Loop Id: 97 | Module: exec | Source: advec_mom_kernel.f90:151-176 | Coverage: 0.02% |
---|
Loop Id: 97 | Module: exec | Source: advec_mom_kernel.f90:151-176 | Coverage: 0.02% |
---|
0x41fa60 VMOVD %XMM9,%R12D |
0x41fa65 CMP %R12D,0x140(%RSP) |
0x41fa6d JG 41fbf1 |
0x41fa73 MOVSXD 0x138(%RSP),%RAX |
0x41fa7b VMOVQ %XMM22,%RSI |
0x41fa81 MOV %R15D,0x150(%RSP) |
0x41fa89 MOV %R10,%R12 |
0x41fa8c MOV %RBX,%R15 |
0x41fa8f MOV %R11,%R13 |
0x41fa92 VXORPD %XMM7,%XMM7,%XMM7 |
0x41fa96 VMOVDDUP 0x6f432(%RIP),%XMM13 |
0x41fa9e VMOVSD 0x6f48a(%RIP),%XMM12 |
0x41faa6 LEA 0x1(%RAX),%RDI |
0x41faaa LEA 0x1(%RAX,%RSI,1),%R9 |
0x41faaf MOV %RDI,%RBX |
0x41fab2 MOV %R9,0x170(%RSP) |
0x41faba JMP 41fbab |
(98) 0x41fac0 LEA -0x2(%RAX),%R9D |
(98) 0x41fac4 MOV %RAX,%R10 |
(98) 0x41fac7 MOVSXD %R9D,%R11 |
(98) 0x41faca MOVSXD %R9D,%R9 |
(98) 0x41facd LEA (%R13,%RSI,1),%RDI |
(98) 0x41fad2 ADD %R12,%R10 |
(98) 0x41fad5 ADD %R12,%RSI |
(98) 0x41fad8 ADD %R12,%R9 |
(98) 0x41fadb VMOVSD (%R14,%RSI,8),%XMM0 |
(98) 0x41fae1 VMOVSD (%R14,%R10,8),%XMM2 |
(98) 0x41fae7 VMOVSD (%R8,%RDI,8),%XMM25 |
(98) 0x41faee VSUBSD (%R14,%R9,8),%XMM0,%XMM5 |
(98) 0x41faf4 VSUBSD %XMM0,%XMM2,%XMM1 |
(98) 0x41faf8 VMOVSD -0x8(%RDX,%RAX,8),%XMM3 |
(98) 0x41fafe VMULSD %XMM5,%XMM1,%XMM2 |
(98) 0x41fb02 VCOMISD %XMM7,%XMM2 |
(98) 0x41fb06 JBE 41fb91 |
(98) 0x41fb0c VCOMISD %XMM1,%XMM7 |
(98) 0x41fb10 JAE 422040 |
(98) 0x41fb16 VMOVSD %XMM11,%XMM11,%XMM18 |
(98) 0x41fb1c VMOVSD %XMM11,%XMM11,%XMM20 |
(98) 0x41fb22 VUNPCKLPD %XMM5,%XMM1,%XMM5 |
(98) 0x41fb26 MOV 0x158(%RSP),%RDI |
(98) 0x41fb2e VANDPD %XMM15,%XMM4,%XMM1 |
(98) 0x41fb33 VMOVQ %XMM14,%R9 |
(98) 0x41fb38 VANDPD %XMM13,%XMM5,%XMM2 |
(98) 0x41fb3d VDIVSD %XMM25,%XMM1,%XMM19 |
(98) 0x41fb43 VMOVDDUP %XMM19,%XMM5 |
(98) 0x41fb49 VADDSUBPD %XMM5,%XMM8,%XMM1 |
(98) 0x41fb4d VSUBSD %XMM19,%XMM18,%XMM17 |
(98) 0x41fb53 VMULSD %XMM20,%XMM17,%XMM16 |
(98) 0x41fb59 VMULPD %XMM1,%XMM2,%XMM1 |
(98) 0x41fb5d ADD %RDI,%R11 |
(98) 0x41fb60 VMOVHPD (%R9,%R11,8),%XMM3,%XMM5 |
(98) 0x41fb66 VMULSD %XMM12,%XMM3,%XMM3 |
(98) 0x41fb6b VDIVPD %XMM5,%XMM1,%XMM1 |
(98) 0x41fb6f VUNPCKHPD %XMM1,%XMM1,%XMM5 |
(98) 0x41fb73 VADDPD %XMM1,%XMM5,%XMM5 |
(98) 0x41fb77 VMULSD %XMM5,%XMM3,%XMM1 |
(98) 0x41fb7b VMOVSD %XMM2,%XMM2,%XMM5 |
(98) 0x41fb7f VUNPCKHPD %XMM2,%XMM2,%XMM2 |
(98) 0x41fb83 VMINSD %XMM2,%XMM5,%XMM3 |
(98) 0x41fb87 VMINSD %XMM3,%XMM1,%XMM1 |
(98) 0x41fb8b VFMADD231SD %XMM1,%XMM16,%XMM0 |
(98) 0x41fb91 VMULSD %XMM4,%XMM0,%XMM4 |
(98) 0x41fb95 VMOVSD %XMM4,-0x8(%RCX,%RAX,8) |
(98) 0x41fb9b MOV %RBX,%RAX |
(98) 0x41fb9e CMP %RBX,0x170(%RSP) |
(98) 0x41fba6 JE 41fbe0 |
(98) 0x41fba8 INC %RBX |
(98) 0x41fbab VMOVSD -0x8(%R15,%RAX,8),%XMM4 |
(98) 0x41fbb2 LEA -0x1(%RAX),%RSI |
(98) 0x41fbb6 VCOMISD %XMM4,%XMM7 |
(98) 0x41fbba JBE 41fac0 |
(98) 0x41fbc0 MOV %RSI,%R10 |
(98) 0x41fbc3 MOVSXD %EAX,%R11 |
(98) 0x41fbc6 LEA 0x1(%RAX),%R9D |
(98) 0x41fbca MOV %RAX,%RSI |
(98) 0x41fbcd JMP 41faca |
0x41fbe0 MOV %R15,%RBX |
0x41fbe3 MOV 0x150(%RSP),%R15D |
0x41fbeb MOV %R13,%R11 |
0x41fbee MOV %R12,%R10 |
0x41fbf1 MOV 0x178(%RSP),%R13 |
0x41fbf9 MOV 0x128(%RSP),%RSI |
0x41fc01 VMOVQ %XMM10,%R12 |
0x41fc06 VMOVQ %XMM6,%RDI |
0x41fc0b INC %R15D |
0x41fc0e ADD %R12,%RCX |
0x41fc11 ADD %RDI,%RBX |
0x41fc14 ADD %R13,%R11 |
0x41fc17 ADD %RSI,%R10 |
0x41fc1a CMP %R15D,0x148(%RSP) |
0x41fc22 JG 41fa60 |
(98) 0x422040 MOV 0x6cee1(%RIP),%R10 |
(98) 0x422047 MOV 0x6cf1a(%RIP),%RSI |
(98) 0x42204e VMOVQ %R10,%XMM20 |
(98) 0x422054 VMOVQ %RSI,%XMM18 |
(98) 0x42205a JMP 41fb22 |
/beegfs/hackathon/users/eoseret/qaas_runs/170-861-0321/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/advec_mom_kernel.f90: 151 - 176 |
-------------------------------------------------------------------------------- |
151: DO j=x_min-1,x_max+1 |
152: IF(node_flux(j,k).LT.0.0)THEN |
153: upwind=j+2 |
154: donor=j+1 |
155: downwind=j |
156: dif=donor |
157: ELSE |
158: upwind=j-1 |
159: donor=j |
160: downwind=j+1 |
161: dif=upwind |
162: ENDIF |
163: sigma=ABS(node_flux(j,k))/(node_mass_pre(donor,k)) |
164: width=celldx(j) |
165: vdiffuw=vel1(donor,k)-vel1(upwind,k) |
166: vdiffdw=vel1(downwind,k)-vel1(donor,k) |
167: limiter=0.0 |
168: IF(vdiffuw*vdiffdw.GT.0.0)THEN |
169: auw=ABS(vdiffuw) |
170: adw=ABS(vdiffdw) |
171: wind=1.0_8 |
172: IF(vdiffdw.LE.0.0) wind=-1.0_8 |
173: limiter=wind*MIN(width*((2.0_8-sigma)*adw/width+(1.0_8+sigma)*auw/celldx(dif))/6.0_8,auw,adw) |
174: ENDIF |
175: advec_vel_s=vel1(donor,k)+(1.0-sigma)*limiter |
176: mom_flux(j,k)=advec_vel_s*node_flux(j,k) |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.67 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.53 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.45 |
Bottlenecks | micro-operation queue, |
Function | __advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0 |
Source | advec_mom_kernel.f90:151-152,advec_mom_kernel.f90:163-163,advec_mom_kernel.f90:170-170,advec_mom_kernel.f90:173-173 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.33 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 5.33 |
CQA cycles if fully vectorized | 0.63 |
Front-end cycles | 5.33 |
DIV/SQRT cycles | 2.75 |
P0 cycles | 2.75 |
P1 cycles | 2.50 |
P2 cycles | 2.50 |
P3 cycles | 1.50 |
P4 cycles | 3.67 |
P5 cycles | 3.67 |
P6 cycles | 3.67 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 2.00 |
P12 cycles | 2.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 32.00 |
Nb uops | 32.00 |
Nb loads | 8.00 |
Nb stores | 2.00 |
Nb stack references | 7.00 |
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 | 11.25 |
Bytes prefetched | 0.00 |
Bytes loaded | 48.00 |
Bytes stored | 12.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 4.76 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 8.33 |
Vector-efficiency ratio all | 12.20 |
Vector-efficiency ratio load | 10.94 |
Vector-efficiency ratio store | 9.38 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.67 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.53 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.45 |
Bottlenecks | micro-operation queue, |
Function | __advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0 |
Source | advec_mom_kernel.f90:151-152,advec_mom_kernel.f90:163-163,advec_mom_kernel.f90:170-170,advec_mom_kernel.f90:173-173 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.33 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 5.33 |
CQA cycles if fully vectorized | 0.63 |
Front-end cycles | 5.33 |
DIV/SQRT cycles | 2.75 |
P0 cycles | 2.75 |
P1 cycles | 2.50 |
P2 cycles | 2.50 |
P3 cycles | 1.50 |
P4 cycles | 3.67 |
P5 cycles | 3.67 |
P6 cycles | 3.67 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 2.00 |
P12 cycles | 2.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 32.00 |
Nb uops | 32.00 |
Nb loads | 8.00 |
Nb stores | 2.00 |
Nb stack references | 7.00 |
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 | 11.25 |
Bytes prefetched | 0.00 |
Bytes loaded | 48.00 |
Bytes stored | 12.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 4.76 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 8.33 |
Vector-efficiency ratio all | 12.20 |
Vector-efficiency ratio load | 10.94 |
Vector-efficiency ratio store | 9.38 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Path / |
Function | __advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0 |
Source file and lines | advec_mom_kernel.f90:151-176 |
Module | exec |
nb instructions | 32 |
nb uops | 32 |
loop length | 167 |
used x86 registers | 12 |
used mmx registers | 0 |
used xmm registers | 7 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 5.33 cycles |
front end | 5.33 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.75 | 2.75 | 2.50 | 2.50 | 1.50 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 | 0.00 | 0.00 | 2.00 | 2.00 |
cycles | 2.75 | 2.75 | 2.50 | 2.50 | 1.50 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 | 0.00 | 0.00 | 2.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Front-end | 5.33 |
Dispatch | 3.67 |
Overall L1 | 5.33 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 33% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 4% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 8% |
all | 11% |
load | 9% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 16% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 12% |
load | 10% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVD %XMM9,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 5 | 1 |
CMP %R12D,0x140(%RSP) | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JG 41fbf1 <__advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0+0x13b1> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOVSXD 0x138(%RSP),%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM22,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
MOV %R15D,0x150(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOV %R10,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %RBX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R11,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VXORPD %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVDDUP 0x6f432(%RIP),%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VMOVSD 0x6f48a(%RIP),%XMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%RAX),%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LEA 0x1(%RAX,%RSI,1),%R9 | 2 | 0 | 0 | 0.50 | 0.50 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R9,0x170(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 41fbab <__advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0+0x136b> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
MOV %R15,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV 0x150(%RSP),%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV %R13,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R12,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV 0x178(%RSP),%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV 0x128(%RSP),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
VMOVQ %XMM10,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
VMOVQ %XMM6,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
INC %R15D | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %R12,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %RDI,%RBX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %R13,%R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %RSI,%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
CMP %R15D,0x148(%RSP) | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JG 41fa60 <__advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0+0x1220> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
Function | __advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0 |
Source file and lines | advec_mom_kernel.f90:151-176 |
Module | exec |
nb instructions | 32 |
nb uops | 32 |
loop length | 167 |
used x86 registers | 12 |
used mmx registers | 0 |
used xmm registers | 7 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 5.33 cycles |
front end | 5.33 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.75 | 2.75 | 2.50 | 2.50 | 1.50 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 | 0.00 | 0.00 | 2.00 | 2.00 |
cycles | 2.75 | 2.75 | 2.50 | 2.50 | 1.50 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 | 0.00 | 0.00 | 2.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Front-end | 5.33 |
Dispatch | 3.67 |
Overall L1 | 5.33 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 33% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 4% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 8% |
all | 11% |
load | 9% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 16% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 12% |
load | 10% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVD %XMM9,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 5 | 1 |
CMP %R12D,0x140(%RSP) | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JG 41fbf1 <__advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0+0x13b1> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOVSXD 0x138(%RSP),%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM22,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
MOV %R15D,0x150(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOV %R10,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %RBX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R11,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VXORPD %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVDDUP 0x6f432(%RIP),%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VMOVSD 0x6f48a(%RIP),%XMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%RAX),%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LEA 0x1(%RAX,%RSI,1),%R9 | 2 | 0 | 0 | 0.50 | 0.50 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R9,0x170(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 41fbab <__advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0+0x136b> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
MOV %R15,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV 0x150(%RSP),%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV %R13,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R12,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV 0x178(%RSP),%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV 0x128(%RSP),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
VMOVQ %XMM10,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
VMOVQ %XMM6,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
INC %R15D | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %R12,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %RDI,%RBX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %R13,%R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD %RSI,%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
CMP %R15D,0x148(%RSP) | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JG 41fa60 <__advec_mom_kernel_mod_MOD_advec_mom_kernel._omp_fn.0+0x1220> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |