Loop Id: 1173 | Module: exec | Source: DistanceTableBA.h:99-99 [...] | Coverage: 0.52% |
---|
Loop Id: 1173 | Module: exec | Source: DistanceTableBA.h:99-99 [...] | Coverage: 0.52% |
---|
0x45fc80 XOR %ECX,%ECX |
0x45fc82 TEST $-0x80000000,%R12D |
0x45fc89 SETE %CL |
0x45fc8c MOVSXD %R12D,%R14 |
0x45fc8f VMOVSD (%RDX,%R14,8),%XMM0 [2] |
0x45fc95 VMOVDDUP 0x49c680(,%RCX,8),%XMM1 [10] |
0x45fc9e VSUBSD %XMM26,%XMM0,%XMM0 |
0x45fca4 VMULSD %XMM1,%XMM0,%XMM0 |
0x45fca8 VMOVSD (%RSI,%R14,8),%XMM2 [9] |
0x45fcae VMOVHPD (%R9,%R14,8),%XMM2,%XMM2 [5] |
0x45fcb4 VMULSD %XMM0,%XMM20,%XMM3 |
0x45fcba VSUBPD 0x110(%RSP),%XMM2,%XMM2 [6] |
0x45fcc3 VMULPD %XMM1,%XMM2,%XMM2 |
0x45fcc7 VUNPCKLPD %XMM0,%XMM2,%XMM4 |
0x45fccb VMULPD %XMM4,%XMM10,%XMM4 |
0x45fccf VUNPCKLPD %XMM2,%XMM0,%XMM6 |
0x45fcd3 VFMADD213PD %XMM4,%XMM16,%XMM6 |
0x45fcd9 VPERMILPD $0x3,%XMM2,%XMM4 |
0x45fcdf VFMADD213PD %XMM6,%XMM11,%XMM4 |
0x45fce4 VROUNDPD $0x9,%XMM4,%XMM4 |
0x45fcea VFMADD231SD %XMM2,%XMM15,%XMM3 |
0x45fcef VPERMILPD $0x1,%XMM2,%XMM6 |
0x45fcf5 VFMADD213SD %XMM3,%XMM12,%XMM6 |
0x45fcfa VROUNDSD $0x9,%XMM6,%XMM6,%XMM3 |
0x45fd00 VPERMILPD $0x1,%XMM4,%XMM8 |
0x45fd06 VMOVDDUP %XMM3,%XMM6 |
0x45fd0a VFMSUB231SD %XMM21,%XMM4,%XMM0 |
0x45fd10 VFMADD231SD %XMM22,%XMM8,%XMM0 |
0x45fd16 VFNMSUB231SD %XMM3,%XMM23,%XMM0 |
0x45fd1c VFMSUB213PD %XMM2,%XMM13,%XMM8 |
0x45fd21 VFMADD231PD %XMM4,%XMM9,%XMM8 |
0x45fd26 VFNMSUB231PD %XMM6,%XMM14,%XMM8 |
0x45fd2b VADDSD %XMM0,%XMM24,%XMM2 |
0x45fd31 VADDSD %XMM8,%XMM25,%XMM3 |
0x45fd37 VPERMILPD $0x1,%XMM8,%XMM31 |
0x45fd3e VADDSD 0xb8(%RSP),%XMM31,%XMM4 [6] |
0x45fd46 VBROADCASTSD %XMM0,%YMM6 |
0x45fd4b VUNPCKLPD %XMM6,%XMM2,%XMM2 |
0x45fd4f VMULPD %XMM2,%XMM2,%XMM2 |
0x45fd53 VUNPCKLPD %XMM8,%XMM3,%XMM3 |
0x45fd58 VFMADD213PD %XMM2,%XMM3,%XMM3 |
0x45fd5d VBLENDPD $0x1,%XMM4,%XMM8,%XMM2 |
0x45fd63 VFMADD213PD %XMM3,%XMM2,%XMM2 |
0x45fd68 VPERMILPD $0x1,%XMM2,%XMM3 |
0x45fd6e XOR %R10D,%R10D |
0x45fd71 VUCOMISD %XMM3,%XMM2 |
0x45fd75 SETB %R10B |
0x45fd79 VMINSD %XMM3,%XMM2,%XMM2 |
0x45fd7d VADDSD %XMM0,%XMM27,%XMM3 |
0x45fd83 VADDSD %XMM8,%XMM17,%XMM4 |
0x45fd89 VMOVAPD %XMM12,%XMM5 |
0x45fd8d VADDSD %XMM31,%XMM18,%XMM12 |
0x45fd93 VMULSD %XMM3,%XMM3,%XMM3 |
0x45fd97 VFMADD231SD %XMM4,%XMM4,%XMM3 |
0x45fd9c VFMADD231SD %XMM12,%XMM12,%XMM3 |
0x45fda1 VMOVAPD %XMM5,%XMM12 |
0x45fda5 VUCOMISD %XMM2,%XMM3 |
0x45fda9 VMINSD %XMM2,%XMM3,%XMM2 |
0x45fdad VADDPD 0x100(%RSP),%XMM8,%XMM3 [6] |
0x45fdb6 VMULPD %XMM3,%XMM3,%XMM3 |
0x45fdba VPERMILPD $0x1,%XMM3,%XMM4 |
0x45fdc0 VADDSD %XMM3,%XMM4,%XMM3 |
0x45fdc4 VADDSD %XMM0,%XMM19,%XMM4 |
0x45fdca VFMADD213SD %XMM3,%XMM4,%XMM4 |
0x45fdcf MOV $0x2,%ECX |
0x45fdd4 CMOVB %RCX,%R10 |
0x45fdd8 VUCOMISD %XMM2,%XMM4 |
0x45fddc VMINSD %XMM2,%XMM4,%XMM2 |
0x45fde0 VADDPD %YMM6,%YMM28,%YMM3 |
0x45fde6 VBROADCASTSD %XMM8,%YMM4 |
0x45fdeb VADDPD %YMM4,%YMM29,%YMM4 |
0x45fdf1 VPERMPD $0x55,%YMM8,%YMM6 |
0x45fdf7 VADDPD %YMM6,%YMM30,%YMM6 |
0x45fdfd VMULPD %YMM3,%YMM3,%YMM3 |
0x45fe01 VFMADD231PD %YMM4,%YMM4,%YMM3 |
0x45fe06 VFMADD231PD %YMM6,%YMM6,%YMM3 |
0x45fe0b VMINSD %XMM2,%XMM3,%XMM4 |
0x45fe0f VPERMILPD $0x1,%XMM3,%XMM6 |
0x45fe15 VMINSD %XMM4,%XMM6,%XMM6 |
0x45fe19 VEXTRACTF128 $0x1,%YMM3,%XMM7 |
0x45fe1f VUNPCKLPD %XMM4,%XMM2,%XMM2 |
0x45fe23 VMINSD %XMM6,%XMM7,%XMM4 |
0x45fe27 VUNPCKLPD %XMM4,%XMM6,%XMM6 |
0x45fe2b VINSERTF128 $0x1,%XMM6,%YMM2,%YMM2 |
0x45fe31 VPERMILPD $0x1,%XMM7,%XMM6 |
0x45fe37 VMINSD %XMM4,%XMM6,%XMM4 |
0x45fe3b VSQRTSD %XMM4,%XMM4,%XMM4 |
0x45fe3f VMOVSD %XMM4,(%R8,%R14,8) [3] |
0x45fe45 VCMPPD $0x1,%YMM2,%YMM3,%K0 |
0x45fe4c KMOVD %K0,%ECX |
0x45fe50 MOV $0x3,%EBX |
0x45fe55 CMOVB %RBX,%R10 |
0x45fe59 MOV $0x4,%EBX |
0x45fe5e TEST $0x1,%CL |
0x45fe61 CMOVNE %RBX,%R10 |
0x45fe65 MOV $0x5,%EBX |
0x45fe6a TEST $0x2,%CL |
0x45fe6d CMOVNE %RBX,%R10 |
0x45fe71 MOV $0x6,%EBX |
0x45fe76 TEST $0x4,%CL |
0x45fe79 CMOVNE %RBX,%R10 |
0x45fe7d TEST $0x8,%CL |
0x45fe80 MOV $0x7,%ECX |
0x45fe85 CMOVNE %RCX,%R10 |
0x45fe89 VADDSD 0x180(%RDI,%R10,8),%XMM0,%XMM0 [7] |
0x45fe93 VMULSD %XMM1,%XMM0,%XMM0 |
0x45fe97 VMOVSD %XMM0,(%R11,%R14,8) [8] |
0x45fe9d VADDSD 0x1c0(%RDI,%R10,8),%XMM8,%XMM0 [7] |
0x45fea7 VMULSD %XMM1,%XMM0,%XMM0 |
0x45feab VMOVSD %XMM0,(%RAX,%R14,8) [1] |
0x45feb1 VADDSD 0x200(%RDI,%R10,8),%XMM31,%XMM0 [7] |
0x45feb9 VMULSD %XMM1,%XMM0,%XMM0 |
0x45febd VMOVSD %XMM0,(%R15,%R14,8) [4] |
0x45fec3 INC %R12 |
0x45fec6 CMP %R12,%R13 |
0x45fec9 JNE 45fc80 |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Particle/DistanceTableBA.h: 99 - 99 |
-------------------------------------------------------------------------------- |
99: for (size_t jel = first; jel < last; ++jel) |
/home/kcamus/qaas_runs/169-390-4082/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; |
[...] |
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]); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | qmcplusplus::ParticleSet::upda[...] | stl_vector.h:990 | 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 | 1.44 |
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 | DistanceTableBA.h:99-99,ParticleBConds.h:249-278 |
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 | 21.13 |
CQA cycles if fully vectorized | 5.88 |
Front-end cycles | 30.25 |
DIV/SQRT cycles | 30.50 |
P0 cycles | 30.50 |
P1 cycles | 5.00 |
P2 cycles | 5.00 |
P3 cycles | 4.00 |
P4 cycles | 23.00 |
P5 cycles | 22.00 |
P6 cycles | 4.00 |
P7 cycles | 4.50 - 6.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 56.15 - 57.50 |
Stall cycles (UFS) | 25.36 - 26.71 |
Nb insns | 116.00 |
Nb uops | 117.00 |
Nb loads | 10.00 |
Nb stores | 4.00 |
Nb stack references | 3.00 |
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 | 4.20 |
Bytes prefetched | 0.00 |
Bytes loaded | 96.00 |
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 | 36.84 |
Vectorization ratio load | 20.00 |
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 | 39.02 |
Vector-efficiency ratio all | 18.88 |
Vector-efficiency ratio load | 15.00 |
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 | 17.84 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.02 |
CQA speedup if FP arith vectorized | 1.44 |
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 | DistanceTableBA.h:99-99,ParticleBConds.h:249-278 |
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 | 21.13 |
CQA cycles if fully vectorized | 5.88 |
Front-end cycles | 30.25 |
DIV/SQRT cycles | 30.50 |
P0 cycles | 30.50 |
P1 cycles | 5.00 |
P2 cycles | 5.00 |
P3 cycles | 4.00 |
P4 cycles | 23.00 |
P5 cycles | 22.00 |
P6 cycles | 4.00 |
P7 cycles | 4.50 - 6.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 56.15 - 57.50 |
Stall cycles (UFS) | 25.36 - 26.71 |
Nb insns | 116.00 |
Nb uops | 117.00 |
Nb loads | 10.00 |
Nb stores | 4.00 |
Nb stack references | 3.00 |
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 | 4.20 |
Bytes prefetched | 0.00 |
Bytes loaded | 96.00 |
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 | 36.84 |
Vectorization ratio load | 20.00 |
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 | 39.02 |
Vector-efficiency ratio all | 18.88 |
Vector-efficiency ratio load | 15.00 |
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 | 17.84 |
Path / |
Function | qmcplusplus::DistanceTableBA |
Source file and lines | DistanceTableBA.h:99-99 |
Module | exec |
nb instructions | 116 |
nb uops | 117 |
loop length | 591 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 29 |
used ymm registers | 8 |
used zmm registers | 0 |
nb stack references | 3 |
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 | 5.00 | 5.00 | 4.00 | 23.00 | 22.00 | 4.00 |
cycles | 30.50 | 30.50 | 5.00 | 5.00 | 4.00 | 23.00 | 22.00 | 4.00 |
Cycles executing div or sqrt instructions | 4.50-6.00 |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 56.15-57.50 |
Stall cycles | 25.36-26.71 |
ROB full (events) | 2.58-6.57 |
RS full (events) | 43.62-38.48 |
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 | 38% |
load | 20% |
store | 0% |
mul | 45% |
add-sub | 29% |
fma | 52% |
div/sqrt | 0% |
other | 44% |
all | 36% |
load | 20% |
store | 0% |
mul | 45% |
add-sub | 29% |
fma | 52% |
div/sqrt | 0% |
other | 39% |
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 | 15% |
store | 12% |
mul | 20% |
add-sub | 20% |
fma | 22% |
div/sqrt | 12% |
other | 19% |
all | 18% |
load | 15% |
store | 12% |
mul | 20% |
add-sub | 20% |
fma | 22% |
div/sqrt | 12% |
other | 17% |
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,%R12D | 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 %R12D,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDX,%R14,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVDDUP 0x49c680(,%RCX,8),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD %XMM26,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%RSI,%R14,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVHPD (%R9,%R14,8),%XMM2,%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
VMULSD %XMM0,%XMM20,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBPD 0x110(%RSP),%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %XMM1,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM0,%XMM2,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMULPD %XMM4,%XMM10,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM2,%XMM0,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM4,%XMM16,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x3,%XMM2,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM6,%XMM11,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VROUNDPD $0x9,%XMM4,%XMM4 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VFMADD231SD %XMM2,%XMM15,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM2,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213SD %XMM3,%XMM12,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VROUNDSD $0x9,%XMM6,%XMM6,%XMM3 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VPERMILPD $0x1,%XMM4,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDDUP %XMM3,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMSUB231SD %XMM21,%XMM4,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM22,%XMM8,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMSUB231SD %XMM3,%XMM23,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB213PD %XMM2,%XMM13,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %XMM4,%XMM9,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMSUB231PD %XMM6,%XMM14,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM24,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM8,%XMM25,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM8,%XMM31 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD 0xb8(%RSP),%XMM31,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM0,%YMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VUNPCKLPD %XMM6,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMULPD %XMM2,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM8,%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 |
VBLENDPD $0x1,%XMM4,%XMM8,%XMM2 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VFMADD213PD %XMM3,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM2,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD %XMM3,%XMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
SETB %R10B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMINSD %XMM3,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM27,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM8,%XMM17,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %XMM12,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VADDSD %XMM31,%XMM18,%XMM12 | 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 %XMM12,%XMM12,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %XMM5,%XMM12 | 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 |
VMINSD %XMM2,%XMM3,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD 0x100(%RSP),%XMM8,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 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,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM3,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM19,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD213SD %XMM3,%XMM4,%XMM4 | 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,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VUCOMISD %XMM2,%XMM4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMINSD %XMM2,%XMM4,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD %YMM6,%YMM28,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM8,%YMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %YMM4,%YMM29,%YMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMPD $0x55,%YMM8,%YMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %YMM6,%YMM30,%YMM6 | 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 %YMM6,%YMM6,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMINSD %XMM2,%XMM3,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM4,%XMM6,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VEXTRACTF128 $0x1,%YMM3,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VUNPCKLPD %XMM4,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM6,%XMM7,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM4,%XMM6,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VINSERTF128 $0x1,%XMM6,%YMM2,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPERMILPD $0x1,%XMM7,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM4,%XMM6,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSQRTSD %XMM4,%XMM4,%XMM4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-19 | 4.50-6 |
VMOVSD %XMM4,(%R8,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VCMPPD $0x1,%YMM2,%YMM3,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
KMOVD %K0,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
MOV $0x3,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVB %RBX,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x4,%EBX | 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 %RBX,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x5,%EBX | 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 %RBX,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x6,%EBX | 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 %RBX,%R10 | 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,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VADDSD 0x180(%RDI,%R10,8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%R11,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD 0x1c0(%RDI,%R10,8),%XMM8,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%RAX,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD 0x200(%RDI,%R10,8),%XMM31,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%R15,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R12,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 45fc80 | 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 | 591 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 29 |
used ymm registers | 8 |
used zmm registers | 0 |
nb stack references | 3 |
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 | 5.00 | 5.00 | 4.00 | 23.00 | 22.00 | 4.00 |
cycles | 30.50 | 30.50 | 5.00 | 5.00 | 4.00 | 23.00 | 22.00 | 4.00 |
Cycles executing div or sqrt instructions | 4.50-6.00 |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 56.15-57.50 |
Stall cycles | 25.36-26.71 |
ROB full (events) | 2.58-6.57 |
RS full (events) | 43.62-38.48 |
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 | 38% |
load | 20% |
store | 0% |
mul | 45% |
add-sub | 29% |
fma | 52% |
div/sqrt | 0% |
other | 44% |
all | 36% |
load | 20% |
store | 0% |
mul | 45% |
add-sub | 29% |
fma | 52% |
div/sqrt | 0% |
other | 39% |
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 | 15% |
store | 12% |
mul | 20% |
add-sub | 20% |
fma | 22% |
div/sqrt | 12% |
other | 19% |
all | 18% |
load | 15% |
store | 12% |
mul | 20% |
add-sub | 20% |
fma | 22% |
div/sqrt | 12% |
other | 17% |
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,%R12D | 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 %R12D,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDX,%R14,8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVDDUP 0x49c680(,%RCX,8),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD %XMM26,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%RSI,%R14,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVHPD (%R9,%R14,8),%XMM2,%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
VMULSD %XMM0,%XMM20,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBPD 0x110(%RSP),%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD %XMM1,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM0,%XMM2,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMULPD %XMM4,%XMM10,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM2,%XMM0,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM4,%XMM16,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x3,%XMM2,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213PD %XMM6,%XMM11,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VROUNDPD $0x9,%XMM4,%XMM4 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VFMADD231SD %XMM2,%XMM15,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM2,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMADD213SD %XMM3,%XMM12,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VROUNDSD $0x9,%XMM6,%XMM6,%XMM3 | 2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 8 | 1 |
VPERMILPD $0x1,%XMM4,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVDDUP %XMM3,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VFMSUB231SD %XMM21,%XMM4,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM22,%XMM8,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMSUB231SD %XMM3,%XMM23,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB213PD %XMM2,%XMM13,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231PD %XMM4,%XMM9,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMSUB231PD %XMM6,%XMM14,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM24,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM8,%XMM25,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM8,%XMM31 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD 0xb8(%RSP),%XMM31,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM0,%YMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VUNPCKLPD %XMM6,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMULPD %XMM2,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM8,%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 |
VBLENDPD $0x1,%XMM4,%XMM8,%XMM2 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VFMADD213PD %XMM3,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM2,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VUCOMISD %XMM3,%XMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
SETB %R10B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMINSD %XMM3,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM27,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM8,%XMM17,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %XMM12,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VADDSD %XMM31,%XMM18,%XMM12 | 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 %XMM12,%XMM12,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %XMM5,%XMM12 | 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 |
VMINSD %XMM2,%XMM3,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD 0x100(%RSP),%XMM8,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 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,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM3,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM0,%XMM19,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD213SD %XMM3,%XMM4,%XMM4 | 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,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VUCOMISD %XMM2,%XMM4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMINSD %XMM2,%XMM4,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDPD %YMM6,%YMM28,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM8,%YMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %YMM4,%YMM29,%YMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMPD $0x55,%YMM8,%YMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %YMM6,%YMM30,%YMM6 | 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 %YMM6,%YMM6,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMINSD %XMM2,%XMM3,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM3,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM4,%XMM6,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VEXTRACTF128 $0x1,%YMM3,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VUNPCKLPD %XMM4,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM6,%XMM7,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUNPCKLPD %XMM4,%XMM6,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VINSERTF128 $0x1,%XMM6,%YMM2,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPERMILPD $0x1,%XMM7,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMINSD %XMM4,%XMM6,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSQRTSD %XMM4,%XMM4,%XMM4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-19 | 4.50-6 |
VMOVSD %XMM4,(%R8,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VCMPPD $0x1,%YMM2,%YMM3,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
KMOVD %K0,%ECX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
MOV $0x3,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVB %RBX,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x4,%EBX | 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 %RBX,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x5,%EBX | 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 %RBX,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV $0x6,%EBX | 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 %RBX,%R10 | 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,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VADDSD 0x180(%RDI,%R10,8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%R11,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD 0x1c0(%RDI,%R10,8),%XMM8,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%RAX,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD 0x200(%RDI,%R10,8),%XMM31,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,(%R15,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R12,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 45fc80 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |