Computation Issues+2
[SA] Presence of a large number of scalar integer instructions - Simplify loop structure, perform loop splitting or perform unroll and jam. This issue costs 2 points.2
Control Flow Issues+2
[SA] Non innermost loop (InBetween) - Collapse loop with innermost ones. This issue costs 2 points.2
Data Access Issues+3
+[SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 1 issues (= instructions) costing 1 point each.1
Number of ZMM BROADCAST instructions: 1
[SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points.2
Vectorization Roadblocks+1002
[SA] Too many paths (at least 1000 paths) - Simplify control structure. There are at least 1000 issues ( = paths) costing 1 point.1000
[SA] Non innermost loop (InBetween) - Collapse loop with innermost ones. This issue costs 2 points.2
Inefficient Vectorization+1
+[SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 1 issues (= instructions) costing 1 point each.1
Number of ZMM BROADCAST instructions: 1
×