| Loop Id: 2470 | Module: exec | Source: par_csr_matop.c:187-231 [...] | Coverage: 1.6% |
|---|
| Loop Id: 2470 | Module: exec | Source: par_csr_matop.c:187-231 [...] | Coverage: 1.6% |
|---|
0x5591c0 MOV 0xc8(%RSP),%R15 |
0x5591c8 MOV 0xd0(%RSP),%RSI |
0x5591d0 MOV (%R15,%R12,8),%R15 |
0x5591d4 LEA 0x8(,%R15,8),%R13 |
0x5591dc MOV (%RSI,%R15,8),%RAX |
0x5591e0 LEA (%RSI,%R13,1),%R11 |
0x5591e4 MOV (%R11),%RSI |
0x5591e7 CMP %RSI,%RAX |
0x5591ea JGE 559212 |
0x5591ec NOPL (%RAX) |
(2472) 0x5591f0 MOV (%R9,%RAX,8),%RDX |
(2472) 0x5591f4 LEA (%RDI,%RDX,8),%RDX |
(2472) 0x5591f8 CMP (%RDX),%RBX |
(2472) 0x5591fb JLE 5593b0 |
(2472) 0x559201 MOV %RCX,(%RDX) |
(2472) 0x559204 INC %RAX |
(2472) 0x559207 INC %RCX |
(2472) 0x55920a MOV (%R11),%RSI |
(2472) 0x55920d CMP %RAX,%RSI |
(2472) 0x559210 JG 5591f0 |
0x559212 CMPQ $0,0xd8(%RSP) |
0x55921b JNE 5593cb |
0x559221 MOV 0xe0(%RSP),%R13 |
0x559229 MOV 0xe8(%RSP),%RAX |
0x559231 INC %R12 |
0x559234 CMP %R12,0x8(%R13,%RAX,8) |
0x559239 JG 5591c0 |
(2472) 0x5593b0 INC %RAX |
(2472) 0x5593b3 CMP %RSI,%RAX |
(2472) 0x5593b6 JL 5591f0 |
0x5593bc CMPQ $0,0xd8(%RSP) |
0x5593c5 JE 559221 |
0x5593cb MOV 0xa0(%RSP),%R11 |
0x5593d3 ADD %R11,%R13 |
0x5593d6 MOV (%R11,%R15,8),%RAX |
0x5593da MOV (%R13),%RSI |
0x5593de CMP %RSI,%RAX |
0x5593e1 JGE 559221 |
0x5593e7 NOPW (%RAX,%RAX,1) |
(2471) 0x5593f0 MOV (%R14,%RAX,8),%RDX |
(2471) 0x5593f4 MOV 0xf0(%RSP),%R11 |
(2471) 0x5593fc MOV 0xf8(%RSP),%R15 |
(2471) 0x559404 ADD (%R11,%RDX,8),%R15 |
(2471) 0x559408 LEA (%RDI,%R15,8),%RDX |
(2471) 0x55940c CMP (%RDX),%R10 |
(2471) 0x55940f JLE 559430 |
(2471) 0x559411 MOV %R8,(%RDX) |
(2471) 0x559414 INC %RAX |
(2471) 0x559417 INC %R8 |
(2471) 0x55941a MOV (%R13),%RSI |
(2471) 0x55941e CMP %RAX,%RSI |
(2471) 0x559421 JG 5593f0 |
0x559423 JMP 559221 |
(2471) 0x559430 INC %RAX |
(2471) 0x559433 CMP %RAX,%RSI |
(2471) 0x559436 JG 5593f0 |
0x559438 JMP 559221 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 187 - 231 |
-------------------------------------------------------------------------------- |
187: for (jj2 = A_diag_i[i1]; jj2 < A_diag_i[i1+1]; jj2++) |
[...] |
195: for (jj3 = B_diag_i[i2]; jj3 < B_diag_i[i2+1]; jj3++) |
[...] |
205: if (B_marker[i3] < jj_row_begin_diag) |
206: { |
207: B_marker[i3] = jj_count_diag; |
208: jj_count_diag++; |
[...] |
216: if (num_cols_offd_B) |
217: { |
218: for (jj3 = B_offd_i[i2]; jj3 < B_offd_i[i2+1]; jj3++) |
219: { |
220: i3 = num_cols_diag_B+map_B_to_C[B_offd_j[jj3]]; |
[...] |
228: if (B_marker[i3] < jj_row_begin_offd) |
229: { |
230: B_marker[i3] = jj_count_offd; |
231: jj_count_offd++; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| 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 | 1.12 |
| Bottlenecks | micro-operation queue, |
| Function | hypre_ParMatmul_RowSizes._omp_fn.0 |
| Source | par_csr_matop.c:187-231 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 7.25 |
| CQA cycles if no scalar integer | 7.25 |
| CQA cycles if FP arith vectorized | 7.25 |
| CQA cycles if fully vectorized | 0.91 |
| Front-end cycles | 7.25 |
| DIV/SQRT cycles | 4.00 |
| P0 cycles | 4.00 |
| P1 cycles | 6.50 |
| P2 cycles | 6.50 |
| P3 cycles | 0.00 |
| P4 cycles | 4.00 |
| P5 cycles | 4.00 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 7.45 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 28.00 |
| Nb uops | 28.00 |
| Nb loads | 13.00 |
| Nb stores | 0.00 |
| Nb stack references | 6.00 |
| 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 | 14.34 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 104.00 |
| Bytes stored | 0.00 |
| 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 | NA |
| 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 | NA |
| 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 | 1.00 |
| 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 | 1.12 |
| Bottlenecks | micro-operation queue, |
| Function | hypre_ParMatmul_RowSizes._omp_fn.0 |
| Source | par_csr_matop.c:187-231 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 7.25 |
| CQA cycles if no scalar integer | 7.25 |
| CQA cycles if FP arith vectorized | 7.25 |
| CQA cycles if fully vectorized | 0.91 |
| Front-end cycles | 7.25 |
| DIV/SQRT cycles | 4.00 |
| P0 cycles | 4.00 |
| P1 cycles | 6.50 |
| P2 cycles | 6.50 |
| P3 cycles | 0.00 |
| P4 cycles | 4.00 |
| P5 cycles | 4.00 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 7.45 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 28.00 |
| Nb uops | 28.00 |
| Nb loads | 13.00 |
| Nb stores | 0.00 |
| Nb stack references | 6.00 |
| 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 | 14.34 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 104.00 |
| Bytes stored | 0.00 |
| 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 | NA |
| 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 | NA |
| 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_ParMatmul_RowSizes._omp_fn.0 |
| Source file and lines | par_csr_matop.c:187-231 |
| Module | exec |
| nb instructions | 28 |
| nb uops | 28 |
| loop length | 151 |
| used x86 registers | 7 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 6 |
| micro-operation queue | 7.25 cycles |
| front end | 7.25 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 4.00 | 4.00 | 6.50 | 6.50 | 0.00 | 4.00 | 4.00 | 0.00 |
| cycles | 4.00 | 4.00 | 6.50 | 6.50 | 0.00 | 4.00 | 4.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 7.45 |
| Stall cycles | 0.00 |
| Front-end | 7.25 |
| Dispatch | 6.50 |
| Overall L1 | 7.25 |
| all | 0% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | NA (no store vectorizable/vectorized instructions) |
| 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 0xc8(%RSP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0xd0(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%R15,%R12,8),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| LEA 0x8(,%R15,8),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| MOV (%RSI,%R15,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| LEA (%RSI,%R13,1),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| MOV (%R11),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 559212 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMPQ $0,0xd8(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JNE 5593cb | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0xe0(%RSP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0xe8(%RSP),%RAX | 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 |
| CMP %R12,0x8(%R13,%RAX,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JG 5591c0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMPQ $0,0xd8(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JE 559221 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0xa0(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| ADD %R11,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV (%R11,%R15,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%R13),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 559221 | 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 |
| JMP 559221 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| JMP 559221 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| Function | hypre_ParMatmul_RowSizes._omp_fn.0 |
| Source file and lines | par_csr_matop.c:187-231 |
| Module | exec |
| nb instructions | 28 |
| nb uops | 28 |
| loop length | 151 |
| used x86 registers | 7 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 6 |
| micro-operation queue | 7.25 cycles |
| front end | 7.25 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 4.00 | 4.00 | 6.50 | 6.50 | 0.00 | 4.00 | 4.00 | 0.00 |
| cycles | 4.00 | 4.00 | 6.50 | 6.50 | 0.00 | 4.00 | 4.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 7.45 |
| Stall cycles | 0.00 |
| Front-end | 7.25 |
| Dispatch | 6.50 |
| Overall L1 | 7.25 |
| all | 0% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | NA (no store vectorizable/vectorized instructions) |
| 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 0xc8(%RSP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0xd0(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%R15,%R12,8),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| LEA 0x8(,%R15,8),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| MOV (%RSI,%R15,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| LEA (%RSI,%R13,1),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| MOV (%R11),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 559212 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMPQ $0,0xd8(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JNE 5593cb | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0xe0(%RSP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0xe8(%RSP),%RAX | 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 |
| CMP %R12,0x8(%R13,%RAX,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JG 5591c0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMPQ $0,0xd8(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JE 559221 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0xa0(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| ADD %R11,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV (%R11,%R15,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%R13),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 559221 | 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 |
| JMP 559221 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| JMP 559221 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
