Loop Id: 386 | Module: libparcsr_mv.so | Source: par_csr_matop.c:3590-3596 | Coverage: 0.01% |
---|
Loop Id: 386 | Module: libparcsr_mv.so | Source: par_csr_matop.c:3590-3596 | Coverage: 0.01% |
---|
0x1c8f0 MOV (%R14,%RSI,8),%R9 [6] |
0x1c8f4 MOV %R9,(%RDI,%RAX,8) [2] |
0x1c8f8 VMOVQ (%R10,%RSI,8),%XMM0 [1] |
0x1c8fe VMOVQ %XMM0,(%R8,%RAX,8) [5] |
0x1c904 MOV %RAX,(%R11,%R9,8) [4] |
0x1c908 INC %RAX |
0x1c90b INC %RSI |
0x1c90e CMP (%RBX,%R13,8),%RSI [3] |
0x1c912 JL 1c8f0 |
/home/eoseret/qaas_runs_CPU_9468/171-716-5699/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 3590 - 3596 |
-------------------------------------------------------------------------------- |
3590: for (jk = C_tmp_diag_i[ik]; jk < C_tmp_diag_i[ik+1]; jk++) |
3591: { |
3592: jcol = C_tmp_diag_j[jk]; |
3593: C_diag_j[nnz_d] = jcol; |
3594: C_diag_data[nnz_d] = C_tmp_diag_data[jk]; |
3595: B_marker[jcol] = nnz_d; |
3596: nnz_d++; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.50 |
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 | 1.50 |
Bottlenecks | micro-operation queue, P4, P7, P8, P9, |
Function | hypre_ParTMatmul.extracted |
Source | par_csr_matop.c:3590-3596 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.50 |
CQA cycles if no scalar integer | 1.00 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.19 |
Front-end cycles | 1.50 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.00 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 1.50 |
P4 cycles | 0.00 |
P5 cycles | 0.50 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 0.00 |
P10 cycles | 1.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.62 |
Stall cycles (UFS) | 0.00 |
Nb insns | 9.00 |
Nb uops | 8.00 |
Nb loads | 3.00 |
Nb stores | 3.00 |
Nb stack references | 0.00 |
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 | 32.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 24.00 |
Bytes stored | 24.00 |
Stride 0 | 1.00 |
Stride 1 | 4.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
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 | NA |
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 | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.50 |
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 | 1.50 |
Bottlenecks | micro-operation queue, P4, P7, P8, P9, |
Function | hypre_ParTMatmul.extracted |
Source | par_csr_matop.c:3590-3596 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.50 |
CQA cycles if no scalar integer | 1.00 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.19 |
Front-end cycles | 1.50 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.00 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 1.50 |
P4 cycles | 0.00 |
P5 cycles | 0.50 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 0.00 |
P10 cycles | 1.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.62 |
Stall cycles (UFS) | 0.00 |
Nb insns | 9.00 |
Nb uops | 8.00 |
Nb loads | 3.00 |
Nb stores | 3.00 |
Nb stack references | 0.00 |
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 | 32.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 24.00 |
Bytes stored | 24.00 |
Stride 0 | 1.00 |
Stride 1 | 4.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
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 | NA |
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 | NA |
Path / |
Function | hypre_ParTMatmul.extracted |
Source file and lines | par_csr_matop.c:3590-3596 |
Module | libparcsr_mv.so |
nb instructions | 9 |
nb uops | 8 |
loop length | 36 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.50 cycles |
front end | 1.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.00 | 1.00 | 1.00 | 1.50 | 0.00 | 0.50 | 1.50 | 1.50 | 1.50 | 0.00 | 1.00 |
cycles | 0.50 | 0.00 | 1.00 | 1.00 | 1.50 | 0.00 | 0.50 | 1.50 | 1.50 | 1.50 | 0.00 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.62 |
Stall cycles | 0.00 |
Front-end | 1.50 |
Dispatch | 1.50 |
Data deps. | 1.00 |
Overall L1 | 1.50 |
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 | NA (no other vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R14,%RSI,8),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R9,(%RDI,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVQ (%R10,%RSI,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVQ %XMM0,(%R8,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,(%R11,%R9,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
INC %RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP (%RBX,%R13,8),%RSI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JL 1c8f0 <hypre_ParTMatmul.extracted+0xab0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_ParTMatmul.extracted |
Source file and lines | par_csr_matop.c:3590-3596 |
Module | libparcsr_mv.so |
nb instructions | 9 |
nb uops | 8 |
loop length | 36 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.50 cycles |
front end | 1.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.00 | 1.00 | 1.00 | 1.50 | 0.00 | 0.50 | 1.50 | 1.50 | 1.50 | 0.00 | 1.00 |
cycles | 0.50 | 0.00 | 1.00 | 1.00 | 1.50 | 0.00 | 0.50 | 1.50 | 1.50 | 1.50 | 0.00 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.62 |
Stall cycles | 0.00 |
Front-end | 1.50 |
Dispatch | 1.50 |
Data deps. | 1.00 |
Overall L1 | 1.50 |
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 | NA (no other vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R14,%RSI,8),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R9,(%RDI,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVQ (%R10,%RSI,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVQ %XMM0,(%R8,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,(%R11,%R9,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
INC %RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP (%RBX,%R13,8),%RSI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JL 1c8f0 <hypre_ParTMatmul.extracted+0xab0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |