| Loop Id: 3761 | Module: exec | Source: IJMatrix_parcsr.c:3383-3454 [...] | Coverage: 0.91% |
|---|
| Loop Id: 3761 | Module: exec | Source: IJMatrix_parcsr.c:3383-3454 [...] | Coverage: 0.91% |
|---|
0x4dfa40 MOV -0x40(%RBP),%R9 |
0x4dfa44 MOV 0x10(%RBP),%RAX |
0x4dfa48 VMOVQ (%RAX,%R9,8),%XMM0 |
0x4dfa4e MOV 0x70(%RBP),%RAX |
0x4dfa52 VMOVQ %XMM0,(%RAX,%RBX,8) |
0x4dfa57 MOV %R9,%RBX |
0x4dfa5a MOV 0x68(%RBP),%R9 |
0x4dfa5e XCHG %AX,%AX |
0x4dfa60 INC %RBX |
0x4dfa63 INC %RSI |
0x4dfa66 CMP %R14,%RSI |
0x4dfa69 JE 4dfda0 |
0x4dfa6f MOV -0x90(%RBP),%RAX |
0x4dfa76 MOV (%RAX,%RBX,8),%RAX |
0x4dfa7a CMP 0x28(%RBP),%RAX |
0x4dfa7e MOV %RBX,-0x40(%RBP) |
0x4dfa82 JL 4dfae0 |
0x4dfa84 CMP 0x30(%RBP),%RAX |
0x4dfa88 JG 4dfae0 |
0x4dfa8a MOV 0x60(%RBP),%RBX |
0x4dfa8e MOV -0x50(%RBP),%RDI |
0x4dfa92 MOV (%RBX,%RDI,8),%RBX |
0x4dfa96 CMP %RDX,%RBX |
0x4dfa99 JGE 4dfaae |
0x4dfa9b NOPL (%RAX,%RAX,1) |
(3763) 0x4dfaa0 CMP %RAX,(%R9,%RBX,8) |
(3763) 0x4dfaa4 JE 4dfa40 |
(3763) 0x4dfaa6 INC %RBX |
(3763) 0x4dfaa9 CMP %RBX,%RDX |
(3763) 0x4dfaac JNE 4dfaa0 |
0x4dfaae CMP -0x60(%RBP),%R15 |
0x4dfab2 JGE 4dfe40 |
0x4dfab8 MOV %RAX,(%R9,%R15,8) |
0x4dfabc MOV -0x40(%RBP),%RBX |
0x4dfac0 MOV 0x10(%RBP),%RAX |
0x4dfac4 VMOVQ (%RAX,%RBX,8),%XMM0 |
0x4dfac9 MOV 0x70(%RBP),%RAX |
0x4dfacd VMOVQ %XMM0,(%RAX,%R15,8) |
0x4dfad3 INC %R15 |
0x4dfad6 JMP 4dfa60 |
0x4dfae0 MOV 0x78(%RBP),%RBX |
0x4dfae4 MOV -0x50(%RBP),%RDI |
0x4dfae8 MOV (%RBX,%RDI,8),%RBX |
0x4dfaec CMP %RCX,%RBX |
0x4dfaef JGE 4dfb0e |
0x4dfaf1 NOPW %CS:(%RAX,%RAX,1) |
(3762) 0x4dfb00 CMP %RAX,(%R8,%RBX,8) |
(3762) 0x4dfb04 JE 4dfb40 |
(3762) 0x4dfb06 INC %RBX |
(3762) 0x4dfb09 CMP %RBX,%RCX |
(3762) 0x4dfb0c JNE 4dfb00 |
0x4dfb0e CMP %R11,%R13 |
0x4dfb11 JGE 4dfe80 |
0x4dfb17 MOV %RAX,(%R8,%R13,8) |
0x4dfb1b MOV -0x40(%RBP),%RBX |
0x4dfb1f MOV 0x10(%RBP),%RAX |
0x4dfb23 VMOVQ (%RAX,%RBX,8),%XMM0 |
0x4dfb28 MOV 0x88(%RBP),%RAX |
0x4dfb2f VMOVQ %XMM0,(%RAX,%R13,8) |
0x4dfb35 INC %R13 |
0x4dfb38 JMP 4dfa60 |
0x4dfb40 MOV -0x40(%RBP),%RAX |
0x4dfb44 MOV 0x10(%RBP),%RDI |
0x4dfb48 VMOVQ (%RDI,%RAX,8),%XMM0 |
0x4dfb4d MOV 0x88(%RBP),%R9 |
0x4dfb54 VMOVQ %XMM0,(%R9,%RBX,8) |
0x4dfb5a MOV 0x68(%RBP),%R9 |
0x4dfb5e MOV 0x80(%RBP),%R8 |
0x4dfb65 MOV %RAX,%RBX |
0x4dfb68 JMP 4dfa60 |
/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 | 3.75 |
| 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 | 2.14 |
| Bottlenecks | micro-operation queue, 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 | 15.00 |
| CQA cycles if no scalar integer | 4.00 |
| CQA cycles if FP arith vectorized | 15.00 |
| CQA cycles if fully vectorized | 1.88 |
| Front-end cycles | 15.00 |
| DIV/SQRT cycles | 5.25 |
| P0 cycles | 5.25 |
| P1 cycles | 15.00 |
| P2 cycles | 15.00 |
| P3 cycles | 7.00 |
| P4 cycles | 5.25 |
| P5 cycles | 5.25 |
| P6 cycles | 7.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 15.17 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 60.00 |
| Nb uops | 60.00 |
| Nb loads | 30.00 |
| Nb stores | 7.00 |
| Nb stack references | 13.00 |
| 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 | 19.73 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 240.00 |
| Bytes stored | 56.00 |
| 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 | 0.00 |
| 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 | 12.50 |
| 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 | 3.75 |
| 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 | 2.14 |
| Bottlenecks | micro-operation queue, 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 | 15.00 |
| CQA cycles if no scalar integer | 4.00 |
| CQA cycles if FP arith vectorized | 15.00 |
| CQA cycles if fully vectorized | 1.88 |
| Front-end cycles | 15.00 |
| DIV/SQRT cycles | 5.25 |
| P0 cycles | 5.25 |
| P1 cycles | 15.00 |
| P2 cycles | 15.00 |
| P3 cycles | 7.00 |
| P4 cycles | 5.25 |
| P5 cycles | 5.25 |
| P6 cycles | 7.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 15.17 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 60.00 |
| Nb uops | 60.00 |
| Nb loads | 30.00 |
| Nb stores | 7.00 |
| Nb stack references | 13.00 |
| 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 | 19.73 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 240.00 |
| Bytes stored | 56.00 |
| 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 | 0.00 |
| 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 | 12.50 |
| 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 | 60 |
| nb uops | 60 |
| loop length | 262 |
| used x86 registers | 13 |
| used mmx registers | 0 |
| used xmm registers | 1 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 13 |
| micro-operation queue | 15.00 cycles |
| front end | 15.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 5.25 | 5.25 | 15.00 | 15.00 | 7.00 | 5.25 | 5.25 | 7.00 |
| cycles | 5.25 | 5.25 | 15.00 | 15.00 | 7.00 | 5.25 | 5.25 | 7.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 15.17 |
| Stall cycles | 0.00 |
| Front-end | 15.00 |
| Dispatch | 15.00 |
| Overall L1 | 15.00 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| 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 | 12% |
| 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 -0x40(%RBP),%R9 | 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,%R9,8),%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,%RBX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV %R9,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| MOV 0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| INC %RBX | 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 4dfda0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x90(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP 0x28(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| MOV %RBX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JL 4dfae0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMP 0x30(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JG 4dfae0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0x60(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RBX,%RDI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %RDX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4dfaae | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMP -0x60(%RBP),%R15 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 4dfe40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RAX,(%R9,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x40(%RBP),%RBX | 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,%RBX,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,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INC %R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JMP 4dfa60 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV 0x78(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RBX,%RDI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %RCX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4dfb0e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMP %R11,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4dfe80 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RAX,(%R8,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x40(%RBP),%RBX | 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,%RBX,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x88(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RAX,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INC %R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JMP 4dfa60 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RDI,%RAX,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x88(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%R9,%RBX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV 0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x80(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %RAX,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| JMP 4dfa60 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| Function | hypre_IJMatrixSetValuesOMPParCSR.extracted.28 |
| Source file and lines | IJMatrix_parcsr.c:3383-3454 |
| Module | exec |
| nb instructions | 60 |
| nb uops | 60 |
| loop length | 262 |
| used x86 registers | 13 |
| used mmx registers | 0 |
| used xmm registers | 1 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 13 |
| micro-operation queue | 15.00 cycles |
| front end | 15.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 5.25 | 5.25 | 15.00 | 15.00 | 7.00 | 5.25 | 5.25 | 7.00 |
| cycles | 5.25 | 5.25 | 15.00 | 15.00 | 7.00 | 5.25 | 5.25 | 7.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 15.17 |
| Stall cycles | 0.00 |
| Front-end | 15.00 |
| Dispatch | 15.00 |
| Overall L1 | 15.00 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| 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 | 12% |
| 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 -0x40(%RBP),%R9 | 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,%R9,8),%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,%RBX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV %R9,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| MOV 0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| INC %RBX | 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 4dfda0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x90(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP 0x28(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| MOV %RBX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JL 4dfae0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMP 0x30(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JG 4dfae0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0x60(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RBX,%RDI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %RDX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4dfaae | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMP -0x60(%RBP),%R15 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 4dfe40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RAX,(%R9,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x40(%RBP),%RBX | 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,%RBX,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,%R15,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INC %R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JMP 4dfa60 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV 0x78(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RBX,%RDI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %RCX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4dfb0e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMP %R11,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4dfe80 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RAX,(%R8,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x40(%RBP),%RBX | 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,%RBX,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x88(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%RAX,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INC %R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JMP 4dfa60 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x10(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ (%RDI,%RAX,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x88(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVQ %XMM0,(%R9,%RBX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV 0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x80(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %RAX,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| JMP 4dfa60 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
