Loop Id: 977 | Module: exec | Source: DistanceTableBA.h:99-99 [...] | Coverage: 0.17% |
---|
Loop Id: 977 | Module: exec | Source: DistanceTableBA.h:99-99 [...] | Coverage: 0.17% |
---|
0x459340 XOR %ECX,%ECX |
0x459342 TEST $-0x80000000,%R8D |
0x459349 SETE %CL |
0x45934c MOVSXD %R8D,%R10 |
0x45934f VMOVSD (%R9,%R10,8),%XMM0 [4] |
0x459355 VSUBSD 0x108(%RSP),%XMM0,%XMM0 [8] |
0x45935e VMOVDDUP 0x496300(,%RCX,8),%XMM6 [10] |
0x459367 VMULSD %XMM6,%XMM0,%XMM0 |
0x45936b VMOVSD (%RDX,%R10,8),%XMM7 [5] |
0x459371 VMOVHPD (%RBX,%R10,8),%XMM7,%XMM7 [2] |
0x459377 VSUBPD %XMM10,%XMM7,%XMM7 |
0x45937c VMULPD %XMM6,%XMM7,%XMM12 |
0x459380 VMULPD %XMM12,%XMM30,%XMM7 |
0x459386 VPERMILPD $0x1,%XMM12,%XMM1 |
0x45938c VFMADD231PD %XMM1,%XMM3,%XMM7 |
0x459391 VMOVDDUP %XMM0,%XMM2 |
0x459395 VFMADD213PD %XMM7,%XMM31,%XMM2 |
0x45939b VROUNDPD $0x9,%XMM2,%XMM7 |
0x4593a1 VMULSD %XMM1,%XMM27,%XMM1 |
0x4593a7 VFMADD231SD %XMM12,%XMM11,%XMM1 |
0x4593ac VFMADD231SD %XMM0,%XMM13,%XMM1 |
0x4593b1 VROUNDSD $0x9,%XMM1,%XMM1,%XMM1 |
0x4593b7 VPERMILPD $0x1,%XMM7,%XMM2 |
0x4593bd VMOVAPD %XMM3,%XMM29 |
0x4593c3 VMOVAPD %XMM27,%XMM3 |
0x4593c9 VMOVDDUP %XMM1,%XMM27 |
0x4593cf VFMSUB231PD %XMM8,%XMM2,%XMM12 |
0x4593d4 VFMADD231PD %XMM28,%XMM7,%XMM12 |
0x4593da VFNMSUB231PD %XMM27,%XMM9,%XMM12 |
0x4593e0 VMOVAPD %XMM3,%XMM27 |
0x4593e6 VFMSUB213SD %XMM0,%XMM17,%XMM7 |
0x4593ec VFMADD231SD %XMM2,%XMM18,%XMM7 |
0x4593f2 VFNMSUB231SD %XMM1,%XMM19,%XMM7 |
0x4593f8 VPERMILPD $0x1,%XMM12,%XMM0 |
0x4593fe VADDSD %XMM0,%XMM20,%XMM1 |
0x459404 VADDSD %XMM12,%XMM21,%XMM2 |
0x45940a VADDSD %XMM7,%XMM22,%XMM3 |
0x459410 VBLENDPD $0x1,%XMM1,%XMM12,%XMM1 |
0x459416 VMULPD %XMM1,%XMM1,%XMM1 |
0x45941a VUNPCKLPD %XMM12,%XMM2,%XMM2 |
0x45941f VFMADD213PD %XMM1,%XMM2,%XMM2 |
0x459424 VBROADCASTSD %XMM7,%YMM1 |
0x459429 VUNPCKLPD %XMM1,%XMM3,%XMM3 |
0x45942d VFMADD213PD %XMM2,%XMM3,%XMM3 |
0x459432 VPERMILPD $0x1,%XMM3,%XMM2 |
0x459438 XOR %R11D,%R11D |
0x45943b VUCOMISD %XMM2,%XMM3 |
0x45943f SETB %R11B |
0x459443 VMINSD %XMM2,%XMM3,%XMM2 |
0x459447 VADDSD %XMM0,%XMM23,%XMM3 |
0x45944d VADDSD %XMM12,%XMM24,%XMM4 |
0x459453 VADDSD %XMM7,%XMM14,%XMM5 |
0x459457 VMULSD %XMM3,%XMM3,%XMM3 |
0x45945b VFMADD231SD %XMM4,%XMM4,%XMM3 |
0x459460 VFMADD231SD %XMM5,%XMM5,%XMM3 |
0x459465 VUCOMISD %XMM2,%XMM3 |
0x459469 VMINSD %XMM2,%XMM3,%XMM2 |
0x45946d VADDPD 0x130(%RSP),%XMM12,%XMM3 [8] |
0x459476 VADDSD %XMM7,%XMM15,%XMM4 |
0x45947a VMULPD %XMM3,%XMM3,%XMM3 |
0x45947e VPERMILPD $0x1,%XMM3,%XMM5 |
0x459484 VADDSD %XMM5,%XMM3,%XMM3 |
0x459488 VFMADD231SD %XMM4,%XMM4,%XMM3 |
0x45948d MOV $0x2,%ECX |
0x459492 CMOVB %RCX,%R11 |
0x459496 VUCOMISD %XMM2,%XMM3 |
0x45949a VMINSD %XMM2,%XMM3,%XMM2 |
0x45949e VPERMPD $0x55,%YMM12,%YMM3 |
0x4594a4 VADDPD %YMM3,%YMM16,%YMM3 |
0x4594aa VBROADCASTSD %XMM12,%YMM4 |
0x4594af VADDPD %YMM4,%YMM25,%YMM4 |
0x4594b5 VADDPD %YMM1,%YMM26,%YMM1 |
0x4594bb VMULPD %YMM3,%YMM3,%YMM3 |
0x4594bf VFMADD231PD %YMM4,%YMM4,%YMM3 |
0x4594c4 VFMADD231PD %YMM1,%YMM1,%YMM3 |
0x4594c9 VMINSD %XMM2,%XMM3,%XMM1 |
0x4594cd VPERMILPD $0x1,%XMM3,%XMM4 |
0x4594d3 VMINSD %XMM1,%XMM4,%XMM4 |
0x4594d7 VEXTRACTF128 $0x1,%YMM3,%XMM5 |
0x4594dd VUNPCKLPD %XMM1,%XMM2,%XMM1 |
0x4594e1 VMINSD %XMM4,%XMM5,%XMM2 |
0x4594e5 VUNPCKLPD %XMM2,%XMM4,%XMM4 |
0x4594e9 VINSERTF128 $0x1,%XMM4,%YMM1,%YMM1 |
0x4594ef VPERMILPD $0x1,%XMM5,%XMM4 |
0x4594f5 VMINSD %XMM2,%XMM4,%XMM2 |
0x4594f9 VSQRTSD %XMM2,%XMM2,%XMM2 |
0x4594fd VMOVSD %XMM2,(%R15,%R10,8) [1] |
0x459503 VCMPPD $0x1,%YMM1,%YMM3,%K0 |
0x45950a VMOVAPD %XMM29,%XMM3 |
0x459510 KMOVD %K0,%ECX |
0x459514 MOV $0x3,%ESI |
0x459519 CMOVB %RSI,%R11 |
0x45951d MOV $0x4,%ESI |
0x459522 TEST $0x1,%CL |
0x459525 CMOVNE %RSI,%R11 |
0x459529 MOV $0x5,%ESI |
0x45952e TEST $0x2,%CL |
0x459531 CMOVNE %RSI,%R11 |
0x459535 MOV $0x6,%ESI |
0x45953a TEST $0x4,%CL |
0x45953d CMOVNE %RSI,%R11 |
0x459541 TEST $0x8,%CL |
0x459544 MOV $0x7,%ECX |
0x459549 CMOVNE %RCX,%R11 |
0x45954d VADDSD 0x180(%RDI,%R11,8),%XMM0,%XMM0 [9] |
0x459557 VMULSD %XMM6,%XMM0,%XMM0 |
0x45955b VMOVSD %XMM0,(%R14,%R10,8) [3] |
0x459561 VADDSD 0x1c0(%RDI,%R11,8),%XMM12,%XMM0 [9] |
0x45956b VMULSD %XMM6,%XMM0,%XMM0 |
0x45956f VMOVSD %XMM0,(%RAX,%R10,8) [6] |
0x459575 VADDSD 0x200(%RDI,%R11,8),%XMM7,%XMM0 [9] |
0x45957f VMULSD %XMM6,%XMM0,%XMM0 |
0x459583 VMOVSD %XMM0,(%R12,%R10,8) [7] |
0x459589 INC %R8 |
0x45958c CMP %R8,%R13 |
0x45958f JNE 459340 |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds.h: 249 - 278 |
-------------------------------------------------------------------------------- |
249: const T flip = iat < flip_ind ? one : minusone; |
250: const T displ_0 = (px[iat] - x0) * flip; |
251: const T displ_1 = (py[iat] - y0) * flip; |
252: const T displ_2 = (pz[iat] - z0) * flip; |
253: |
254: const T ar_0 = -std::floor(displ_0 * g00 + displ_1 * g10 + displ_2 * g20); |
255: const T ar_1 = -std::floor(displ_0 * g01 + displ_1 * g11 + displ_2 * g21); |
256: const T ar_2 = -std::floor(displ_0 * g02 + displ_1 * g12 + displ_2 * g22); |
257: |
258: const T delx = displ_0 + ar_0 * r00 + ar_1 * r10 + ar_2 * r20; |
259: const T dely = displ_1 + ar_0 * r01 + ar_1 * r11 + ar_2 * r21; |
260: const T delz = displ_2 + ar_0 * r02 + ar_1 * r12 + ar_2 * r22; |
[...] |
267: const T x = delx + cellx[c]; |
268: const T y = dely + celly[c]; |
269: const T z = delz + cellz[c]; |
270: const T r2 = x * x + y * y + z * z; |
271: ic = (r2 < rmin) ? c : ic; |
272: rmin = (r2 < rmin) ? r2 : rmin; |
273: } |
274: |
275: temp_r[iat] = std::sqrt(rmin); |
276: dx[iat] = flip * (delx + cellx[ic]); |
277: dy[iat] = flip * (dely + celly[ic]); |
278: dz[iat] = flip * (delz + cellz[ic]); |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Particle/DistanceTableBA.h: 99 - 99 |
-------------------------------------------------------------------------------- |
99: for (size_t jel = first; jel < last; ++jel) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | qmcplusplus::ParticleSet::upda[...] | ParticleSet.cpp:250 | exec |
○ | main.extracted.107 | miniqmc.cpp:390 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | main | miniqmc.cpp:374 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.02 |
CQA speedup if FP arith vectorized | 1.67 |
CQA speedup if fully vectorized | 5.19 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.01 |
Bottlenecks | P0, P1, |
Function | qmcplusplus::DistanceTableBA |
Source | ParticleBConds.h:249-278,DistanceTableBA.h:99-99 |
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 | 30.50 |
CQA cycles if no scalar integer | 30.00 |
CQA cycles if FP arith vectorized | 18.25 |
CQA cycles if fully vectorized | 5.88 |
Front-end cycles | 30.25 |
DIV/SQRT cycles | 30.50 |
P0 cycles | 30.50 |
P1 cycles | 4.50 |
P2 cycles | 4.50 |
P3 cycles | 4.00 |
P4 cycles | 21.50 |
P5 cycles | 21.50 |
P6 cycles | 4.00 |
P7 cycles | 4.50 - 6.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 55.68 - 57.42 |
Stall cycles (UFS) | 24.88 - 26.63 |
Nb insns | 116.00 |
Nb uops | 117.00 |
Nb loads | 9.00 |
Nb stores | 4.00 |
Nb stack references | 2.00 |
FLOP/cycle | 3.51 |
Nb FLOP add-sub | 28.00 |
Nb FLOP mul | 18.00 |
Nb FLOP fma | 30.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 1.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 3.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 80.00 |
Bytes stored | 32.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 8.00 |
Vectorization ratio all | 37.89 |
Vectorization ratio load | 11.11 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 45.45 |
Vectorization ratio add_sub | 29.41 |
Vectorization ratio fma | 52.94 |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 41.46 |
Vector-efficiency ratio all | 19.01 |
Vector-efficiency ratio load | 13.89 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 20.45 |
Vector-efficiency ratio add_sub | 20.59 |
Vector-efficiency ratio fma | 22.06 |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | 18.14 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.02 |
CQA speedup if FP arith vectorized | 1.67 |
CQA speedup if fully vectorized | 5.19 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.01 |
Bottlenecks | P0, P1, |
Function | qmcplusplus::DistanceTableBA |
Source | ParticleBConds.h:249-278,DistanceTableBA.h:99-99 |
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 | 30.50 |
CQA cycles if no scalar integer | 30.00 |
CQA cycles if FP arith vectorized | 18.25 |
CQA cycles if fully vectorized | 5.88 |
Front-end cycles | 30.25 |
DIV/SQRT cycles | 30.50 |
P0 cycles | 30.50 |
P1 cycles | 4.50 |
P2 cycles | 4.50 |
P3 cycles | 4.00 |
P4 cycles | 21.50 |
P5 cycles | 21.50 |
P6 cycles | 4.00 |
P7 cycles | 4.50 - 6.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 55.68 - 57.42 |
Stall cycles (UFS) | 24.88 - 26.63 |
Nb insns | 116.00 |
Nb uops | 117.00 |
Nb loads | 9.00 |
Nb stores | 4.00 |
Nb stack references | 2.00 |
FLOP/cycle | 3.51 |
Nb FLOP add-sub | 28.00 |
Nb FLOP mul | 18.00 |
Nb FLOP fma | 30.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 1.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 3.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 80.00 |
Bytes stored | 32.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 8.00 |
Vectorization ratio all | 37.89 |
Vectorization ratio load | 11.11 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 45.45 |
Vectorization ratio add_sub | 29.41 |
Vectorization ratio fma | 52.94 |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 41.46 |
Vector-efficiency ratio all | 19.01 |
Vector-efficiency ratio load | 13.89 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 20.45 |
Vector-efficiency ratio add_sub | 20.59 |
Vector-efficiency ratio fma | 22.06 |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | 18.14 |
Path / |
Function | qmcplusplus::DistanceTableBA |
Source file and lines | DistanceTableBA.h:99-99 |
Module | exec |
nb instructions | 116 |
nb uops | 117 |
loop length | 597 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 29 |
used ymm registers | 7 |
used zmm registers | 0 |
nb stack references | 2 |
ADD-SUB / MUL ratio | 1.55 |
micro-operation queue | 30.25 cycles |
front end | 30.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 30.50 | 30.50 | 4.50 | 4.50 | 4.00 | 21.50 | 21.50 | 4.00 |
cycles | 30.50 | 30.50 | 4.50 | 4.50 | 4.00 | 21.50 | 21.50 | 4.00 |
Cycles executing div or sqrt instructions | 4.50-6.00 |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 55.68-57.42 |
Stall cycles | 24.88-26.63 |
ROB full (events) | 5.22-9.17 |
RS full (events) | 39.81-35.25 |
Front-end | 30.25 |
Dispatch | 30.50 |
DIV/SQRT | 4.50-6.00 |
Data deps. | 0.00 |
Overall L1 | 30.50 |
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 | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 40% |
load | 11% |
store | 0% |
mul | 45% |
add-sub | 29% |
fma | 52% |
div/sqrt | 0% |
other | 47% |
all | 37% |
load | 11% |
store | 0% |
mul | 45% |
add-sub | 29% |
fma | 52% |
div/sqrt | 0% |
other | 41% |
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 | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 6% |
all | 19% |
load | 13% |
store | 12% |
mul | 20% |
add-sub | 20% |
fma | 22% |
div/sqrt | 12% |
other | 19% |
all | 19% |
load | 13% |
store | 12% |
mul | 20% |
add-sub | 20% |
fma | 22% |
div/sqrt | 12% |
other | 18% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST $-0x80000000,%R8D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %CL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVSXD %R8D,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%R9,%R10,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x108(%RSP),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVDDUP 0x496300(,%RCX,8),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM6,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%RDX,%R10,8),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVHPD (%RBX,%R10,8),%XMM7,%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
VSUBPD %XMM10,%XMM7,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %XMM6,%XMM7,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %XMM12,%XMM30,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM12,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD231PD %XMM1,%XMM3,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVDDUP %XMM0,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM7,%XMM31,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VROUNDPD $0x9,%XMM2,%XMM7 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VMULSD %XMM1,%XMM27,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM12,%XMM11,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM0,%XMM13,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VROUNDSD $0x9,%XMM1,%XMM1,%XMM1 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VPERMILPD $0x1,%XMM7,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVAPD %XMM3,%XMM29 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM27,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDDUP %XMM1,%XMM27 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMSUB231PD %XMM8,%XMM2,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %XMM28,%XMM7,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMSUB231PD %XMM27,%XMM9,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %XMM3,%XMM27 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMSUB213SD %XMM0,%XMM17,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM2,%XMM18,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMSUB231SD %XMM1,%XMM19,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM12,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM0,%XMM20,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM12,%XMM21,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM7,%XMM22,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBLENDPD $0x1,%XMM1,%XMM12,%XMM1 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMULPD %XMM1,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM12,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM1,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM7,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VUNPCKLPD %XMM1,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM2,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD %XMM2,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
SETB %R11B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMINSD %XMM2,%XMM3,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM23,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM12,%XMM24,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM7,%XMM14,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM3,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM4,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM5,%XMM5,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUCOMISD %XMM2,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMINSD %XMM2,%XMM3,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD 0x130(%RSP),%XMM12,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM7,%XMM15,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %XMM3,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM5,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM4,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOV $0x2,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVB %RCX,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VUCOMISD %XMM2,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMINSD %XMM2,%XMM3,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMPD $0x55,%YMM12,%YMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %YMM3,%YMM16,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM12,%YMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %YMM4,%YMM25,%YMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD %YMM1,%YMM26,%YMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %YMM3,%YMM3,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %YMM4,%YMM4,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %YMM1,%YMM1,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMINSD %XMM2,%XMM3,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM1,%XMM4,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VEXTRACTF128 $0x1,%YMM3,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VUNPCKLPD %XMM1,%XMM2,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM4,%XMM5,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM2,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VINSERTF128 $0x1,%XMM4,%YMM1,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPERMILPD $0x1,%XMM5,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM2,%XMM4,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSQRTSD %XMM2,%XMM2,%XMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-19 | 4.50-6 |
VMOVSD %XMM2,(%R15,%R10,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VCMPPD $0x1,%YMM1,%YMM3,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVAPD %XMM29,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
KMOVD %K0,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
MOV $0x3,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVB %RSI,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x4,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST $0x1,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVNE %RSI,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x5,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST $0x2,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVNE %RSI,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x6,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST $0x4,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVNE %RSI,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
TEST $0x8,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x7,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVNE %RCX,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VADDSD 0x180(%RDI,%R11,8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM6,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%R14,%R10,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD 0x1c0(%RDI,%R11,8),%XMM12,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM6,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%RAX,%R10,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD 0x200(%RDI,%R11,8),%XMM7,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM6,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%R12,%R10,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 459340 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | qmcplusplus::DistanceTableBA |
Source file and lines | DistanceTableBA.h:99-99 |
Module | exec |
nb instructions | 116 |
nb uops | 117 |
loop length | 597 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 29 |
used ymm registers | 7 |
used zmm registers | 0 |
nb stack references | 2 |
ADD-SUB / MUL ratio | 1.55 |
micro-operation queue | 30.25 cycles |
front end | 30.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 30.50 | 30.50 | 4.50 | 4.50 | 4.00 | 21.50 | 21.50 | 4.00 |
cycles | 30.50 | 30.50 | 4.50 | 4.50 | 4.00 | 21.50 | 21.50 | 4.00 |
Cycles executing div or sqrt instructions | 4.50-6.00 |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 55.68-57.42 |
Stall cycles | 24.88-26.63 |
ROB full (events) | 5.22-9.17 |
RS full (events) | 39.81-35.25 |
Front-end | 30.25 |
Dispatch | 30.50 |
DIV/SQRT | 4.50-6.00 |
Data deps. | 0.00 |
Overall L1 | 30.50 |
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 | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 40% |
load | 11% |
store | 0% |
mul | 45% |
add-sub | 29% |
fma | 52% |
div/sqrt | 0% |
other | 47% |
all | 37% |
load | 11% |
store | 0% |
mul | 45% |
add-sub | 29% |
fma | 52% |
div/sqrt | 0% |
other | 41% |
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 | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 6% |
all | 19% |
load | 13% |
store | 12% |
mul | 20% |
add-sub | 20% |
fma | 22% |
div/sqrt | 12% |
other | 19% |
all | 19% |
load | 13% |
store | 12% |
mul | 20% |
add-sub | 20% |
fma | 22% |
div/sqrt | 12% |
other | 18% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST $-0x80000000,%R8D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETE %CL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOVSXD %R8D,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%R9,%R10,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD 0x108(%RSP),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVDDUP 0x496300(,%RCX,8),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM6,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%RDX,%R10,8),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVHPD (%RBX,%R10,8),%XMM7,%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
VSUBPD %XMM10,%XMM7,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %XMM6,%XMM7,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %XMM12,%XMM30,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM12,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD231PD %XMM1,%XMM3,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVDDUP %XMM0,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM7,%XMM31,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VROUNDPD $0x9,%XMM2,%XMM7 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VMULSD %XMM1,%XMM27,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM12,%XMM11,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM0,%XMM13,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VROUNDSD $0x9,%XMM1,%XMM1,%XMM1 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VPERMILPD $0x1,%XMM7,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVAPD %XMM3,%XMM29 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM27,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDDUP %XMM1,%XMM27 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMSUB231PD %XMM8,%XMM2,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %XMM28,%XMM7,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMSUB231PD %XMM27,%XMM9,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %XMM3,%XMM27 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VFMSUB213SD %XMM0,%XMM17,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM2,%XMM18,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMSUB231SD %XMM1,%XMM19,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM12,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM0,%XMM20,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM12,%XMM21,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM7,%XMM22,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBLENDPD $0x1,%XMM1,%XMM12,%XMM1 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMULPD %XMM1,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM12,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM1,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM7,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VUNPCKLPD %XMM1,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM2,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD %XMM2,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
SETB %R11B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMINSD %XMM2,%XMM3,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM23,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM12,%XMM24,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM7,%XMM14,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM3,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM4,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM5,%XMM5,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUCOMISD %XMM2,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMINSD %XMM2,%XMM3,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD 0x130(%RSP),%XMM12,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM7,%XMM15,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %XMM3,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM5,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM4,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOV $0x2,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVB %RCX,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VUCOMISD %XMM2,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMINSD %XMM2,%XMM3,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMPD $0x55,%YMM12,%YMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %YMM3,%YMM16,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM12,%YMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %YMM4,%YMM25,%YMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD %YMM1,%YMM26,%YMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %YMM3,%YMM3,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %YMM4,%YMM4,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %YMM1,%YMM1,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMINSD %XMM2,%XMM3,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM1,%XMM4,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VEXTRACTF128 $0x1,%YMM3,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VUNPCKLPD %XMM1,%XMM2,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM4,%XMM5,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM2,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VINSERTF128 $0x1,%XMM4,%YMM1,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPERMILPD $0x1,%XMM5,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM2,%XMM4,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSQRTSD %XMM2,%XMM2,%XMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-19 | 4.50-6 |
VMOVSD %XMM2,(%R15,%R10,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VCMPPD $0x1,%YMM1,%YMM3,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVAPD %XMM29,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
KMOVD %K0,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
MOV $0x3,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVB %RSI,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x4,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST $0x1,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVNE %RSI,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x5,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST $0x2,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVNE %RSI,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x6,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST $0x4,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVNE %RSI,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
TEST $0x8,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x7,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVNE %RCX,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VADDSD 0x180(%RDI,%R11,8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM6,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%R14,%R10,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD 0x1c0(%RDI,%R11,8),%XMM12,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM6,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%RAX,%R10,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD 0x200(%RDI,%R11,8),%XMM7,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM6,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%R12,%R10,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 459340 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |