Loop Id: 176 | Module: exec | Source: advec_mom_kernel.f90:81-131 [...] | Coverage: 0.01% |
---|
Loop Id: 176 | Module: exec | Source: advec_mom_kernel.f90:81-131 [...] | Coverage: 0.01% |
---|
0x4344c0 MOVSXD %R14D,%RAX |
0x4344c3 MOV 0x120(%RSP),%RSI |
0x4344cb LEA (%RSI,%RAX,1),%R15 |
0x4344cf SUB 0x340(%RSP),%RAX |
0x4344d7 MOV %R9,%R14 |
0x4344da IMUL %RAX,%R14 |
0x4344de IMUL %R9,%R15 |
0x4344e2 IMUL %RAX,%R11 |
0x4344e6 MOV %R11,%R12 |
0x4344e9 XOR %EAX,%EAX |
0x4344eb VPBROADCASTQ %RAX,%ZMM7 |
0x4344f1 VPSUBQ %ZMM7,%ZMM0,%ZMM7 |
0x4344f7 VPCMPNLEUQ %ZMM1,%ZMM7,%K1 |
0x4344fe MOV 0xe8(%RSP),%R9 |
0x434506 ADD %R9,%R14 |
0x434509 ADD 0x2c0(%RSP),%RAX |
0x434511 MOV %RAX,%RSI |
0x434514 SUB 0x300(%RSP),%RSI |
0x43451c VMOVUPD -0x10(%R14,%RSI,8),%ZMM7{%K1}{z} |
0x434527 VMOVAPD %ZMM7,%ZMM6{%K1} |
0x43452d ADD %R9,%R15 |
0x434530 VMOVUPD -0x10(%R15,%RSI,8),%ZMM7{%K1}{z} |
0x43453b VMOVAPD %ZMM7,%ZMM5{%K1} |
0x434541 VADDPD %ZMM5,%ZMM6,%ZMM7 |
0x434547 ADD 0x18(%RSP),%RAX |
0x43454c VMOVUPD (%R15,%RAX,8),%ZMM8{%K1}{z} |
0x434553 VMOVAPD %ZMM8,%ZMM4{%K1} |
0x434559 VMOVUPD (%R14,%RAX,8),%ZMM8{%K1}{z} |
0x434560 VMOVAPD %ZMM8,%ZMM3{%K1} |
0x434566 VADDPD %ZMM3,%ZMM4,%ZMM8 |
0x43456c VADDPD %ZMM8,%ZMM7,%ZMM7 |
0x434572 VMULPD %ZMM2,%ZMM7,%ZMM7 |
0x434578 ADD 0x50(%RSP),%R12 |
0x43457d VMOVUPD %ZMM7,-0x10(%R12,%RSI,8){%K1} |
0x434588 JMP 434590 |
0x434590 LEA 0x1(%RDI),%EAX |
0x434593 INC %EDX |
0x434595 CMP %ECX,%EDI |
0x434597 MOV %EAX,%EDI |
0x434599 JE 431e32 |
0x43459f TEST %R13D,%R13D |
0x4345a2 JS 434590 |
0x4345a4 MOV 0x280(%RSP),%RAX |
0x4345ac LEA (%RAX,%RDI,1),%R14D |
0x4345b0 MOV 0x110(%RSP),%RAX |
0x4345b8 MOV (%RAX),%R9 |
0x4345bb MOV 0x400(%RSP),%RAX |
0x4345c3 MOV (%RAX),%R11 |
0x4345c6 TEST %R10,%R10 |
0x4345c9 JE 4344c0 |
0x4345cf MOV %ECX,%EBX |
0x4345d1 MOV %R13D,%ECX |
0x4345d4 MOVSXD %EDX,%RSI |
0x4345d7 MOV 0x120(%RSP),%R15 |
0x4345df LEA (%R15,%RSI,1),%RAX |
0x4345e3 ADD %R8,%RSI |
0x4345e6 MOVSXD %R14D,%R12 |
0x4345e9 ADD %R12,%R15 |
0x4345ec SUB 0x340(%RSP),%R12 |
0x4345f4 MOV %R9,%R14 |
0x4345f7 IMUL %R12,%R14 |
0x4345fb IMUL %R9,%R15 |
0x4345ff IMUL %R11,%R12 |
0x434603 IMUL %R9,%RAX |
0x434607 MOV 0x28(%RSP),%R13 |
0x43460c ADD %R13,%RAX |
0x43460f IMUL %RSI,%R9 |
0x434613 ADD %R13,%R9 |
0x434616 IMUL %R11,%RSI |
0x43461a ADD 0x40(%RSP),%RSI |
0x43461f XOR %R11D,%R11D |
0x434622 NOPW %CS:(%RAX,%RAX,1) |
(177) 0x434630 VMOVUPD -0x8(%R9,%R11,8),%ZMM7 |
(177) 0x43463b VADDPD -0x8(%RAX,%R11,8),%ZMM7,%ZMM7 |
(177) 0x434646 VADDPD (%RAX,%R11,8),%ZMM7,%ZMM7 |
(177) 0x43464d VADDPD (%R9,%R11,8),%ZMM7,%ZMM7 |
(177) 0x434654 VMULPD %ZMM2,%ZMM7,%ZMM7 |
(177) 0x43465a VMOVUPD %ZMM7,(%RSI,%R11,8) |
(177) 0x434661 ADD $0x8,%R11 |
(177) 0x434665 CMP %R10,%R11 |
(177) 0x434668 JB 434630 |
0x43466a MOV %R10,%RAX |
0x43466d CMP 0x20(%RSP),%R10 |
0x434672 MOV %ECX,%R13D |
0x434675 MOV %EBX,%ECX |
0x434677 JNE 4344eb |
0x43467d JMP 434590 |
/scratch_na/users/xoserete/qaas_runs/171-215-0463/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/advec_mom_kernel.f90: 81 - 131 |
-------------------------------------------------------------------------------- |
81: IF(mom_sweep.EQ.1)THEN ! x 1 |
[...] |
126: DO k=y_min,y_max+1 |
127: !$OMP SIMD |
128: DO j=x_min-2,x_max+2 |
129: ! Find staggered mesh mass fluxes, nodal masses and volumes. |
130: node_flux(j,k)=0.25_8*(mass_flux_x(j,k-1 )+mass_flux_x(j ,k) & |
131: +mass_flux_x(j+1,k-1)+mass_flux_x(j+1,k)) |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.69 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.76 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.24 |
Bottlenecks | |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source | advec_mom_kernel.f90:81-81,advec_mom_kernel.f90:126-131 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 7.57 |
CQA cycles if no scalar integer | 4.48 |
CQA cycles if FP arith vectorized | 7.57 |
CQA cycles if fully vectorized | 4.29 |
Front-end cycles | 6.79 |
DIV/SQRT cycles | 4.58 |
P0 cycles | 6.62 |
P1 cycles | 3.75 |
P2 cycles | 3.75 |
P3 cycles | 0.25 |
P4 cycles | 4.55 |
P5 cycles | 4.47 |
P6 cycles | 0.25 |
P7 cycles | 0.25 |
P8 cycles | 0.25 |
P9 cycles | 4.55 |
P10 cycles | 3.75 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 7.00 - 7.25 |
Stall cycles (UFS) | 0.00 - 0.14 |
Nb insns | 41.75 |
Nb uops | 40.75 |
Nb loads | 11.25 |
Nb stores | 0.50 |
Nb stack references | 7.75 |
FLOP/cycle | 2.11 |
Nb FLOP add-sub | 12.00 |
Nb FLOP mul | 4.00 |
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 | 25.16 |
Bytes prefetched | 0.00 |
Bytes loaded | 202.00 |
Bytes stored | 32.00 |
Stride 0 | 0.75 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 4.75 |
Stride indirect | 0.00 |
Vectorization ratio all | 28.40 |
Vectorization ratio load | 35.71 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 33.33 |
Vectorization ratio add_sub | 36.67 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 24.55 |
Vector-efficiency ratio all | 34.52 |
Vector-efficiency ratio load | 43.75 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 41.67 |
Vector-efficiency ratio add_sub | 41.93 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 30.16 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 16.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.00 |
Bottlenecks | |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source | advec_mom_kernel.f90:81-81,advec_mom_kernel.f90:126-131 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.00 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 0.13 |
Front-end cycles | 1.00 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 1.00 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 1.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 1.07 - 2.05 |
Stall cycles (UFS) | 0.00 - 0.57 |
Nb insns | 7.00 |
Nb uops | 6.00 |
Nb loads | 0.00 |
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 | 0.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 0.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
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 | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 6.25 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 6.25 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 6.25 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.53 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.17 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.40 |
Bottlenecks | micro-operation queue, |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source | advec_mom_kernel.f90:81-81,advec_mom_kernel.f90:126-131 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 8.00 |
CQA cycles if no scalar integer | 3.17 |
CQA cycles if FP arith vectorized | 8.00 |
CQA cycles if fully vectorized | 6.85 |
Front-end cycles | 8.00 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 5.73 |
P1 cycles | 5.33 |
P2 cycles | 5.33 |
P3 cycles | 0.50 |
P4 cycles | 5.00 |
P5 cycles | 5.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 5.00 |
P10 cycles | 5.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 8.32 |
Stall cycles (UFS) | 0.00 |
Nb insns | 50.00 |
Nb uops | 48.00 |
Nb loads | 16.00 |
Nb stores | 1.00 |
Nb stack references | 10.00 |
FLOP/cycle | 4.00 |
Nb FLOP add-sub | 24.00 |
Nb FLOP mul | 8.00 |
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 | 52.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 352.00 |
Bytes stored | 64.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 6.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 65.22 |
Vectorization ratio load | 57.14 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 50.00 |
Vectorization ratio add_sub | 80.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 62.50 |
Vector-efficiency ratio all | 68.75 |
Vector-efficiency ratio load | 62.50 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 56.25 |
Vector-efficiency ratio add_sub | 81.25 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 65.63 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.52 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.29 |
Bottlenecks | P1, |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source | advec_mom_kernel.f90:81-81,advec_mom_kernel.f90:126-131 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 9.27 |
CQA cycles if no scalar integer | 9.27 |
CQA cycles if FP arith vectorized | 9.27 |
CQA cycles if fully vectorized | 0.80 |
Front-end cycles | 7.17 |
DIV/SQRT cycles | 4.80 |
P0 cycles | 9.27 |
P1 cycles | 3.33 |
P2 cycles | 3.33 |
P3 cycles | 0.00 |
P4 cycles | 4.80 |
P5 cycles | 4.60 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 4.80 |
P10 cycles | 3.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 7.35 |
Stall cycles (UFS) | 0.00 |
Nb insns | 43.00 |
Nb uops | 43.00 |
Nb loads | 10.00 |
Nb stores | 0.00 |
Nb stack references | 8.00 |
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 | 8.63 |
Bytes prefetched | 0.00 |
Bytes loaded | 80.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 4.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 9.87 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 10.42 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 8.13 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.14 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.17 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.05 |
Bottlenecks | micro-operation queue, |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source | advec_mom_kernel.f90:81-81,advec_mom_kernel.f90:126-131 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 11.00 |
CQA cycles if no scalar integer | 3.50 |
CQA cycles if FP arith vectorized | 11.00 |
CQA cycles if fully vectorized | 9.39 |
Front-end cycles | 11.00 |
DIV/SQRT cycles | 7.50 |
P0 cycles | 10.47 |
P1 cycles | 6.33 |
P2 cycles | 6.33 |
P3 cycles | 0.50 |
P4 cycles | 7.40 |
P5 cycles | 7.30 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 7.40 |
P10 cycles | 6.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 11.27 - 11.28 |
Stall cycles (UFS) | 0.00 |
Nb insns | 67.00 |
Nb uops | 66.00 |
Nb loads | 19.00 |
Nb stores | 1.00 |
Nb stack references | 13.00 |
FLOP/cycle | 2.91 |
Nb FLOP add-sub | 24.00 |
Nb FLOP mul | 8.00 |
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 | 40.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 376.00 |
Bytes stored | 64.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 9.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 48.39 |
Vectorization ratio load | 50.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 50.00 |
Vectorization ratio add_sub | 66.67 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 35.71 |
Vector-efficiency ratio all | 53.23 |
Vector-efficiency ratio load | 56.25 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 56.25 |
Vector-efficiency ratio add_sub | 69.79 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 40.63 |
Path / |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source file and lines | advec_mom_kernel.f90:81-131 |
Module | exec |
nb instructions | 41.75 |
nb uops | 40.75 |
loop length | 201.75 |
used x86 registers | 12 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 4.50 |
nb stack references | 7.75 |
micro-operation queue | 6.79 cycles |
front end | 6.79 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.58 | 4.85 | 3.75 | 3.75 | 0.25 | 4.55 | 4.48 | 0.25 | 0.25 | 0.25 | 4.55 | 3.75 |
cycles | 4.58 | 6.62 | 3.75 | 3.75 | 0.25 | 4.55 | 4.48 | 0.25 | 0.25 | 0.25 | 4.55 | 3.75 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 7.00-7.25 |
Stall cycles | 0.00-0.14 |
Front-end | 6.79 |
Dispatch | 6.62 |
Data deps. | 2.00 |
Overall L1 | 7.57 |
all | 7% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 20% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 8% |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 28% |
load | 35% |
store | 100% |
mul | 33% |
add-sub | 36% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 24% |
all | 15% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 27% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 15% |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 34% |
load | 43% |
store | 100% |
mul | 41% |
add-sub | 41% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 30% |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source file and lines | advec_mom_kernel.f90:81-131 |
Module | exec |
nb instructions | 7 |
nb uops | 6 |
loop length | 20 |
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 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.00 |
cycles | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 1.07-2.05 |
Stall cycles | 0.00-0.57 |
Front-end | 1.00 |
Dispatch | 1.00 |
Data deps. | 2.00 |
Overall L1 | 2.00 |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 6% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 6% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LEA 0x1(%RDI),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
INC %EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP %ECX,%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EAX,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 431e32 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x7a2> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %R13D,%R13D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 434590 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2f00> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source file and lines | advec_mom_kernel.f90:81-131 |
Module | exec |
nb instructions | 50 |
nb uops | 48 |
loop length | 265 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 9 |
nb stack references | 10 |
ADD-SUB / MUL ratio | 3.00 |
micro-operation queue | 8.00 cycles |
front end | 8.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 5.00 | 5.33 | 5.33 | 0.50 | 5.00 | 5.00 | 0.50 | 0.50 | 0.50 | 5.00 | 5.33 |
cycles | 5.00 | 5.73 | 5.33 | 5.33 | 0.50 | 5.00 | 5.00 | 0.50 | 0.50 | 0.50 | 5.00 | 5.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 8.32 |
Stall cycles | 0.00 |
Front-end | 8.00 |
Dispatch | 5.73 |
Data deps. | 2.00 |
Overall L1 | 8.00 |
all | 20% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 25% |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 65% |
load | 57% |
store | 100% |
mul | 50% |
add-sub | 80% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 62% |
all | 28% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 53% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 31% |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 68% |
load | 62% |
store | 100% |
mul | 56% |
add-sub | 81% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 65% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD %R14D,%RAX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
MOV 0x120(%RSP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RSI,%RAX,1),%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
SUB 0x340(%RSP),%RAX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOV %R9,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %RAX,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R9,%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RAX,%R11 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %R11,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VPBROADCASTQ %RAX,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPSUBQ %ZMM7,%ZMM0,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 |
VPCMPNLEUQ %ZMM1,%ZMM7,%K1 | |||||||||||||||
MOV 0xe8(%RSP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R9,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD 0x2c0(%RSP),%RAX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB 0x300(%RSP),%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 |
VMOVUPD -0x10(%R14,%RSI,8),%ZMM7{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VMOVAPD %ZMM7,%ZMM6{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
ADD %R9,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVUPD -0x10(%R15,%RSI,8),%ZMM7{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VMOVAPD %ZMM7,%ZMM5{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VADDPD %ZMM5,%ZMM6,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD 0x18(%RSP),%RAX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
VMOVUPD (%R15,%RAX,8),%ZMM8{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VMOVAPD %ZMM8,%ZMM4{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VMOVUPD (%R14,%RAX,8),%ZMM8{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VMOVAPD %ZMM8,%ZMM3{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VADDPD %ZMM3,%ZMM4,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDPD %ZMM8,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMULPD %ZMM2,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD 0x50(%RSP),%R12 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
VMOVUPD %ZMM7,-0x10(%R12,%RSI,8){%K1} | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
JMP 434590 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2f00> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RDI),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
INC %EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP %ECX,%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EAX,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 431e32 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x7a2> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %R13D,%R13D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 434590 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2f00> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x280(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RAX,%RDI,1),%R14D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
MOV 0x110(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x400(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %R10,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 4344c0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2e30> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source file and lines | advec_mom_kernel.f90:81-131 |
Module | exec |
nb instructions | 43 |
nb uops | 43 |
loop length | 184 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 7.17 cycles |
front end | 7.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.80 | 6.00 | 3.33 | 3.33 | 0.00 | 4.80 | 4.60 | 0.00 | 0.00 | 0.00 | 4.80 | 3.33 |
cycles | 4.80 | 9.27 | 3.33 | 3.33 | 0.00 | 4.80 | 4.60 | 0.00 | 0.00 | 0.00 | 4.80 | 3.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 7.35 |
Stall cycles | 0.00 |
Front-end | 7.17 |
Dispatch | 9.27 |
Data deps. | 2.00 |
Overall L1 | 9.27 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 9% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 10% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 8% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LEA 0x1(%RDI),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
INC %EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP %ECX,%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EAX,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 431e32 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x7a2> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %R13D,%R13D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 434590 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2f00> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x280(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RAX,%RDI,1),%R14D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
MOV 0x110(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x400(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %R10,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 4344c0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2e30> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %ECX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOVSXD %EDX,%RSI | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
MOV 0x120(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%R15,%RSI,1),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
ADD %R8,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOVSXD %R14D,%R12 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
ADD %R12,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
SUB 0x340(%RSP),%R12 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOV %R9,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R12,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R9,%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R11,%R12 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R9,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x28(%RSP),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R13,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
IMUL %RSI,%R9 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %R13,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
IMUL %R11,%RSI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD 0x40(%RSP),%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 |
XOR %R11D,%R11D | 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 |
MOV %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP 0x20(%RSP),%R10 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOV %ECX,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %EBX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 4344eb <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2e5b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 434590 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2f00> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source file and lines | advec_mom_kernel.f90:81-131 |
Module | exec |
nb instructions | 67 |
nb uops | 66 |
loop length | 338 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 9 |
nb stack references | 13 |
ADD-SUB / MUL ratio | 3.00 |
micro-operation queue | 11.00 cycles |
front end | 11.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 7.50 | 7.40 | 6.33 | 6.33 | 0.50 | 7.40 | 7.30 | 0.50 | 0.50 | 0.50 | 7.40 | 6.33 |
cycles | 7.50 | 10.47 | 6.33 | 6.33 | 0.50 | 7.40 | 7.30 | 0.50 | 0.50 | 0.50 | 7.40 | 6.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 11.27-11.28 |
Stall cycles | 0.00 |
Front-end | 11.00 |
Dispatch | 10.47 |
Data deps. | 2.00 |
Overall L1 | 11.00 |
all | 11% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 10% |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 48% |
load | 50% |
store | 100% |
mul | 50% |
add-sub | 66% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 35% |
all | 19% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 39% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 16% |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 53% |
load | 56% |
store | 100% |
mul | 56% |
add-sub | 69% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 40% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VPBROADCASTQ %RAX,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPSUBQ %ZMM7,%ZMM0,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 |
VPCMPNLEUQ %ZMM1,%ZMM7,%K1 | |||||||||||||||
MOV 0xe8(%RSP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R9,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD 0x2c0(%RSP),%RAX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB 0x300(%RSP),%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 |
VMOVUPD -0x10(%R14,%RSI,8),%ZMM7{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VMOVAPD %ZMM7,%ZMM6{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
ADD %R9,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVUPD -0x10(%R15,%RSI,8),%ZMM7{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VMOVAPD %ZMM7,%ZMM5{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VADDPD %ZMM5,%ZMM6,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD 0x18(%RSP),%RAX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
VMOVUPD (%R15,%RAX,8),%ZMM8{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VMOVAPD %ZMM8,%ZMM4{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VMOVUPD (%R14,%RAX,8),%ZMM8{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VMOVAPD %ZMM8,%ZMM3{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VADDPD %ZMM3,%ZMM4,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VADDPD %ZMM8,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMULPD %ZMM2,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD 0x50(%RSP),%R12 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
VMOVUPD %ZMM7,-0x10(%R12,%RSI,8){%K1} | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
JMP 434590 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2f00> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RDI),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
INC %EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP %ECX,%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EAX,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 431e32 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x7a2> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %R13D,%R13D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 434590 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2f00> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x280(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RAX,%RDI,1),%R14D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
MOV 0x110(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x400(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %R10,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 4344c0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2e30> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %ECX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOVSXD %EDX,%RSI | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
MOV 0x120(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%R15,%RSI,1),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
ADD %R8,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOVSXD %R14D,%R12 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
ADD %R12,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
SUB 0x340(%RSP),%R12 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOV %R9,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R12,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R9,%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R11,%R12 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R9,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x28(%RSP),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R13,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
IMUL %RSI,%R9 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %R13,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
IMUL %R11,%RSI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD 0x40(%RSP),%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 |
XOR %R11D,%R11D | 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 |
MOV %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP 0x20(%RSP),%R10 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOV %ECX,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %EBX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 4344eb <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x2e5b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |