Loop Id: 228 | Module: exec | Source: BsplineFunctor.h:246-260 | Coverage: 0.06% |
---|
Loop Id: 228 | Module: exec | Source: BsplineFunctor.h:246-260 | Coverage: 0.06% |
---|
0x41bb10 VMULPD (%R9,%RAX,8),%ZMM0,%ZMM12 [1] |
0x41bb17 VCVTTPD2DQ %ZMM12,%YMM13 |
0x41bb1d KXNORW %K0,%K0,%K1 |
0x41bb21 VXORPD %XMM14,%XMM14,%XMM14 |
0x41bb26 VGATHERDPD (%RSI,%YMM13,8),%ZMM14{%K1} [3] |
0x41bb2d KXNORW %K0,%K0,%K1 |
0x41bb31 VXORPD %XMM15,%XMM15,%XMM15 |
0x41bb36 VGATHERDPD 0x8(%RSI,%YMM13,8),%ZMM15{%K1} [3] |
0x41bb3e KXNORW %K0,%K0,%K1 |
0x41bb42 VXORPD %XMM4,%XMM4,%XMM4 |
0x41bb46 VGATHERDPD 0x10(%RSI,%YMM13,8),%ZMM4{%K1} [3] |
0x41bb4e VRNDSCALEPD $0xb,%ZMM12,%ZMM5 |
0x41bb55 VSUBPD %ZMM5,%ZMM12,%ZMM5 |
0x41bb5b VPADDD %YMM10,%YMM13,%YMM12 |
0x41bb60 KXNORW %K0,%K0,%K1 |
0x41bb64 VXORPD %XMM13,%XMM13,%XMM13 |
0x41bb69 VGATHERDPD (%RSI,%YMM12,8),%ZMM13{%K1} [2] |
0x41bb70 VMOVAPD %ZMM5,%ZMM12 |
0x41bb76 VFMADD213PD %ZMM19,%ZMM18,%ZMM12 |
0x41bb7c VFMADD213PD %ZMM20,%ZMM5,%ZMM12 |
0x41bb82 VFMADD213PD %ZMM21,%ZMM5,%ZMM12 |
0x41bb88 VFMADD213PD %ZMM11,%ZMM14,%ZMM12 |
0x41bb8e VMOVAPD %ZMM5,%ZMM11 |
0x41bb94 VFMADD213PD %ZMM23,%ZMM22,%ZMM11 |
0x41bb9a VFMADD213PD %ZMM24,%ZMM5,%ZMM11 |
0x41bba0 VFMADD213PD %ZMM25,%ZMM5,%ZMM11 |
0x41bba6 VFMADD213PD %ZMM12,%ZMM15,%ZMM11 |
0x41bbac VMOVAPD %ZMM5,%ZMM12 |
0x41bbb2 VFMADD213PD %ZMM27,%ZMM26,%ZMM12 |
0x41bbb8 VFMADD213PD %ZMM28,%ZMM5,%ZMM12 |
0x41bbbe VFMADD213PD %ZMM29,%ZMM5,%ZMM12 |
0x41bbc4 VFMADD213PD %ZMM11,%ZMM4,%ZMM12 |
0x41bbca VMOVAPD %ZMM5,%ZMM11 |
0x41bbd0 VFMADD213PD %ZMM31,%ZMM30,%ZMM11 |
0x41bbd6 VFMADD213PD %ZMM8,%ZMM5,%ZMM11 |
0x41bbdc VFMADD213PD %ZMM9,%ZMM5,%ZMM11 |
0x41bbe2 VFMADD213PD %ZMM12,%ZMM13,%ZMM11 |
0x41bbe8 ADD $0x8,%RAX |
0x41bbec CMP %RCX,%RAX |
0x41bbef JB 41bb10 |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 246 - 260 |
-------------------------------------------------------------------------------- |
246: for (int jat = 0; jat < iCount; jat++) |
247: { |
248: real_type r = distArrayCompressed[jat]; |
249: r *= DeltaRInv; |
250: int i = (int)r; |
251: real_type t = r - real_type(i); |
252: real_type tp0 = t * t * t; |
253: real_type tp1 = t * t; |
254: real_type tp2 = t; |
255: |
256: real_type d1 = SplineCoefs[i + 0] * (A[0] * tp0 + A[1] * tp1 + A[2] * tp2 + A[3]); |
257: real_type d2 = SplineCoefs[i + 1] * (A[4] * tp0 + A[5] * tp1 + A[6] * tp2 + A[7]); |
258: real_type d3 = SplineCoefs[i + 2] * (A[8] * tp0 + A[9] * tp1 + A[10] * tp2 + A[11]); |
259: real_type d4 = SplineCoefs[i + 3] * (A[12] * tp0 + A[13] * tp1 + A[14] * tp2 + A[15]); |
260: d += (d1 + d2 + d3 + d4); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►71.43+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:130 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:219 | exec |
○ | main.extracted.104 | stl_vector.h:1126 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | main | miniqmc.cpp:404 | exec |
○ | __libc_init_first | libc.so.6 | |
►28.57+ | miniqmcreference::OneBodyJastr[...] | OneBodyJastrowRef.h:150 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:219 | exec |
○ | main.extracted.104 | stl_vector.h:1126 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | main | miniqmc.cpp:404 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.03 |
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 | 1.03 |
Bottlenecks | P0, P5, |
Function | qmcplusplus::BsplineFunctor |
Source | BsplineFunctor.h:246-260 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 17.00 |
CQA cycles if no scalar integer | 16.50 |
CQA cycles if FP arith vectorized | 17.00 |
CQA cycles if fully vectorized | 17.00 |
Front-end cycles | 13.50 |
DIV/SQRT cycles | 17.00 |
P0 cycles | 9.00 |
P1 cycles | 16.50 |
P2 cycles | 16.50 |
P3 cycles | 0.00 |
P4 cycles | 17.00 |
P5 cycles | 1.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 16 |
FE+BE cycles (UFS) | 43.47 |
Stall cycles (UFS) | 31.42 |
Nb insns | 40.00 |
Nb uops | 53.00 |
Nb loads | 5.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 16.00 |
Nb FLOP add-sub | 8.00 |
Nb FLOP mul | 8.00 |
Nb FLOP fma | 128.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 18.82 |
Bytes prefetched | 0.00 |
Bytes loaded | 320.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 89.39 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | 75.00 |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 78.57 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.03 |
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 | 1.03 |
Bottlenecks | P0, P5, |
Function | qmcplusplus::BsplineFunctor |
Source | BsplineFunctor.h:246-260 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 17.00 |
CQA cycles if no scalar integer | 16.50 |
CQA cycles if FP arith vectorized | 17.00 |
CQA cycles if fully vectorized | 17.00 |
Front-end cycles | 13.50 |
DIV/SQRT cycles | 17.00 |
P0 cycles | 9.00 |
P1 cycles | 16.50 |
P2 cycles | 16.50 |
P3 cycles | 0.00 |
P4 cycles | 17.00 |
P5 cycles | 1.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 16 |
FE+BE cycles (UFS) | 43.47 |
Stall cycles (UFS) | 31.42 |
Nb insns | 40.00 |
Nb uops | 53.00 |
Nb loads | 5.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 16.00 |
Nb FLOP add-sub | 8.00 |
Nb FLOP mul | 8.00 |
Nb FLOP fma | 128.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 18.82 |
Bytes prefetched | 0.00 |
Bytes loaded | 320.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 89.39 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | 75.00 |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 78.57 |
Path / |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:246-260 |
Module | exec |
nb instructions | 40 |
nb uops | 53 |
loop length | 229 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 3 |
used zmm registers | 24 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 1.00 |
micro-operation queue | 13.50 cycles |
front end | 13.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 17.00 | 1.50 | 16.50 | 16.50 | 0.00 | 17.00 | 1.50 | 0.00 |
cycles | 17.00 | 9.00 | 16.50 | 16.50 | 0.00 | 17.00 | 1.50 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 16.00 |
FE+BE cycles | 43.47 |
Stall cycles | 31.42 |
ROB full (events) | 32.80 |
RS full (events) | 0.25 |
Front-end | 13.50 |
Dispatch | 17.00 |
Data deps. | 16.00 |
Overall L1 | 17.00 |
all | 100% |
load | NA (no load vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 50% |
load | NA (no load vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
all | 90% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 78% |
all | 89% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 75% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 78% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
VMULPD (%R9,%RAX,8),%ZMM0,%ZMM12 | 1 | 0.50 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VCVTTPD2DQ %ZMM12,%YMM13 | 2 | 0.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 7 | 1 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM14,%XMM14,%XMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD (%RSI,%YMM13,8),%ZMM14{%K1} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM15,%XMM15,%XMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD 0x8(%RSI,%YMM13,8),%ZMM15{%K1} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD 0x10(%RSI,%YMM13,8),%ZMM4{%K1} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
VRNDSCALEPD $0xb,%ZMM12,%ZMM5 | 2 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 8 | 1 |
VSUBPD %ZMM5,%ZMM12,%ZMM5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VPADDD %YMM10,%YMM13,%YMM12 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM13,%XMM13,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD (%RSI,%YMM12,8),%ZMM13{%K1} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
VMOVAPD %ZMM5,%ZMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMADD213PD %ZMM19,%ZMM18,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM20,%ZMM5,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM21,%ZMM5,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM11,%ZMM14,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMOVAPD %ZMM5,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMADD213PD %ZMM23,%ZMM22,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM24,%ZMM5,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM25,%ZMM5,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM12,%ZMM15,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMOVAPD %ZMM5,%ZMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMADD213PD %ZMM27,%ZMM26,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM28,%ZMM5,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM29,%ZMM5,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM11,%ZMM4,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMOVAPD %ZMM5,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMADD213PD %ZMM31,%ZMM30,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM8,%ZMM5,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM9,%ZMM5,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM12,%ZMM13,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bb10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | qmcplusplus::BsplineFunctor |
Source file and lines | BsplineFunctor.h:246-260 |
Module | exec |
nb instructions | 40 |
nb uops | 53 |
loop length | 229 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 3 |
used zmm registers | 24 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 1.00 |
micro-operation queue | 13.50 cycles |
front end | 13.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 17.00 | 1.50 | 16.50 | 16.50 | 0.00 | 17.00 | 1.50 | 0.00 |
cycles | 17.00 | 9.00 | 16.50 | 16.50 | 0.00 | 17.00 | 1.50 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 16.00 |
FE+BE cycles | 43.47 |
Stall cycles | 31.42 |
ROB full (events) | 32.80 |
RS full (events) | 0.25 |
Front-end | 13.50 |
Dispatch | 17.00 |
Data deps. | 16.00 |
Overall L1 | 17.00 |
all | 100% |
load | NA (no load vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 50% |
load | NA (no load vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
all | 90% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 78% |
all | 89% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 75% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 78% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
VMULPD (%R9,%RAX,8),%ZMM0,%ZMM12 | 1 | 0.50 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VCVTTPD2DQ %ZMM12,%YMM13 | 2 | 0.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 7 | 1 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM14,%XMM14,%XMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD (%RSI,%YMM13,8),%ZMM14{%K1} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM15,%XMM15,%XMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD 0x8(%RSI,%YMM13,8),%ZMM15{%K1} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD 0x10(%RSI,%YMM13,8),%ZMM4{%K1} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
VRNDSCALEPD $0xb,%ZMM12,%ZMM5 | 2 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 8 | 1 |
VSUBPD %ZMM5,%ZMM12,%ZMM5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VPADDD %YMM10,%YMM13,%YMM12 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM13,%XMM13,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD (%RSI,%YMM12,8),%ZMM13{%K1} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
VMOVAPD %ZMM5,%ZMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMADD213PD %ZMM19,%ZMM18,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM20,%ZMM5,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM21,%ZMM5,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM11,%ZMM14,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMOVAPD %ZMM5,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMADD213PD %ZMM23,%ZMM22,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM24,%ZMM5,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM25,%ZMM5,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM12,%ZMM15,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMOVAPD %ZMM5,%ZMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMADD213PD %ZMM27,%ZMM26,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM28,%ZMM5,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM29,%ZMM5,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM11,%ZMM4,%ZMM12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMOVAPD %ZMM5,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMADD213PD %ZMM31,%ZMM30,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM8,%ZMM5,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM9,%ZMM5,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM12,%ZMM13,%ZMM11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bb10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |