Loop Id: 170 | Module: exec | Source: advec_mom_kernel.f90:81-184 [...] | Coverage: 0.01% |
---|
Loop Id: 170 | Module: exec | Source: advec_mom_kernel.f90:81-184 [...] | Coverage: 0.01% |
---|
0x432280 MOVSXD %R9D,%RAX |
0x432283 SUB 0x280(%RSP),%RAX |
0x43228b IMUL %RAX,%RSI |
0x43228f MOV 0x3c0(%RSP),%R15 |
0x432297 IMUL %RAX,%R15 |
0x43229b MOV 0x30(%RSP),%RBX |
0x4322a0 IMUL %RAX,%RBX |
0x4322a4 IMUL %RAX,%RDI |
0x4322a8 MOV %RDI,%R9 |
0x4322ab MOV %RSI,%R14 |
0x4322ae XOR %EAX,%EAX |
0x4322b0 VPBROADCASTQ %RAX,%ZMM7 |
0x4322b6 VPSUBQ %ZMM7,%ZMM0,%ZMM7 |
0x4322bc VPCMPNLEUQ %ZMM1,%ZMM7,%K1 |
0x4322c3 ADD 0xb0(%RSP),%R14 |
0x4322cb ADD 0x50(%RSP),%RAX |
0x4322d0 MOV %RAX,%RSI |
0x4322d3 SUB 0x340(%RSP),%RSI |
0x4322db VMOVUPD (%R14,%RSI,8),%ZMM7{%K1}{z} |
0x4322e2 VMOVAPD %ZMM7,%ZMM6{%K1} |
0x4322e8 ADD 0xf8(%RSP),%R15 |
0x4322f0 VMOVUPD (%R15,%RSI,8),%ZMM7{%K1}{z} |
0x4322f7 VMOVAPD %ZMM7,%ZMM5{%K1} |
0x4322fd ADD 0xd8(%RSP),%RBX |
0x432305 ADD 0x400(%RSP),%RAX |
0x43230d VMOVUPD (%RBX,%RAX,8),%ZMM7{%K1}{z} |
0x432314 VMOVAPD %ZMM7,%ZMM4{%K1} |
0x43231a VMOVAPD %ZMM5,%ZMM7 |
0x432320 VMOVUPD (%RBX,%RSI,8),%ZMM8{%K1}{z} |
0x432327 VFMADD213PD %ZMM4,%ZMM6,%ZMM7 |
0x43232d VMOVAPD %ZMM8,%ZMM3{%K1} |
0x432333 VSUBPD %ZMM3,%ZMM7,%ZMM7 |
0x432339 ADD 0xe0(%RSP),%R9 |
0x432341 VMOVUPD (%R9,%RSI,8),%ZMM8{%K1}{z} |
0x432348 VMOVAPD %ZMM8,%ZMM2{%K1} |
0x43234e VDIVPD %ZMM2,%ZMM7,%ZMM7 |
0x432354 VMOVUPD %ZMM7,(%R15,%RSI,8){%K1} |
0x43235b JMP 432360 |
0x432360 LEA 0x1(%RDX),%EAX |
0x432363 INC %R12D |
0x432366 CMP %ECX,%EDX |
0x432368 MOV %EAX,%EDX |
0x43236a JE 4320a7 |
0x432370 TEST %R11D,%R11D |
0x432373 JS 432360 |
0x432375 MOV 0x38(%RSP),%RAX |
0x43237a LEA (%RAX,%RDX,1),%R9D |
0x43237e MOV 0x118(%RSP),%RAX |
0x432386 MOV (%RAX),%RSI |
0x432389 MOV 0x1e0(%RSP),%RAX |
0x432391 MOV (%RAX),%RDI |
0x432394 TEST %R10,%R10 |
0x432397 JE 432280 |
0x43239d MOV %R11D,%ECX |
0x4323a0 MOVSXD %R12D,%R13 |
0x4323a3 ADD 0x2c0(%RSP),%R13 |
0x4323ab MOV 0x30(%RSP),%RBX |
0x4323b0 MOV %RBX,%RAX |
0x4323b3 IMUL %R13,%RAX |
0x4323b7 ADD 0x18(%RSP),%RAX |
0x4323bc MOV 0x3c0(%RSP),%R15 |
0x4323c4 MOV %R15,%R11 |
0x4323c7 IMUL %R13,%R11 |
0x4323cb ADD 0x60(%RSP),%R11 |
0x4323d0 MOVSXD %R9D,%R9 |
0x4323d3 SUB 0x280(%RSP),%R9 |
0x4323db MOV %RSI,%R14 |
0x4323de IMUL %R9,%R14 |
0x4323e2 IMUL %R9,%R15 |
0x4323e6 IMUL %R9,%RBX |
0x4323ea IMUL %RDI,%R9 |
0x4323ee IMUL %R13,%RDI |
0x4323f2 ADD 0x10(%RSP),%RDI |
0x4323f7 IMUL %RSI,%R13 |
0x4323fb ADD %R8,%R13 |
0x4323fe XOR %ESI,%ESI |
(171) 0x432400 VMOVUPD (%R13,%RSI,8),%ZMM7 |
(171) 0x432408 VMOVUPD (%R11,%RSI,8),%ZMM8 |
(171) 0x43240f VFMADD213PD -0x8(%RAX,%RSI,8),%ZMM7,%ZMM8 |
(171) 0x43241a VSUBPD (%RAX,%RSI,8),%ZMM8,%ZMM7 |
(171) 0x432421 VDIVPD (%RDI,%RSI,8),%ZMM7,%ZMM7 |
(171) 0x432428 VMOVUPD %ZMM7,(%R11,%RSI,8) |
(171) 0x43242f ADD $0x8,%RSI |
(171) 0x432433 CMP %R10,%RSI |
(171) 0x432436 JB 432400 |
0x432438 MOV %R10,%RAX |
0x43243b CMP 0x300(%RSP),%R10 |
0x432443 MOV %ECX,%R11D |
0x432446 MOV 0x120(%RSP),%ECX |
0x43244d JNE 4322b0 |
0x432453 JMP 432360 |
/scratch_na/users/xoserete/qaas_runs/171-215-0463/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/advec_mom_kernel.f90: 81 - 184 |
-------------------------------------------------------------------------------- |
81: IF(mom_sweep.EQ.1)THEN ! x 1 |
[...] |
181: DO k=y_min,y_max+1 |
182: !$OMP SIMD |
183: DO j=x_min,x_max+1 |
184: vel1 (j,k)=(vel1 (j,k)*node_mass_pre(j,k)+mom_flux(j-1,k)-mom_flux(j,k))/node_mass_post(j,k) |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.36 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.52 |
Bottlenecks | |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source | advec_mom_kernel.f90:81-81,advec_mom_kernel.f90:181-184 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 11.32 |
CQA cycles if no scalar integer | 11.32 |
CQA cycles if FP arith vectorized | 11.32 |
CQA cycles if fully vectorized | 8.34 |
Front-end cycles | 7.25 |
DIV/SQRT cycles | 4.92 |
P0 cycles | 7.97 |
P1 cycles | 5.00 |
P2 cycles | 5.00 |
P3 cycles | 0.25 |
P4 cycles | 4.90 |
P5 cycles | 4.83 |
P6 cycles | 0.25 |
P7 cycles | 0.25 |
P8 cycles | 0.25 |
P9 cycles | 4.90 |
P10 cycles | 5.00 |
P11 cycles | 8.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 10.54 - 10.78 |
Stall cycles (UFS) | 2.82 - 2.96 |
Nb insns | 43.50 |
Nb uops | 43.50 |
Nb loads | 15.00 |
Nb stores | 0.50 |
Nb stack references | 11.00 |
FLOP/cycle | 1.41 |
Nb FLOP add-sub | 4.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 4.00 |
Nb FLOP div | 4.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 18.83 |
Bytes prefetched | 0.00 |
Bytes loaded | 258.00 |
Bytes stored | 32.00 |
Stride 0 | 0.75 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 5.25 |
Stride indirect | 0.00 |
Vectorization ratio all | 30.62 |
Vectorization ratio load | 44.44 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 23.81 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | 100.00 |
Vectorization ratio other | 29.17 |
Vector-efficiency ratio all | 36.87 |
Vector-efficiency ratio load | 50.95 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 30.77 |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | 100.00 |
Vector-efficiency ratio other | 34.95 |
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.f90:181-184 |
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 | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.81 |
Bottlenecks | P0, |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source | advec_mom_kernel.f90:81-81,advec_mom_kernel.f90:181-184 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 16.00 |
CQA cycles if no scalar integer | 16.00 |
CQA cycles if FP arith vectorized | 16.00 |
CQA cycles if fully vectorized | 16.00 |
Front-end cycles | 8.83 |
DIV/SQRT cycles | 5.70 |
P0 cycles | 6.93 |
P1 cycles | 6.67 |
P2 cycles | 6.67 |
P3 cycles | 0.50 |
P4 cycles | 5.50 |
P5 cycles | 5.60 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 5.60 |
P10 cycles | 6.67 |
P11 cycles | 16.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 16.42 - 16.44 |
Stall cycles (UFS) | 6.90 - 6.92 |
Nb insns | 53.00 |
Nb uops | 53.00 |
Nb loads | 20.00 |
Nb stores | 1.00 |
Nb stack references | 13.00 |
FLOP/cycle | 2.00 |
Nb FLOP add-sub | 8.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 8.00 |
Nb FLOP div | 8.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 31.50 |
Bytes prefetched | 0.00 |
Bytes loaded | 440.00 |
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 | 73.91 |
Vectorization ratio load | 83.33 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 66.67 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | 100.00 |
Vectorization ratio other | 70.00 |
Vector-efficiency ratio all | 76.36 |
Vector-efficiency ratio load | 85.42 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 68.75 |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | 100.00 |
Vector-efficiency ratio other | 72.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 9.26 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.54 |
Bottlenecks | P1, |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source | advec_mom_kernel.f90:81-81,advec_mom_kernel.f90:181-184 |
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 | 11.27 |
CQA cycles if FP arith vectorized | 11.27 |
CQA cycles if fully vectorized | 1.22 |
Front-end cycles | 7.33 |
DIV/SQRT cycles | 4.80 |
P0 cycles | 11.27 |
P1 cycles | 4.67 |
P2 cycles | 4.67 |
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 | 4.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 8.16 |
Stall cycles (UFS) | 0.29 |
Nb insns | 44.00 |
Nb uops | 44.00 |
Nb loads | 14.00 |
Nb stores | 0.00 |
Nb stack references | 12.00 |
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 | 9.59 |
Bytes prefetched | 0.00 |
Bytes loaded | 108.00 |
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 | 10.94 |
Vector-efficiency ratio load | 11.81 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 11.46 |
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 | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.26 |
Bottlenecks | P0, |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source | advec_mom_kernel.f90:81-81,advec_mom_kernel.f90:181-184 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 16.00 |
CQA cycles if no scalar integer | 16.00 |
CQA cycles if FP arith vectorized | 16.00 |
CQA cycles if fully vectorized | 16.00 |
Front-end cycles | 11.83 |
DIV/SQRT cycles | 8.20 |
P0 cycles | 12.67 |
P1 cycles | 8.67 |
P2 cycles | 8.67 |
P3 cycles | 0.50 |
P4 cycles | 8.30 |
P5 cycles | 8.10 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 8.20 |
P10 cycles | 8.67 |
P11 cycles | 16.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 16.52 - 16.48 |
Stall cycles (UFS) | 4.08 - 4.07 |
Nb insns | 70.00 |
Nb uops | 71.00 |
Nb loads | 26.00 |
Nb stores | 1.00 |
Nb stack references | 19.00 |
FLOP/cycle | 2.00 |
Nb FLOP add-sub | 8.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 8.00 |
Nb FLOP div | 8.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 34.25 |
Bytes prefetched | 0.00 |
Bytes loaded | 484.00 |
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 | 48.57 |
Vectorization ratio load | 50.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 28.57 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | 100.00 |
Vectorization ratio other | 46.67 |
Vector-efficiency ratio all | 53.93 |
Vector-efficiency ratio load | 55.63 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 36.61 |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | 100.00 |
Vector-efficiency ratio other | 51.67 |
Path / |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source file and lines | advec_mom_kernel.f90:81-184 |
Module | exec |
nb instructions | 43.50 |
nb uops | 43.50 |
loop length | 213.75 |
used x86 registers | 12 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 4.50 |
nb stack references | 11 |
micro-operation queue | 7.25 cycles |
front end | 7.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.93 | 5.70 | 5.00 | 5.00 | 0.25 | 4.90 | 4.83 | 0.25 | 0.25 | 0.25 | 4.90 | 5.00 |
cycles | 4.93 | 7.97 | 5.00 | 5.00 | 0.25 | 4.90 | 4.83 | 0.25 | 0.25 | 0.25 | 4.90 | 5.00 |
Cycles executing div or sqrt instructions | 8.00 |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 10.54-10.78 |
Stall cycles | 2.82-2.96 |
PRF_INT full (events) | 3.13-3.13 |
Front-end | 7.25 |
Dispatch | 7.97 |
DIV/SQRT | 8.00 |
Data deps. | 2.00 |
Overall L1 | 11.32 |
all | 8% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 16% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 9% |
all | 100% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 30% |
load | 44% |
store | 100% |
mul | 0% |
add-sub | 23% |
fma | 100% |
div/sqrt | 100% |
other | 29% |
all | 17% |
load | 11% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 24% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 16% |
all | 100% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 36% |
load | 50% |
store | 100% |
mul | 12% |
add-sub | 30% |
fma | 100% |
div/sqrt | 100% |
other | 34% |
Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
Source file and lines | advec_mom_kernel.f90:81-184 |
Module | exec |
nb instructions | 7 |
nb uops | 6 |
loop length | 21 |
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(%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 %R12D | 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 4320a7 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xa17> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %R11D,%R11D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 432360 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xcd0> | 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.f90:81-184 |
Module | exec |
nb instructions | 53 |
nb uops | 53 |
loop length | 282 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 9 |
nb stack references | 13 |
micro-operation queue | 8.83 cycles |
front end | 8.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.70 | 5.60 | 6.67 | 6.67 | 0.50 | 5.50 | 5.60 | 0.50 | 0.50 | 0.50 | 5.60 | 6.67 |
cycles | 5.70 | 6.93 | 6.67 | 6.67 | 0.50 | 5.50 | 5.60 | 0.50 | 0.50 | 0.50 | 5.60 | 6.67 |
Cycles executing div or sqrt instructions | 16.00 |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 16.42-16.44 |
Stall cycles | 6.90-6.92 |
PRF_INT full (events) | 7.23-7.25 |
Front-end | 8.83 |
Dispatch | 6.93 |
DIV/SQRT | 16.00 |
Data deps. | 2.00 |
Overall L1 | 16.00 |
all | 25% |
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 | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 73% |
load | 83% |
store | 100% |
mul | 0% |
add-sub | 66% |
fma | 100% |
div/sqrt | 100% |
other | 70% |
all | 32% |
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 | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 76% |
load | 85% |
store | 100% |
mul | 12% |
add-sub | 68% |
fma | 100% |
div/sqrt | 100% |
other | 72% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD %R9D,%RAX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
SUB 0x280(%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 |
IMUL %RAX,%RSI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x3c0(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
IMUL %RAX,%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x30(%RSP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
IMUL %RAX,%RBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RAX,%RDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %RDI,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RSI,%R14 | 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 | |||||||||||||||
ADD 0xb0(%RSP),%R14 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
ADD 0x50(%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 0x340(%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 (%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 0xf8(%RSP),%R15 | 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,%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 |
ADD 0xd8(%RSP),%RBX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
ADD 0x400(%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 (%RBX,%RAX,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,%ZMM4{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VMOVAPD %ZMM5,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VMOVUPD (%RBX,%RSI,8),%ZMM8{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VFMADD213PD %ZMM4,%ZMM6,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %ZMM8,%ZMM3{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VSUBPD %ZMM3,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD 0xe0(%RSP),%R9 | 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 (%R9,%RSI,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,%ZMM2{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VDIVPD %ZMM2,%ZMM7,%ZMM7 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
VMOVUPD %ZMM7,(%R15,%RSI,8){%K1} | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
JMP 432360 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xcd0> | 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 %R12D | 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 4320a7 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xa17> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %R11D,%R11D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 432360 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xcd0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x38(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RAX,%RDX,1),%R9D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
MOV 0x118(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x1e0(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%RDI | 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 432280 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xbf0> | 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.f90:81-184 |
Module | exec |
nb instructions | 44 |
nb uops | 44 |
loop length | 192 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 12 |
micro-operation queue | 7.33 cycles |
front end | 7.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.80 | 8.00 | 4.67 | 4.67 | 0.00 | 4.80 | 4.60 | 0.00 | 0.00 | 0.00 | 4.80 | 4.67 |
cycles | 4.80 | 11.27 | 4.67 | 4.67 | 0.00 | 4.80 | 4.60 | 0.00 | 0.00 | 0.00 | 4.80 | 4.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 8.16 |
Stall cycles | 0.29 |
PRF_INT full (events) | 0.88 |
Front-end | 7.33 |
Dispatch | 11.27 |
Data deps. | 2.00 |
Overall L1 | 11.27 |
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 | 10% |
load | 11% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 11% |
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 %R12D | 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 4320a7 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xa17> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %R11D,%R11D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 432360 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xcd0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x38(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RAX,%RDX,1),%R9D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
MOV 0x118(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x1e0(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%RDI | 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 432280 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xbf0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R11D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOVSXD %R12D,%R13 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
ADD 0x2c0(%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 0x30(%RSP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R13,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
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 |
MOV 0x3c0(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R15,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R13,%R11 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD 0x60(%RSP),%R11 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOVSXD %R9D,%R9 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
SUB 0x280(%RSP),%R9 | 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 %RSI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R9,%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 %R9,%RBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RDI,%R9 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R13,%RDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD 0x10(%RSP),%RDI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
IMUL %RSI,%R13 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %R8,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
XOR %ESI,%ESI | 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 0x300(%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,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x120(%RSP),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JNE 4322b0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xc20> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 432360 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xcd0> | 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.f90:81-184 |
Module | exec |
nb instructions | 70 |
nb uops | 71 |
loop length | 360 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 9 |
nb stack references | 19 |
micro-operation queue | 11.83 cycles |
front end | 11.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 8.20 | 8.20 | 8.67 | 8.67 | 0.50 | 8.30 | 8.10 | 0.50 | 0.50 | 0.50 | 8.20 | 8.67 |
cycles | 8.20 | 12.67 | 8.67 | 8.67 | 0.50 | 8.30 | 8.10 | 0.50 | 0.50 | 0.50 | 8.20 | 8.67 |
Cycles executing div or sqrt instructions | 16.00 |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 16.52-16.48 |
Stall cycles | 4.08-4.07 |
PRF_INT full (events) | 4.41-4.40 |
Front-end | 11.83 |
Dispatch | 12.67 |
DIV/SQRT | 16.00 |
Data deps. | 2.00 |
Overall L1 | 16.00 |
all | 10% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 16% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 100% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 48% |
load | 50% |
store | 100% |
mul | 0% |
add-sub | 28% |
fma | 100% |
div/sqrt | 100% |
other | 46% |
all | 19% |
load | 11% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 26% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 19% |
all | 100% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 53% |
load | 55% |
store | 100% |
mul | 12% |
add-sub | 36% |
fma | 100% |
div/sqrt | 100% |
other | 51% |
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 | |||||||||||||||
ADD 0xb0(%RSP),%R14 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
ADD 0x50(%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 0x340(%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 (%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 0xf8(%RSP),%R15 | 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,%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 |
ADD 0xd8(%RSP),%RBX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
ADD 0x400(%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 (%RBX,%RAX,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,%ZMM4{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VMOVAPD %ZMM5,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VMOVUPD (%RBX,%RSI,8),%ZMM8{%K1}{z} | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VFMADD213PD %ZMM4,%ZMM6,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %ZMM8,%ZMM3{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VSUBPD %ZMM3,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD 0xe0(%RSP),%R9 | 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 (%R9,%RSI,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,%ZMM2{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
VDIVPD %ZMM2,%ZMM7,%ZMM7 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
VMOVUPD %ZMM7,(%R15,%RSI,8){%K1} | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
JMP 432360 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xcd0> | 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 %R12D | 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 4320a7 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xa17> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
TEST %R11D,%R11D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 432360 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xcd0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x38(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%RAX,%RDX,1),%R9D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
MOV 0x118(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x1e0(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX),%RDI | 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 432280 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xbf0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R11D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOVSXD %R12D,%R13 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
ADD 0x2c0(%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 0x30(%RSP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R13,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
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 |
MOV 0x3c0(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R15,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R13,%R11 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD 0x60(%RSP),%R11 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOVSXD %R9D,%R9 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
SUB 0x280(%RSP),%R9 | 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 %RSI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %R9,%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 %R9,%RBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RDI,%R9 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %R13,%RDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD 0x10(%RSP),%RDI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
IMUL %RSI,%R13 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %R8,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
XOR %ESI,%ESI | 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 0x300(%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,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x120(%RSP),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JNE 4322b0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0xc20> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |