| Loop Id: 3733 | Module: exec | Source: IJMatrix_parcsr.c:3383-3454 [...] | Coverage: 1.04% |
|---|
| Loop Id: 3733 | Module: exec | Source: IJMatrix_parcsr.c:3383-3454 [...] | Coverage: 1.04% |
|---|
0x4cb474 MOV -0x30(%RBP),%R12 |
0x4cb478 MOV 0x10(%RBP),%RAX |
0x4cb47c VMOVQ (%RAX,%R12,8),%XMM0 |
0x4cb482 MOV 0x70(%RBP),%RAX |
0x4cb486 VMOVQ %XMM0,(%RAX,%RDX,8) |
0x4cb48b MOV -0x38(%RBP),%RBX |
0x4cb48f INC %R12 |
0x4cb492 INC %RSI |
0x4cb495 CMP %R14,%RSI |
0x4cb498 JE 4cb59f |
0x4cb49e MOV %R12,-0x30(%RBP) |
0x4cb4a2 MOV (%RBX,%R12,8),%RBX |
0x4cb4a6 CMP 0x28(%RBP),%RBX |
0x4cb4aa JL 4cb510 |
0x4cb4ac CMP 0x30(%RBP),%RBX |
0x4cb4b0 JG 4cb510 |
0x4cb4b2 MOV 0x60(%RBP),%RAX |
0x4cb4b6 MOV -0x50(%RBP),%RDX |
0x4cb4ba MOV (%RAX,%RDX,8),%RDX |
0x4cb4be CMP %R11,%RDX |
0x4cb4c1 MOV 0x68(%RBP),%RAX |
0x4cb4c5 JGE 4cb4de |
0x4cb4c7 NOPW (%RAX,%RAX,1) |
(3735) 0x4cb4d0 CMP %RBX,(%RAX,%RDX,8) |
(3735) 0x4cb4d4 JE 4cb474 |
(3735) 0x4cb4d6 INC %RDX |
(3735) 0x4cb4d9 CMP %RDX,%R11 |
(3735) 0x4cb4dc JNE 4cb4d0 |
0x4cb4de CMP -0x90(%RBP),%RCX |
0x4cb4e5 JGE 4cb81e |
0x4cb4eb MOV %RBX,(%RAX,%RCX,8) |
0x4cb4ef MOV -0x30(%RBP),%R12 |
0x4cb4f3 MOV 0x10(%RBP),%RAX |
0x4cb4f7 VMOVQ (%RAX,%R12,8),%XMM0 |
0x4cb4fd MOV 0x70(%RBP),%RAX |
0x4cb501 VMOVQ %XMM0,(%RAX,%RCX,8) |
0x4cb506 INC %RCX |
0x4cb509 JMP 4cb48b |
0x4cb510 MOV %RCX,-0x48(%RBP) |
0x4cb514 MOV 0x78(%RBP),%RAX |
0x4cb518 MOV -0x50(%RBP),%RDX |
0x4cb51c MOV (%RAX,%RDX,8),%RDX |
0x4cb520 CMP %R9,%RDX |
0x4cb523 MOV 0x80(%RBP),%RAX |
0x4cb52a MOV -0x70(%RBP),%RCX |
0x4cb52e JGE 4cb53e |
(3734) 0x4cb530 CMP %RBX,(%RAX,%RDX,8) |
(3734) 0x4cb534 JE 4cb56e |
(3734) 0x4cb536 INC %RDX |
(3734) 0x4cb539 CMP %RDX,%R9 |
(3734) 0x4cb53c JNE 4cb530 |
0x4cb53e CMP %R10,%RCX |
0x4cb541 JGE 4cb857 |
0x4cb547 MOV %RBX,(%RAX,%RCX,8) |
0x4cb54b MOV -0x30(%RBP),%R12 |
0x4cb54f MOV 0x10(%RBP),%RAX |
0x4cb553 VMOVQ (%RAX,%R12,8),%XMM0 |
0x4cb559 MOV 0x88(%RBP),%RDX |
0x4cb560 VMOVQ %XMM0,(%RDX,%RCX,8) |
0x4cb565 INC %RCX |
0x4cb568 MOV %RCX,-0x70(%RBP) |
0x4cb56c JMP 4cb588 |
0x4cb56e MOV -0x30(%RBP),%R12 |
0x4cb572 MOV 0x10(%RBP),%RAX |
0x4cb576 VMOVQ (%RAX,%R12,8),%XMM0 |
0x4cb57c MOV 0x88(%RBP),%RBX |
0x4cb583 VMOVQ %XMM0,(%RBX,%RDX,8) |
0x4cb588 MOV -0x38(%RBP),%RBX |
0x4cb58c MOV -0x48(%RBP),%RCX |
0x4cb590 INC %R12 |
0x4cb593 INC %RSI |
0x4cb596 CMP %R14,%RSI |
0x4cb599 JNE 4cb49e |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/IJ_mv/IJMatrix_parcsr.c: 3383 - 3454 |
-------------------------------------------------------------------------------- |
3383: for (i=0; i < n; i++) |
3384: { |
3385: if (cols[indx] < col_0 || cols[indx] > col_n) |
3386: /* insert into offd */ |
3387: { |
3388: for (j=offd_i[row_local]; j < offd_indx; j++) |
3389: { |
3390: if (offd_j[j] == cols[indx]) |
3391: { |
3392: offd_data[j] = values[indx]; |
[...] |
3399: if (cnt_offd < offd_space) |
3400: { |
3401: offd_j[cnt_offd] = cols[indx]; |
3402: offd_data[cnt_offd++] = values[indx]; |
[...] |
3422: for (j=diag_i[row_local]; j < diag_indx; j++) |
3423: { |
3424: if (diag_j[j] == cols[indx]) |
3425: { |
3426: diag_data[j] = values[indx]; |
[...] |
3433: if (cnt_diag < diag_space) |
3434: { |
3435: diag_j[cnt_diag] = cols[indx]; |
3436: diag_data[cnt_diag++] = values[indx]; |
[...] |
3454: indx++; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_fork_call | libiomp5.so | |
| ○ | __kmpc_fork_call | libiomp5.so | |
| ○ | hypre_IJMatrixSetValuesOMPParC[...] | IJMatrix_parcsr.c:3240 | exec |
| ○ | BuildIJLaplacian27pt | amg.c:2267 | exec |
| ○ | main | amg.c:274 | exec |
| ○ | __libc_init_first | libc.so.6 |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 3.56 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 8.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.03 |
| Bottlenecks | P2, P3, |
| Function | hypre_IJMatrixSetValuesOMPParCSR.extracted.28 |
| Source | IJMatrix_parcsr.c:3383-3454 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 16.00 |
| CQA cycles if no scalar integer | 4.50 |
| CQA cycles if FP arith vectorized | 16.00 |
| CQA cycles if fully vectorized | 2.00 |
| Front-end cycles | 15.50 |
| DIV/SQRT cycles | 5.75 |
| P0 cycles | 5.75 |
| P1 cycles | 16.00 |
| P2 cycles | 16.00 |
| P3 cycles | 9.00 |
| P4 cycles | 5.75 |
| P5 cycles | 5.75 |
| P6 cycles | 9.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 16.16 |
| Stall cycles (UFS) | 0.45 |
| Nb insns | 63.00 |
| Nb uops | 62.00 |
| Nb loads | 32.00 |
| Nb stores | 9.00 |
| Nb stack references | 15.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 20.50 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 256.00 |
| Bytes stored | 72.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 12.50 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 12.50 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 3.56 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 8.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.03 |
| Bottlenecks | P2, P3, |
| Function | hypre_IJMatrixSetValuesOMPParCSR.extracted.28 |
| Source | IJMatrix_parcsr.c:3383-3454 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 16.00 |
| CQA cycles if no scalar integer | 4.50 |
| CQA cycles if FP arith vectorized | 16.00 |
| CQA cycles if fully vectorized | 2.00 |
| Front-end cycles | 15.50 |
| DIV/SQRT cycles | 5.75 |
| P0 cycles | 5.75 |
| P1 cycles | 16.00 |
| P2 cycles | 16.00 |
| P3 cycles | 9.00 |
| P4 cycles | 5.75 |
| P5 cycles | 5.75 |
| P6 cycles | 9.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 16.16 |
| Stall cycles (UFS) | 0.45 |
| Nb insns | 63.00 |
| Nb uops | 62.00 |
| Nb loads | 32.00 |
| Nb stores | 9.00 |
| Nb stack references | 15.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 20.50 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 256.00 |
| Bytes stored | 72.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 12.50 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 12.50 |
| Path / |
| Function | hypre_IJMatrixSetValuesOMPParCSR.extracted.28 |
| Source file and lines | IJMatrix_parcsr.c:3383-3454 |
| Module | exec |
| nb instructions | 63 |
| nb uops | 62 |
| loop length | 266 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 1 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 15 |
| micro-operation queue | 15.50 cycles |
| front end | 15.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 5.75 | 5.75 | 16.00 | 16.00 | 9.00 | 5.75 | 5.75 | 9.00 |
| cycles | 5.75 | 5.75 | 16.00 | 16.00 | 9.00 | 5.75 | 5.75 | 9.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 16.16 |
| Stall cycles | 0.45 |
| LM full (events) | 1.81 |
| Front-end | 15.50 |
| Dispatch | 16.00 |
| Overall L1 | 16.00 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 12% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 12% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|
| MOV -0x30(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x70(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RAX,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x38(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| INC %RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| CMP %R14,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JE 4cb59f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %R12,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV (%RBX,%R12,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP 0x28(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JL 4cb510 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMP 0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JG 4cb510 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0x60(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %R11,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV 0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JGE 4cb4de | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMP -0x90(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 4cb81e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RBX,(%RAX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x30(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x70(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RAX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JMP 4cb48b | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV %RCX,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV 0x78(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %R9,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV 0x80(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x70(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JGE 4cb53e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMP %R10,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4cb857 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RBX,(%RAX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x30(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x88(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RDX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV %RCX,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JMP 4cb588 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x30(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x88(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RBX,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x38(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x48(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| INC %RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| CMP %R14,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JNE 4cb49e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| Function | hypre_IJMatrixSetValuesOMPParCSR.extracted.28 |
| Source file and lines | IJMatrix_parcsr.c:3383-3454 |
| Module | exec |
| nb instructions | 63 |
| nb uops | 62 |
| loop length | 266 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 1 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 15 |
| micro-operation queue | 15.50 cycles |
| front end | 15.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 5.75 | 5.75 | 16.00 | 16.00 | 9.00 | 5.75 | 5.75 | 9.00 |
| cycles | 5.75 | 5.75 | 16.00 | 16.00 | 9.00 | 5.75 | 5.75 | 9.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 16.16 |
| Stall cycles | 0.45 |
| LM full (events) | 1.81 |
| Front-end | 15.50 |
| Dispatch | 16.00 |
| Overall L1 | 16.00 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 12% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 12% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|
| MOV -0x30(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x70(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RAX,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x38(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| INC %RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| CMP %R14,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JE 4cb59f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %R12,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV (%RBX,%R12,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP 0x28(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JL 4cb510 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMP 0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JG 4cb510 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0x60(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %R11,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV 0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JGE 4cb4de | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMP -0x90(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 4cb81e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RBX,(%RAX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x30(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x70(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RAX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JMP 4cb48b | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV %RCX,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV 0x78(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %R9,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV 0x80(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x70(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JGE 4cb53e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMP %R10,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4cb857 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RBX,(%RAX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x30(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x88(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RDX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV %RCX,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JMP 4cb588 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x30(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x88(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RBX,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x38(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x48(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| INC %RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| CMP %R14,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JNE 4cb49e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
