Loop Id: 174 | Module: exec | Source: advec_mom_kernel.f90:81-131 [...] | Coverage: 0.01% |
---|
Loop Id: 174 | Module: exec | Source: advec_mom_kernel.f90:81-131 [...] | Coverage: 0.01% |
---|
0x435100 MOV 0x2c0(%RSP),%RAX |
0x435108 LEA 0x1(%R12,%RAX,1),%R14 |
0x43510d SUB 0x18(%RSP),%R12 |
0x435112 MOV %RDI,%RAX |
0x435115 IMUL %R12,%RAX |
0x435119 IMUL %RDI,%R14 |
0x43511d IMUL %R10,%R12 |
0x435121 XOR %R10D,%R10D |
0x435124 VPBROADCASTQ %R10,%ZMM7 |
0x43512a VPSUBQ %ZMM7,%ZMM0,%ZMM7 |
0x435130 VPCMPNLEUQ %ZMM1,%ZMM7,%K1 |
0x435137 MOV 0x110(%RSP),%R9 |
0x43513f ADD %R9,%RAX |
0x435142 ADD 0x1e0(%RSP),%R10 |
0x43514a MOV %R10,%RDI |
0x43514d SUB %R11,%RDI |
0x435150 VMOVUPD -0x10(%RAX,%RDI,8),%ZMM7{%K1}{z} |
0x43515b VMOVAPD %ZMM7,%ZMM6{%K1} |
0x435161 ADD %R9,%R14 |
0x435164 VMOVUPD -0x10(%R14,%RDI,8),%ZMM7{%K1}{z} |
0x43516f VMOVAPD %ZMM7,%ZMM5{%K1} |
0x435175 VADDPD %ZMM5,%ZMM6,%ZMM7 |
0x43517b MOV %R11,%R9 |
0x43517e NOT %R9 |
0x435181 ADD %R10,%R9 |
0x435184 VMOVUPD (%R14,%R9,8),%ZMM8{%K1}{z} |
0x43518b VMOVAPD %ZMM8,%ZMM4{%K1} |
0x435191 VMOVUPD (%RAX,%R9,8),%ZMM8{%K1}{z} |
0x435198 VMOVAPD %ZMM8,%ZMM3{%K1} |
0x43519e VADDPD %ZMM3,%ZMM4,%ZMM8 |
0x4351a4 VADDPD %ZMM8,%ZMM7,%ZMM7 |
0x4351aa VMULPD %ZMM2,%ZMM7,%ZMM7 |
0x4351b0 ADD 0x58(%RSP),%R12 |
0x4351b5 VMOVUPD %ZMM7,-0x10(%R12,%RDI,8){%K1} |
0x4351c0 JMP 4351d0 |
0x4351d0 LEA 0x1(%RDX),%EAX |
0x4351d3 INC %R15D |
0x4351d6 CMP %ECX,%EDX |
0x4351d8 MOV %EAX,%EDX |
0x4351da JE 432471 |
0x4351e0 TEST %ESI,%ESI |
0x4351e2 JS 4351d0 |
0x4351e4 MOV 0x90(%RSP),%RAX |
0x4351ec ADD %EDX,%EAX |
0x4351ee MOV 0x150(%RSP),%RDI |
0x4351f6 MOV (%RDI),%RDI |
0x4351f9 MOV 0x98(%RSP),%R9 |
0x435201 MOV (%R9),%R10 |
0x435204 MOVSXD %EAX,%R12 |
0x435207 TEST %R8,%R8 |
0x43520a JE 435100 |
0x435210 MOVSXD %R15D,%R13 |
0x435213 MOV 0x50(%RSP),%RAX |
0x435218 LEA (%RAX,%R13,1),%R9 |
0x43521c ADD 0x38(%RSP),%R13 |
0x435221 MOV 0x2c0(%RSP),%RAX |
0x435229 LEA 0x1(%R12,%RAX,1),%R14 |
0x43522e SUB 0x18(%RSP),%R12 |
0x435233 MOV %RDI,%RAX |
0x435236 IMUL %R12,%RAX |
0x43523a IMUL %RDI,%R14 |
0x43523e IMUL %R10,%R12 |
0x435242 IMUL %RDI,%R13 |
0x435246 IMUL %R9,%RDI |
0x43524a ADD %RBX,%RDI |
0x43524d ADD %RBX,%R13 |
0x435250 IMUL %R9,%R10 |
0x435254 ADD 0x20(%RSP),%R10 |
0x435259 XOR %R9D,%R9D |
0x43525c NOPL (%RAX) |
(175) 0x435260 VMOVUPD -0x8(%RDI,%R9,8),%ZMM7 |
(175) 0x43526b VADDPD -0x8(%R13,%R9,8),%ZMM7,%ZMM7 |
(175) 0x435276 VADDPD (%R13,%R9,8),%ZMM7,%ZMM7 |
(175) 0x43527e VADDPD (%RDI,%R9,8),%ZMM7,%ZMM7 |
(175) 0x435285 VMULPD %ZMM2,%ZMM7,%ZMM7 |
(175) 0x43528b VMOVUPD %ZMM7,(%R10,%R9,8) |
(175) 0x435292 ADD $0x8,%R9 |
(175) 0x435296 CMP %R8,%R9 |
(175) 0x435299 JB 435260 |
0x43529b MOV %R8,%R10 |
0x43529e CMP 0x28(%RSP),%R8 |
0x4352a3 JNE 435124 |
0x4352a9 JMP 4351d0 |
/scratch_na/users/xoserete/qaas_runs/171-415-7919/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/advec_mom_kernel.f90: 81 - 131 |
-------------------------------------------------------------------------------- |
81: IF(mom_sweep.EQ.1)THEN ! x 1 |
[...] |
126: DO k=y_min,y_max+1 |
127: !$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)) |
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 | 1.72 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.75 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.22 |
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 | 7.63 |
CQA cycles if no scalar integer | 4.43 |
CQA cycles if FP arith vectorized | 7.63 |
CQA cycles if fully vectorized | 4.36 |
Front-end cycles | 6.54 |
DIV/SQRT cycles | 4.58 |
P0 cycles | 7.32 |
P1 cycles | 3.58 |
P2 cycles | 3.58 |
P3 cycles | 0.25 |
P4 cycles | 4.60 |
P5 cycles | 4.53 |
P6 cycles | 0.25 |
P7 cycles | 0.25 |
P8 cycles | 0.25 |
P9 cycles | 4.60 |
P10 cycles | 3.58 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 6.88 - 7.12 |
Stall cycles (UFS) | 0.04 - 0.18 |
Nb insns | 40.50 |
Nb uops | 39.25 |
Nb loads | 10.75 |
Nb stores | 0.50 |
Nb stack references | 7.25 |
FLOP/cycle | 2.10 |
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 | 24.02 |
Bytes prefetched | 0.00 |
Bytes loaded | 198.00 |
Bytes stored | 32.00 |
Stride 0 | 0.75 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 5.50 |
Stride indirect | 0.00 |
Vectorization ratio all | 32.05 |
Vectorization ratio load | 41.27 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 50.00 |
Vectorization ratio add_sub | 30.95 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 26.39 |
Vector-efficiency ratio all | 37.98 |
Vector-efficiency ratio load | 48.61 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 56.25 |
Vector-efficiency ratio add_sub | 36.76 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 32.41 |
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 | 1.00 |
Bottlenecks | micro-operation queue, P0, P1, P5, P6, P10, |
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 | 1.00 |
CQA cycles if no scalar integer | 1.00 |
CQA cycles if FP arith vectorized | 1.00 |
CQA cycles if fully vectorized | 0.06 |
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 | 0 |
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 | 2.58 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.12 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.18 |
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 | 8.17 |
CQA cycles if no scalar integer | 3.17 |
CQA cycles if FP arith vectorized | 8.17 |
CQA cycles if fully vectorized | 7.30 |
Front-end cycles | 8.17 |
DIV/SQRT cycles | 5.40 |
P0 cycles | 6.93 |
P1 cycles | 4.67 |
P2 cycles | 4.67 |
P3 cycles | 0.50 |
P4 cycles | 5.40 |
P5 cycles | 5.40 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 5.40 |
P10 cycles | 4.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 8.48 |
Stall cycles (UFS) | 0.00 |
Nb insns | 51.00 |
Nb uops | 49.00 |
Nb loads | 14.00 |
Nb stores | 1.00 |
Nb stack references | 8.00 |
FLOP/cycle | 3.92 |
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 | 48.98 |
Bytes prefetched | 0.00 |
Bytes loaded | 336.00 |
Bytes stored | 64.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 7.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 68.18 |
Vectorization ratio load | 66.67 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 66.67 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 55.56 |
Vector-efficiency ratio all | 71.02 |
Vector-efficiency ratio load | 70.83 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | 69.79 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 59.03 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.92 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.55 |
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 | 10.07 |
CQA cycles if no scalar integer | 10.07 |
CQA cycles if FP arith vectorized | 10.07 |
CQA cycles if fully vectorized | 0.78 |
Front-end cycles | 6.50 |
DIV/SQRT cycles | 4.40 |
P0 cycles | 10.07 |
P1 cycles | 3.67 |
P2 cycles | 3.67 |
P3 cycles | 0.00 |
P4 cycles | 4.60 |
P5 cycles | 4.40 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 4.60 |
P10 cycles | 3.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 7.17 |
Stall cycles (UFS) | 0.16 |
Nb insns | 39.00 |
Nb uops | 39.00 |
Nb loads | 11.00 |
Nb stores | 0.00 |
Nb stack references | 9.00 |
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 | 8.74 |
Bytes prefetched | 0.00 |
Bytes loaded | 88.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 5.00 |
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 | 10.42 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 9.38 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 9.38 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.22 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.21 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.07 |
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 | 11.27 |
CQA cycles if no scalar integer | 3.50 |
CQA cycles if FP arith vectorized | 11.27 |
CQA cycles if fully vectorized | 9.30 |
Front-end cycles | 10.50 |
DIV/SQRT cycles | 7.50 |
P0 cycles | 11.27 |
P1 cycles | 6.00 |
P2 cycles | 6.00 |
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 | 6.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 10.78 |
Stall cycles (UFS) | 0.00 |
Nb insns | 65.00 |
Nb uops | 63.00 |
Nb loads | 18.00 |
Nb stores | 1.00 |
Nb stack references | 12.00 |
FLOP/cycle | 2.84 |
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 | 38.34 |
Bytes prefetched | 0.00 |
Bytes loaded | 368.00 |
Bytes stored | 64.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 10.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 60.00 |
Vectorization ratio load | 57.14 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 50.00 |
Vectorization ratio add_sub | 57.14 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 50.00 |
Vector-efficiency ratio all | 64.25 |
Vector-efficiency ratio load | 62.50 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 56.25 |
Vector-efficiency ratio add_sub | 61.61 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 55.00 |
Path / |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source file and lines | advec_mom_kernel.f90:81-131 |
Module | exec |
nb instructions | 40.50 |
nb uops | 39.25 |
loop length | 189.25 |
used x86 registers | 11.75 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 4.50 |
nb stack references | 7.25 |
micro-operation queue | 6.54 cycles |
front end | 6.54 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.58 | 5.20 | 3.58 | 3.58 | 0.25 | 4.60 | 4.53 | 0.25 | 0.25 | 0.25 | 4.60 | 3.58 |
cycles | 4.58 | 7.32 | 3.58 | 3.58 | 0.25 | 4.60 | 4.53 | 0.25 | 0.25 | 0.25 | 4.60 | 3.58 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 6.88-7.12 |
Stall cycles | 0.04-0.18 |
PRF_INT full (events) | 0.08 |
Front-end | 6.54 |
Dispatch | 7.32 |
Data deps. | 0.00 |
Overall L1 | 7.62 |
all | 9% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 14% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 9% |
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 | 32% |
load | 41% |
store | 100% |
mul | 50% |
add-sub | 30% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 26% |
all | 17% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 22% |
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 | 37% |
load | 48% |
store | 100% |
mul | 56% |
add-sub | 36% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 32% |
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) | 0.00 |
FE+BE cycles | 1.07-2.05 |
Stall cycles | 0.00-0.57 |
Front-end | 1.00 |
Dispatch | 1.00 |
Data deps. | 0.00 |
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 | 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(%RDX),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
INC %R15D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP %ECX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EAX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 432471 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x791> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %ESI,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 4351d0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x34f0> | 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 | 51 |
nb uops | 49 |
loop length | 258 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 9 |
nb stack references | 8 |
ADD-SUB / MUL ratio | 3.00 |
micro-operation queue | 8.17 cycles |
front end | 8.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.40 | 5.40 | 4.67 | 4.67 | 0.50 | 5.40 | 5.40 | 0.50 | 0.50 | 0.50 | 5.40 | 4.67 |
cycles | 5.40 | 6.93 | 4.67 | 4.67 | 0.50 | 5.40 | 5.40 | 0.50 | 0.50 | 0.50 | 5.40 | 4.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 8.48 |
Stall cycles | 0.00 |
Front-end | 8.17 |
Dispatch | 6.93 |
Data deps. | 0.00 |
Overall L1 | 8.17 |
all | 22% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 20% |
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 | 66% |
store | 100% |
mul | 100% |
add-sub | 66% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 55% |
all | 29% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 39% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 26% |
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 | 71% |
load | 70% |
store | 100% |
mul | 100% |
add-sub | 69% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 59% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x2c0(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA 0x1(%R12,%RAX,1),%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
SUB 0x18(%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 %RDI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R12,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RDI,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R10,%R12 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VPBROADCASTQ %R10,%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 0x110(%RSP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R9,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD 0x1e0(%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 %R10,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB %R11,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVUPD -0x10(%RAX,%RDI,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,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVUPD -0x10(%R14,%RDI,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 |
MOV %R11,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
NOT %R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %R10,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVUPD (%R14,%R9,8),%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 (%RAX,%R9,8),%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 0x58(%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,%RDI,8){%K1} | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
JMP 4351d0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x34f0> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RDX),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
INC %R15D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP %ECX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EAX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 432471 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x791> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %ESI,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 4351d0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x34f0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x90(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %EDX,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV 0x150(%RSP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x98(%RSP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVSXD %EAX,%R12 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
TEST %R8,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 435100 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x3420> | 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 | 39 |
nb uops | 39 |
loop length | 163 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 9 |
micro-operation queue | 6.50 cycles |
front end | 6.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.40 | 7.00 | 3.67 | 3.67 | 0.00 | 4.60 | 4.40 | 0.00 | 0.00 | 0.00 | 4.60 | 3.67 |
cycles | 4.40 | 10.07 | 3.67 | 3.67 | 0.00 | 4.60 | 4.40 | 0.00 | 0.00 | 0.00 | 4.60 | 3.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 7.17 |
Stall cycles | 0.16 |
PRF_INT full (events) | 0.33 |
Front-end | 6.50 |
Dispatch | 10.07 |
Data deps. | 0.00 |
Overall L1 | 10.07 |
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 | 10% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 9% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 9% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LEA 0x1(%RDX),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
INC %R15D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP %ECX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EAX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 432471 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x791> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %ESI,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 4351d0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x34f0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x90(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %EDX,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV 0x150(%RSP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x98(%RSP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVSXD %EAX,%R12 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
TEST %R8,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 435100 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x3420> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOVSXD %R15D,%R13 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
MOV 0x50(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RAX,%R13,1),%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
ADD 0x38(%RSP),%R13 | 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 0x2c0(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA 0x1(%R12,%RAX,1),%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
SUB 0x18(%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 %RDI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R12,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RDI,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R10,%R12 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RDI,%R13 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R9,%RDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %RBX,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
IMUL %R9,%R10 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD 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 |
XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R8,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP 0x28(%RSP),%R8 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JNE 435124 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x3444> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 4351d0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x34f0> | 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 | 65 |
nb uops | 63 |
loop length | 316 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 9 |
nb stack references | 12 |
ADD-SUB / MUL ratio | 3.00 |
micro-operation queue | 10.50 cycles |
front end | 10.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 7.50 | 7.40 | 6.00 | 6.00 | 0.50 | 7.40 | 7.30 | 0.50 | 0.50 | 0.50 | 7.40 | 6.00 |
cycles | 7.50 | 11.27 | 6.00 | 6.00 | 0.50 | 7.40 | 7.30 | 0.50 | 0.50 | 0.50 | 7.40 | 6.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 10.78 |
Stall cycles | 0.00 |
Front-end | 10.50 |
Dispatch | 11.27 |
Data deps. | 0.00 |
Overall L1 | 11.27 |
all | 16% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 25% |
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 | 60% |
load | 57% |
store | 100% |
mul | 50% |
add-sub | 57% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
all | 25% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 32% |
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 | 64% |
load | 62% |
store | 100% |
mul | 56% |
add-sub | 61% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 55% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VPBROADCASTQ %R10,%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 0x110(%RSP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R9,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD 0x1e0(%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 %R10,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB %R11,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVUPD -0x10(%RAX,%RDI,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,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVUPD -0x10(%R14,%RDI,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 |
MOV %R11,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
NOT %R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %R10,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVUPD (%R14,%R9,8),%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 (%RAX,%R9,8),%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 0x58(%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,%RDI,8){%K1} | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
JMP 4351d0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x34f0> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RDX),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
INC %R15D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP %ECX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EAX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 432471 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x791> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %ESI,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 4351d0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x34f0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x90(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %EDX,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV 0x150(%RSP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x98(%RSP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVSXD %EAX,%R12 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
TEST %R8,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 435100 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x3420> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOVSXD %R15D,%R13 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
MOV 0x50(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RAX,%R13,1),%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
ADD 0x38(%RSP),%R13 | 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 0x2c0(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA 0x1(%R12,%RAX,1),%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
SUB 0x18(%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 %RDI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R12,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RDI,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R10,%R12 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RDI,%R13 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R9,%RDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %RBX,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
IMUL %R9,%R10 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD 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 |
XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R8,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP 0x28(%RSP),%R8 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JNE 435124 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x3444> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |