Loop Id: 204 | Module: libseq_mv.so | Source: csr_matvec.c:560-579 [...] | Coverage: 0.01% |
---|
Loop Id: 204 | Module: libseq_mv.so | Source: csr_matvec.c:560-579 [...] | Coverage: 0.01% |
---|
0xc4c0 VMOVSD %XMM2,(%R11,%R8,8) |
0xc4c6 INC %RDI |
0xc4c9 CMP %RCX,%RSI |
0xc4cc LEA 0x1(%RSI),%RSI |
0xc4d0 JE c250 |
0xc4d6 LEA (%RAX,%RSI,1),%R8 |
0xc4da VMOVSD (%R11,%R8,8),%XMM2 |
0xc4e0 MOV %R12,%R9 |
0xc4e3 AND $-0x4,%R9 |
0xc4e7 JE c580 |
0xc4ed LEA -0x1(%R9),%R10 |
0xc4f1 VXORPD %XMM3,%XMM3,%XMM3 |
0xc4f5 VPBROADCASTQ %R8,%YMM4 |
0xc4fb XOR %R11D,%R11D |
0xc4fe XCHG %AX,%AX |
(205) 0xc500 VPBROADCASTQ %R11,%YMM5 |
(205) 0xc506 VPADDQ %YMM1,%YMM5,%YMM5 |
(205) 0xc50a VPMULLQ %YMM5,%YMM0,%YMM5 |
(205) 0xc510 VPADDQ %YMM5,%YMM4,%YMM5 |
(205) 0xc514 KXNORW %K0,%K0,%K1 |
(205) 0xc518 VXORPD %XMM6,%XMM6,%XMM6 |
(205) 0xc51c VGATHERQPD (%RBX,%YMM5,8),%YMM6{%K1} |
(205) 0xc523 VADDPD %YMM6,%YMM3,%YMM3 |
(205) 0xc527 ADD $0x4,%R11 |
(205) 0xc52b CMP %R10,%R11 |
(205) 0xc52e JLE c500 |
0xc530 VEXTRACTF128 $0x1,%YMM3,%XMM4 |
0xc536 VADDPD %XMM4,%XMM3,%XMM3 |
0xc53a VSHUFPD $0x1,%XMM3,%XMM3,%XMM4 |
0xc53f VADDSD %XMM4,%XMM3,%XMM3 |
0xc543 VADDSD %XMM3,%XMM2,%XMM2 |
0xc547 CMP %R12,%R9 |
0xc54a MOV -0x58(%RBP),%R11 |
0xc54e JE c4c0 |
0xc554 JMP c583 |
0xc580 XOR %R9D,%R9D |
0xc583 MOV %R12,%R10 |
0xc586 SUB %R9,%R10 |
0xc589 IMUL %R13,%R9 |
0xc58d ADD %RDI,%R9 |
0xc590 LEA (%RBX,%R9,8),%R9 |
0xc594 NOPW %CS:(%RAX,%RAX,1) |
(203) 0xc5a0 VADDSD (%R9),%XMM2,%XMM2 |
(203) 0xc5a5 ADD %RDX,%R9 |
(203) 0xc5a8 DEC %R10 |
(203) 0xc5ab JNE c5a0 |
0xc5ad JMP c4c0 |
/home/eoseret/qaas_runs_CPU_9468/171-716-5699/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c: 560 - 579 |
-------------------------------------------------------------------------------- |
560: #pragma omp for HYPRE_SMP_SCHEDULE |
[...] |
573: #pragma omp for HYPRE_SMP_SCHEDULE |
574: #endif |
575: for (i = 0; i < y_size; i++) |
576: { |
577: for (j = 0; j < num_threads; j++) |
578: { |
579: y_data[i] += y_data_expand[j*y_size + i]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.47 |
CQA speedup if FP arith vectorized | 1.71 |
CQA speedup if fully vectorized | 7.29 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.45 |
Bottlenecks | |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source | csr_matvec.c:560-560,csr_matvec.c:573-579 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 2.72 |
CQA cycles if FP arith vectorized | 2.33 |
CQA cycles if fully vectorized | 0.55 |
Front-end cycles | 4.00 |
DIV/SQRT cycles | 2.07 |
P0 cycles | 2.77 |
P1 cycles | 0.56 |
P2 cycles | 0.56 |
P3 cycles | 0.50 |
P4 cycles | 2.63 |
P5 cycles | 2.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 2.00 |
P10 cycles | 0.56 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 8.07 |
Stall cycles (UFS) | 3.47 |
Nb insns | 24.00 |
Nb uops | 24.00 |
Nb loads | 1.67 |
Nb stores | 1.00 |
Nb stack references | 0.67 |
FLOP/cycle | 0.67 |
Nb FLOP add-sub | 2.67 |
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 | 5.41 |
Bytes prefetched | 0.00 |
Bytes loaded | 13.33 |
Bytes stored | 8.00 |
Stride 0 | 1.33 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.67 |
Stride indirect | 0.00 |
Vectorization ratio all | 22.38 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 16.67 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 34.29 |
Vector-efficiency ratio all | 15.30 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 14.58 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 16.79 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.80 |
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 | 1.67 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source | csr_matvec.c:560-560,csr_matvec.c:573-579 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.00 |
CQA cycles if no scalar integer | 1.67 |
CQA cycles if FP arith vectorized | 3.00 |
CQA cycles if fully vectorized | 0.38 |
Front-end cycles | 3.00 |
DIV/SQRT cycles | 1.40 |
P0 cycles | 1.80 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 0.50 |
P4 cycles | 1.40 |
P5 cycles | 1.40 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 1.40 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 3.10 |
Stall cycles (UFS) | 0.00 |
Nb insns | 18.00 |
Nb uops | 18.00 |
Nb loads | 1.00 |
Nb stores | 1.00 |
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 | 8.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
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 | 1.48 |
CQA speedup if FP arith vectorized | 2.58 |
CQA speedup if fully vectorized | 7.29 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.48 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source | csr_matvec.c:560-560,csr_matvec.c:573-579 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.17 |
CQA cycles if no scalar integer | 3.50 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 0.71 |
Front-end cycles | 5.17 |
DIV/SQRT cycles | 2.70 |
P0 cycles | 3.50 |
P1 cycles | 0.67 |
P2 cycles | 0.67 |
P3 cycles | 0.50 |
P4 cycles | 3.50 |
P5 cycles | 2.70 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 2.60 |
P10 cycles | 0.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 10.33 |
Stall cycles (UFS) | 4.32 |
Nb insns | 31.00 |
Nb uops | 31.00 |
Nb loads | 2.00 |
Nb stores | 1.00 |
Nb stack references | 1.00 |
FLOP/cycle | 0.77 |
Nb FLOP add-sub | 4.00 |
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 | 4.65 |
Bytes prefetched | 0.00 |
Bytes loaded | 16.00 |
Bytes stored | 8.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 30.77 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 25.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 42.86 |
Vector-efficiency ratio all | 16.35 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 15.63 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 17.86 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.28 |
CQA speedup if FP arith vectorized | 1.92 |
CQA speedup if fully vectorized | 6.81 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.28 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source | csr_matvec.c:560-560,csr_matvec.c:573-579 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.83 |
CQA cycles if no scalar integer | 3.00 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 0.56 |
Front-end cycles | 3.83 |
DIV/SQRT cycles | 2.10 |
P0 cycles | 3.00 |
P1 cycles | 0.67 |
P2 cycles | 0.67 |
P3 cycles | 0.50 |
P4 cycles | 3.00 |
P5 cycles | 1.90 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 2.00 |
P10 cycles | 0.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 10.78 |
Stall cycles (UFS) | 6.10 |
Nb insns | 23.00 |
Nb uops | 23.00 |
Nb loads | 2.00 |
Nb stores | 1.00 |
Nb stack references | 1.00 |
FLOP/cycle | 1.04 |
Nb FLOP add-sub | 4.00 |
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 | 6.26 |
Bytes prefetched | 0.00 |
Bytes loaded | 16.00 |
Bytes stored | 8.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 36.36 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 25.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 60.00 |
Vector-efficiency ratio all | 17.05 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 15.63 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 20.00 |
Path / |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source file and lines | csr_matvec.c:560-579 |
Module | libseq_mv.so |
nb instructions | 24 |
nb uops | 24 |
loop length | 106 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 2.33 |
used ymm registers | 1.33 |
used zmm registers | 0 |
nb stack references | 0.67 |
micro-operation queue | 4.00 cycles |
front end | 4.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.07 | 2.63 | 0.56 | 0.56 | 0.50 | 2.63 | 2.00 | 0.50 | 0.50 | 0.50 | 2.00 | 0.56 |
cycles | 2.07 | 2.77 | 0.56 | 0.56 | 0.50 | 2.63 | 2.00 | 0.50 | 0.50 | 0.50 | 2.00 | 0.56 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 8.07 |
Stall cycles | 3.47 |
ROB full (events) | 3.77 |
Front-end | 4.00 |
Dispatch | 2.77 |
Data deps. | 1.00 |
Overall L1 | 4.00 |
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 | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 33% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 22% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 16% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 34% |
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 | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 16% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 16% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 15% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 14% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 16% |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source file and lines | csr_matvec.c:560-579 |
Module | libseq_mv.so |
nb instructions | 18 |
nb uops | 18 |
loop length | 82 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.00 cycles |
front end | 3.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.40 | 1.40 | 0.33 | 0.33 | 0.50 | 1.40 | 1.40 | 0.50 | 0.50 | 0.50 | 1.40 | 0.33 |
cycles | 1.40 | 1.80 | 0.33 | 0.33 | 0.50 | 1.40 | 1.40 | 0.50 | 0.50 | 0.50 | 1.40 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 3.10 |
Stall cycles | 0.00 |
Front-end | 3.00 |
Dispatch | 1.80 |
Data deps. | 1.00 |
Overall L1 | 3.00 |
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 | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
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 | 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 | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
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) |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD %XMM2,(%R11,%R8,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RCX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
LEA 0x1(%RSI),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JE c250 <hypre_CSRMatrixMatvecT.extracted.49+0x210> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA (%RAX,%RSI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVSD (%R11,%R8,8),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
AND $-0x4,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
JE c580 <hypre_CSRMatrixMatvecT.extracted.49+0x540> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R12,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB %R9,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
IMUL %R13,%R9 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RDI,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
LEA (%RBX,%R9,8),%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP c4c0 <hypre_CSRMatrixMatvecT.extracted.49+0x480> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source file and lines | csr_matvec.c:560-579 |
Module | libseq_mv.so |
nb instructions | 31 |
nb uops | 31 |
loop length | 136 |
used x86 registers | 12 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 5.17 cycles |
front end | 5.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.70 | 3.50 | 0.67 | 0.67 | 0.50 | 3.50 | 2.70 | 0.50 | 0.50 | 0.50 | 2.60 | 0.67 |
cycles | 2.70 | 3.50 | 0.67 | 0.67 | 0.50 | 3.50 | 2.70 | 0.50 | 0.50 | 0.50 | 2.60 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 10.33 |
Stall cycles | 4.32 |
ROB full (events) | 4.47 |
Front-end | 5.17 |
Dispatch | 3.50 |
Data deps. | 1.00 |
Overall L1 | 5.17 |
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 | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 50% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 30% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 42% |
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 | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 18% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 16% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 16% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 15% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 17% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD %XMM2,(%R11,%R8,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RCX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
LEA 0x1(%RSI),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JE c250 <hypre_CSRMatrixMatvecT.extracted.49+0x210> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA (%RAX,%RSI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVSD (%R11,%R8,8),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
AND $-0x4,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
JE c580 <hypre_CSRMatrixMatvecT.extracted.49+0x540> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA -0x1(%R9),%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VXORPD %XMM3,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VPBROADCASTQ %R8,%YMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VEXTRACTF128 $0x1,%YMM3,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPD %XMM4,%XMM3,%XMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSHUFPD $0x1,%XMM3,%XMM3,%XMM4 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDSD %XMM4,%XMM3,%XMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDSD %XMM3,%XMM2,%XMM2 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
CMP %R12,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x58(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JE c4c0 <hypre_CSRMatrixMatvecT.extracted.49+0x480> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP c583 <hypre_CSRMatrixMatvecT.extracted.49+0x543> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
MOV %R12,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB %R9,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
IMUL %R13,%R9 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RDI,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
LEA (%RBX,%R9,8),%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP c4c0 <hypre_CSRMatrixMatvecT.extracted.49+0x480> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source file and lines | csr_matvec.c:560-579 |
Module | libseq_mv.so |
nb instructions | 23 |
nb uops | 23 |
loop length | 100 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 3.83 cycles |
front end | 3.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.10 | 3.00 | 0.67 | 0.67 | 0.50 | 3.00 | 1.90 | 0.50 | 0.50 | 0.50 | 2.00 | 0.67 |
cycles | 2.10 | 3.00 | 0.67 | 0.67 | 0.50 | 3.00 | 1.90 | 0.50 | 0.50 | 0.50 | 2.00 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 10.78 |
Stall cycles | 6.10 |
ROB full (events) | 6.85 |
Front-end | 3.83 |
Dispatch | 3.00 |
Data deps. | 1.00 |
Overall L1 | 3.83 |
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 | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 50% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 36% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 60% |
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 | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 18% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 16% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 17% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 15% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 20% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD %XMM2,(%R11,%R8,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RCX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
LEA 0x1(%RSI),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JE c250 <hypre_CSRMatrixMatvecT.extracted.49+0x210> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA (%RAX,%RSI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVSD (%R11,%R8,8),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
AND $-0x4,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
JE c580 <hypre_CSRMatrixMatvecT.extracted.49+0x540> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA -0x1(%R9),%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VXORPD %XMM3,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VPBROADCASTQ %R8,%YMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VEXTRACTF128 $0x1,%YMM3,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPD %XMM4,%XMM3,%XMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSHUFPD $0x1,%XMM3,%XMM3,%XMM4 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDSD %XMM4,%XMM3,%XMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDSD %XMM3,%XMM2,%XMM2 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
CMP %R12,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x58(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JE c4c0 <hypre_CSRMatrixMatvecT.extracted.49+0x480> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |