Loop Id: 101 | Module: exec | Source: timestep.c:88-94 | Coverage: 1.65% |
---|
Loop Id: 101 | Module: exec | Source: timestep.c:88-94 | Coverage: 1.65% |
---|
0x413270 VPMOVSXDQ (%R13,%RCX,4),%ZMM15 [3] |
0x413278 VXORPD %XMM16,%XMM16,%XMM16 |
0x41327e VPSLLQ $0x4,%ZMM15,%ZMM15 |
0x413285 KXNORW %K0,%K0,%K1 |
0x413289 VGATHERQPD 0x8(%R10,%ZMM15,1),%ZMM16{%K1} [1] |
0x413291 VMOVQ %RCX,%XMM15 |
0x413296 VPADDQ %XMM15,%XMM14,%XMM15 |
0x41329b VPSLLQ $0x3,%XMM15,%XMM17 |
0x4132a2 VPSLLQ $0x4,%XMM15,%XMM15 |
0x4132a8 VPADDQ %XMM17,%XMM15,%XMM15 |
0x4132ae VPBROADCASTQ %XMM15,%ZMM15 |
0x4132b4 VPXORD %XMM17,%XMM17,%XMM17 |
0x4132ba KXNORW %K0,%K0,%K1 |
0x4132be VPADDQ %ZMM4,%ZMM15,%ZMM15 |
0x4132c4 VXORPD %XMM18,%XMM18,%XMM18 |
0x4132ca VGATHERQPD (%R9,%ZMM15,1),%ZMM17{%K1} [2] |
0x4132d1 KXNORW %K0,%K0,%K1 |
0x4132d5 VGATHERQPD (%R8,%ZMM15,1),%ZMM18{%K1} [4] |
0x4132dc VDIVPD %ZMM16,%ZMM3,%ZMM16 |
0x4132e2 VFMADD231PD %ZMM17,%ZMM16,%ZMM18 |
0x4132e8 KXNORW %K0,%K0,%K1 |
0x4132ec VXORPD %XMM17,%XMM17,%XMM17 |
0x4132f2 KXNORW %K0,%K0,%K2 |
0x4132f6 VSCATTERQPD %ZMM18,(%R8,%ZMM15,1){%K1} [4] |
0x4132fd VXORPD %XMM18,%XMM18,%XMM18 |
0x413303 VGATHERQPD 0x8(%R9,%ZMM15,1),%ZMM17{%K2} [2] |
0x41330b KXNORW %K0,%K0,%K1 |
0x41330f VGATHERQPD 0x8(%R8,%ZMM15,1),%ZMM18{%K1} [4] |
0x413317 VFMADD231PD %ZMM17,%ZMM16,%ZMM18 |
0x41331d KXNORW %K0,%K0,%K1 |
0x413321 VXORPD %XMM17,%XMM17,%XMM17 |
0x413327 KXNORW %K0,%K0,%K2 |
0x41332b VSCATTERQPD %ZMM18,0x8(%R8,%ZMM15,1){%K1} [4] |
0x413333 VXORPD %XMM18,%XMM18,%XMM18 |
0x413339 VGATHERQPD 0x10(%R9,%ZMM15,1),%ZMM17{%K2} [2] |
0x413341 KXNORW %K0,%K0,%K1 |
0x413345 VGATHERQPD 0x10(%R8,%ZMM15,1),%ZMM18{%K1} [4] |
0x41334d VFMADD231PD %ZMM17,%ZMM16,%ZMM18 |
0x413353 KXNORW %K0,%K0,%K1 |
0x413357 VSCATTERQPD %ZMM18,0x10(%R8,%ZMM15,1){%K1} [4] |
0x41335f ADD $0x8,%RCX |
0x413363 CMP %EDX,%ECX |
0x413365 JLE 413270 |
/scratch_na/users/xoserete/qaas_runs/171-172-4338/intel/CoMD/build/CoMD/CoMD/src-openmp/timestep.c: 88 - 94 |
-------------------------------------------------------------------------------- |
88: for (int iOff=MAXATOMS*iBox,ii=0; ii<s->boxes->nAtoms[iBox]; ii++,iOff++) |
89: { |
90: int iSpecies = s->atoms->iSpecies[iOff]; |
91: real_t invMass = 1.0/s->species[iSpecies].mass; |
92: s->atoms->r[iOff][0] += dt*s->atoms->p[iOff][0]*invMass; |
93: s->atoms->r[iOff][1] += dt*s->atoms->p[iOff][1]*invMass; |
94: s->atoms->r[iOff][2] += dt*s->atoms->p[iOff][2]*invMass; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.31 |
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 | 1.18 |
Bottlenecks | P0, |
Function | advancePosition.extracted |
Source | timestep.c:88-94 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 8 |
CQA cycles | 26.00 |
CQA cycles if no scalar integer | 19.83 |
CQA cycles if FP arith vectorized | 26.00 |
CQA cycles if fully vectorized | 26.00 |
Front-end cycles | 21.67 |
DIV/SQRT cycles | 26.00 |
P0 cycles | 5.00 |
P1 cycles | 19.00 |
P2 cycles | 19.00 |
P3 cycles | 12.00 |
P4 cycles | 22.00 |
P5 cycles | 2.00 |
P6 cycles | 12.00 |
P7 cycles | 12.00 |
P8 cycles | 12.00 |
P9 cycles | 2.00 |
P10 cycles | 19.00 |
P11 cycles | 16.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 32.36 - 279.81 |
Stall cycles (UFS) | 16.43 - 263.80 |
Nb insns | 43.00 |
Nb uops | 130.00 |
Nb loads | 8.00 |
Nb stores | 3.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.15 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 24.00 |
Nb FLOP div | 8.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 25.85 |
Bytes prefetched | 0.00 |
Bytes loaded | 480.00 |
Bytes stored | 192.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 3.00 |
Vectorization ratio all | 93.33 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | 100.00 |
Vectorization ratio other | 89.47 |
Vector-efficiency ratio all | 65.00 |
Vector-efficiency ratio load | 93.75 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | 100.00 |
Vector-efficiency ratio other | 55.26 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.31 |
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 | 1.18 |
Bottlenecks | P0, |
Function | advancePosition.extracted |
Source | timestep.c:88-94 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 8 |
CQA cycles | 26.00 |
CQA cycles if no scalar integer | 19.83 |
CQA cycles if FP arith vectorized | 26.00 |
CQA cycles if fully vectorized | 26.00 |
Front-end cycles | 21.67 |
DIV/SQRT cycles | 26.00 |
P0 cycles | 5.00 |
P1 cycles | 19.00 |
P2 cycles | 19.00 |
P3 cycles | 12.00 |
P4 cycles | 22.00 |
P5 cycles | 2.00 |
P6 cycles | 12.00 |
P7 cycles | 12.00 |
P8 cycles | 12.00 |
P9 cycles | 2.00 |
P10 cycles | 19.00 |
P11 cycles | 16.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 32.36 - 279.81 |
Stall cycles (UFS) | 16.43 - 263.80 |
Nb insns | 43.00 |
Nb uops | 130.00 |
Nb loads | 8.00 |
Nb stores | 3.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.15 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 24.00 |
Nb FLOP div | 8.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 25.85 |
Bytes prefetched | 0.00 |
Bytes loaded | 480.00 |
Bytes stored | 192.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 3.00 |
Vectorization ratio all | 93.33 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | 100.00 |
Vectorization ratio other | 89.47 |
Vector-efficiency ratio all | 65.00 |
Vector-efficiency ratio load | 93.75 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | 100.00 |
Vector-efficiency ratio other | 55.26 |
Path / |
Function | advancePosition.extracted |
Source file and lines | timestep.c:88-94 |
Module | exec |
nb instructions | 43 |
nb uops | 130 |
loop length | 251 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 5 |
used ymm registers | 0 |
used zmm registers | 6 |
nb stack references | 0 |
micro-operation queue | 21.67 cycles |
front end | 21.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 26.00 | 5.00 | 19.00 | 19.00 | 12.00 | 22.00 | 2.00 | 12.00 | 12.00 | 12.00 | 2.00 | 19.00 |
cycles | 26.00 | 5.00 | 19.00 | 19.00 | 12.00 | 22.00 | 2.00 | 12.00 | 12.00 | 12.00 | 2.00 | 19.00 |
Cycles executing div or sqrt instructions | 16.00 |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 32.36-279.81 |
Stall cycles | 16.43-263.80 |
RS full (events) | 28.46-279.32 |
Front-end | 21.67 |
Dispatch | 26.00 |
DIV/SQRT | 16.00 |
Data deps. | 1.00 |
Overall L1 | 26.00 |
all | 80% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 66% |
all | 100% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 93% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 89% |
all | 40% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 33% |
all | 77% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | 100% |
other | 65% |
all | 65% |
load | 93% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | 100% |
div/sqrt | 100% |
other | 55% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VPMOVSXDQ (%R13,%RCX,4),%ZMM15 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
VXORPD %XMM16,%XMM16,%XMM16 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VPSLLQ $0x4,%ZMM15,%ZMM15 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 1 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD 0x8(%R10,%ZMM15,1),%ZMM16{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VMOVQ %RCX,%XMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VPADDQ %XMM15,%XMM14,%XMM15 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPSLLQ $0x3,%XMM15,%XMM17 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 0.50 |
VPSLLQ $0x4,%XMM15,%XMM15 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 0.50 |
VPADDQ %XMM17,%XMM15,%XMM15 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPBROADCASTQ %XMM15,%ZMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPXORD %XMM17,%XMM17,%XMM17 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VPADDQ %ZMM4,%ZMM15,%ZMM15 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VXORPD %XMM18,%XMM18,%XMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD (%R9,%ZMM15,1),%ZMM17{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD (%R8,%ZMM15,1),%ZMM18{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VDIVPD %ZMM16,%ZMM3,%ZMM16 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
VFMADD231PD %ZMM17,%ZMM16,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM17,%XMM17,%XMM17 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
KXNORW %K0,%K0,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM18,(%R8,%ZMM15,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 |
VXORPD %XMM18,%XMM18,%XMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD 0x8(%R9,%ZMM15,1),%ZMM17{%K2} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD 0x8(%R8,%ZMM15,1),%ZMM18{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VFMADD231PD %ZMM17,%ZMM16,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM17,%XMM17,%XMM17 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
KXNORW %K0,%K0,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM18,0x8(%R8,%ZMM15,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 |
VXORPD %XMM18,%XMM18,%XMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD 0x10(%R9,%ZMM15,1),%ZMM17{%K2} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD 0x10(%R8,%ZMM15,1),%ZMM18{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VFMADD231PD %ZMM17,%ZMM16,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM18,0x10(%R8,%ZMM15,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 |
ADD $0x8,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %EDX,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 413270 <advancePosition.extracted+0x270> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | advancePosition.extracted |
Source file and lines | timestep.c:88-94 |
Module | exec |
nb instructions | 43 |
nb uops | 130 |
loop length | 251 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 5 |
used ymm registers | 0 |
used zmm registers | 6 |
nb stack references | 0 |
micro-operation queue | 21.67 cycles |
front end | 21.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 26.00 | 5.00 | 19.00 | 19.00 | 12.00 | 22.00 | 2.00 | 12.00 | 12.00 | 12.00 | 2.00 | 19.00 |
cycles | 26.00 | 5.00 | 19.00 | 19.00 | 12.00 | 22.00 | 2.00 | 12.00 | 12.00 | 12.00 | 2.00 | 19.00 |
Cycles executing div or sqrt instructions | 16.00 |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 32.36-279.81 |
Stall cycles | 16.43-263.80 |
RS full (events) | 28.46-279.32 |
Front-end | 21.67 |
Dispatch | 26.00 |
DIV/SQRT | 16.00 |
Data deps. | 1.00 |
Overall L1 | 26.00 |
all | 80% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 66% |
all | 100% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | 100% |
other | 100% |
all | 93% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 89% |
all | 40% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 33% |
all | 77% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | 100% |
other | 65% |
all | 65% |
load | 93% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | 100% |
div/sqrt | 100% |
other | 55% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VPMOVSXDQ (%R13,%RCX,4),%ZMM15 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
VXORPD %XMM16,%XMM16,%XMM16 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VPSLLQ $0x4,%ZMM15,%ZMM15 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 1 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD 0x8(%R10,%ZMM15,1),%ZMM16{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VMOVQ %RCX,%XMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VPADDQ %XMM15,%XMM14,%XMM15 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPSLLQ $0x3,%XMM15,%XMM17 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 0.50 |
VPSLLQ $0x4,%XMM15,%XMM15 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 0.50 |
VPADDQ %XMM17,%XMM15,%XMM15 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPBROADCASTQ %XMM15,%ZMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VPXORD %XMM17,%XMM17,%XMM17 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VPADDQ %ZMM4,%ZMM15,%ZMM15 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VXORPD %XMM18,%XMM18,%XMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD (%R9,%ZMM15,1),%ZMM17{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD (%R8,%ZMM15,1),%ZMM18{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VDIVPD %ZMM16,%ZMM3,%ZMM16 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
VFMADD231PD %ZMM17,%ZMM16,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM17,%XMM17,%XMM17 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
KXNORW %K0,%K0,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM18,(%R8,%ZMM15,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 |
VXORPD %XMM18,%XMM18,%XMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD 0x8(%R9,%ZMM15,1),%ZMM17{%K2} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD 0x8(%R8,%ZMM15,1),%ZMM18{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VFMADD231PD %ZMM17,%ZMM16,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM17,%XMM17,%XMM17 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
KXNORW %K0,%K0,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM18,0x8(%R8,%ZMM15,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 |
VXORPD %XMM18,%XMM18,%XMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VGATHERQPD 0x10(%R9,%ZMM15,1),%ZMM17{%K2} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VGATHERQPD 0x10(%R8,%ZMM15,1),%ZMM18{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
VFMADD231PD %ZMM17,%ZMM16,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM18,0x10(%R8,%ZMM15,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 |
ADD $0x8,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %EDX,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 413270 <advancePosition.extracted+0x270> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |