Loop Id: 30 | Module: libseq_mv.so | Source: csr_matop.c:540-548 | Coverage: 0.03% |
---|
Loop Id: 30 | Module: libseq_mv.so | Source: csr_matop.c:540-548 | Coverage: 0.03% |
---|
0x3a10 MOV %RDX,%RCX |
0x3a13 CMP %R8,%R13 |
0x3a16 JLE 3d9e |
0x3a1c MOV -0x8(%RDI,%R13,8),%RDX |
0x3a21 DEC %R13 |
0x3a24 CMP %RDX,%RCX |
0x3a27 JLE 3a10 |
0x3a29 NOPL (%RAX) |
(31) 0x3a30 MOV -0x8(%R10,%RCX,8),%RDX |
(31) 0x3a35 MOV (%R12),%RSI |
(31) 0x3a39 IMUL %R14,%RSI |
(31) 0x3a3d ADD %RDX,%RSI |
(31) 0x3a40 DECQ (%R15,%RSI,8) |
(31) 0x3a44 MOV (%R12),%RSI |
(31) 0x3a48 IMUL %R14,%RSI |
(31) 0x3a4c ADD %RDX,%RSI |
(31) 0x3a4f MOV (%R15,%RSI,8),%RDX |
(31) 0x3a53 VMOVSD -0x8(%R9,%RCX,8),%XMM0 |
(31) 0x3a5a VMOVSD %XMM0,(%RAX,%RDX,8) |
(31) 0x3a5f DEC %RCX |
(31) 0x3a62 MOV %R13,(%RBX,%RDX,8) |
(31) 0x3a66 MOV (%RDI,%R13,8),%RDX |
(31) 0x3a6a CMP %RDX,%RCX |
(31) 0x3a6d JG 3a30 |
0x3a6f JMP 3a10 |
/scratch_na/users/xoserete/qaas_runs/171-587-0005/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c: 540 - 548 |
-------------------------------------------------------------------------------- |
540: for (i = iEnd - 1; i >= iBegin; --i) { |
541: for (j = A_i[i + 1] - 1; j >= A_i[i]; --j) { |
542: HYPRE_Int idx = A_j[j]; |
543: --bucket[my_thread_num*num_colsA + idx]; |
544: |
545: HYPRE_Int offset = bucket[my_thread_num*num_colsA + idx]; |
546: |
547: AT_data[offset] = A_data[j]; |
548: AT_j[offset] = i; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
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 | 1.79 |
Bottlenecks | |
Function | hypre_CSRMatrixTranspose.extracted |
Source | csr_matop.c:540-541 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.25 |
CQA cycles if no scalar integer | 1.25 |
CQA cycles if FP arith vectorized | 1.25 |
CQA cycles if fully vectorized | 0.16 |
Front-end cycles | 1.25 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.60 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 0.00 |
P4 cycles | 0.50 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.40 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.34 |
Stall cycles (UFS) | 0.00 |
Nb insns | 8.00 |
Nb uops | 7.50 |
Nb loads | 1.00 |
Nb stores | 0.00 |
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 | 6.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 8.00 |
Bytes stored | 0.00 |
Stride 0 | 0.50 |
Stride 1 | 1.50 |
Stride n | 0.50 |
Stride unknown | 0.50 |
Stride indirect | 1.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | NA |
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 | NA |
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 | 1.50 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixTranspose.extracted |
Source | csr_matop.c:540-541 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.50 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.19 |
Front-end cycles | 1.50 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 0.00 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.60 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.60 |
Stall cycles (UFS) | 0.00 |
Nb insns | 9.00 |
Nb uops | 9.00 |
Nb loads | 1.00 |
Nb stores | 0.00 |
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 | 5.33 |
Bytes prefetched | 0.00 |
Bytes loaded | 8.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 2.00 |
Stride n | 1.00 |
Stride unknown | 1.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | NA |
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 | NA |
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 | 2.50 |
Bottlenecks | micro-operation queue, P0, P6, |
Function | hypre_CSRMatrixTranspose.extracted |
Source | csr_matop.c:540-541 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.00 |
CQA cycles if no scalar integer | 1.00 |
CQA cycles if FP arith vectorized | 1.00 |
CQA cycles if fully vectorized | 0.13 |
Front-end cycles | 1.00 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.40 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 0.00 |
P4 cycles | 0.40 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.20 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.09 |
Stall cycles (UFS) | 0.00 |
Nb insns | 7.00 |
Nb uops | 6.00 |
Nb loads | 1.00 |
Nb stores | 0.00 |
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 | 8.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 8.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | NA |
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 | NA |
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_CSRMatrixTranspose.extracted |
Source file and lines | csr_matop.c:540-548 |
Module | libseq_mv.so |
nb instructions | 8 |
nb uops | 7.50 |
loop length | 29.50 |
used x86 registers | 5.50 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.25 cycles |
front end | 1.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.60 | 0.33 | 0.33 | 0.00 | 0.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.40 | 0.33 |
cycles | 1.00 | 0.60 | 0.33 | 0.33 | 0.00 | 0.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.40 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.35 |
Stall cycles | 0.00 |
Front-end | 1.25 |
Dispatch | 1.00 |
Data deps. | 1.00 |
Overall L1 | 1.25 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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 | NA (no load vectorizable/vectorized instructions) |
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% |
Function | hypre_CSRMatrixTranspose.extracted |
Source file and lines | csr_matop.c:540-548 |
Module | libseq_mv.so |
nb instructions | 9 |
nb uops | 9 |
loop length | 34 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 0 |
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 | 1.00 | 0.80 | 0.33 | 0.33 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 0.33 |
cycles | 1.00 | 0.80 | 0.33 | 0.33 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.60 |
Stall cycles | 0.00 |
Front-end | 1.50 |
Dispatch | 1.00 |
Data deps. | 1.00 |
Overall L1 | 1.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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 | NA (no load vectorizable/vectorized instructions) |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV %RDX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R8,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 3d9e <hypre_CSRMatrixTranspose.extracted+0x9de> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x8(%RDI,%R13,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
DEC %R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RDX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 3a10 <hypre_CSRMatrixTranspose.extracted+0x650> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 3a10 <hypre_CSRMatrixTranspose.extracted+0x650> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
Function | hypre_CSRMatrixTranspose.extracted |
Source file and lines | csr_matop.c:540-548 |
Module | libseq_mv.so |
nb instructions | 7 |
nb uops | 6 |
loop length | 25 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.00 cycles |
front end | 1.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.40 | 0.33 | 0.33 | 0.00 | 0.40 | 1.00 | 0.00 | 0.00 | 0.00 | 0.20 | 0.33 |
cycles | 1.00 | 0.40 | 0.33 | 0.33 | 0.00 | 0.40 | 1.00 | 0.00 | 0.00 | 0.00 | 0.20 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.09 |
Stall cycles | 0.00 |
Front-end | 1.00 |
Dispatch | 1.00 |
Data deps. | 1.00 |
Overall L1 | 1.00 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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 | NA (no load vectorizable/vectorized instructions) |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV %RDX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R8,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 3d9e <hypre_CSRMatrixTranspose.extracted+0x9de> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x8(%RDI,%R13,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
DEC %R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RDX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 3a10 <hypre_CSRMatrixTranspose.extracted+0x650> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |