Function: qmcplusplus::BsplineFunctor<double>::evaluateVGL(int, int, int, double const*, double*, do ... | Module: exec | Source: BsplineFunctor.h:275-339 [...] | Coverage: 0.59% |
---|
Function: qmcplusplus::BsplineFunctor<double>::evaluateVGL(int, int, int, double const*, double*, do ... | Module: exec | Source: BsplineFunctor.h:275-339 [...] | Coverage: 0.59% |
---|
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 275 - 339 |
-------------------------------------------------------------------------------- |
275: { |
276: real_type dSquareDeltaRinv = DeltaRInv * DeltaRInv; |
[...] |
284: int iLimit = iEnd - iStart; |
285: const real_type* distArray = _distArray + iStart; |
[...] |
291: for (int jat = 0; jat < iLimit; jat++) |
292: { |
293: real_type r = distArray[jat]; |
294: if (r < cutoff_radius && iStart + jat != iat) |
295: { |
296: distIndices[iCount] = jat; |
297: distArrayCompressed[iCount] = r; |
298: iCount++; |
299: } |
300: } |
301: |
302: #pragma omp simd |
303: for (int j = 0; j < iCount; j++) |
304: { |
305: real_type r = distArrayCompressed[j]; |
306: int iScatter = distIndices[j]; |
307: real_type rinv = cOne / r; |
308: r *= DeltaRInv; |
309: int iGather = (int)r; |
310: real_type t = r - real_type(iGather); |
311: real_type tp0 = t * t * t; |
312: real_type tp1 = t * t; |
313: real_type tp2 = t; |
314: |
315: real_type sCoef0 = SplineCoefs[iGather + 0]; |
316: real_type sCoef1 = SplineCoefs[iGather + 1]; |
317: real_type sCoef2 = SplineCoefs[iGather + 2]; |
318: real_type sCoef3 = SplineCoefs[iGather + 3]; |
319: |
320: // clang-format off |
321: laplArray[iScatter] = dSquareDeltaRinv * |
322: (sCoef0*( d2A[ 2]*tp2 + d2A[ 3])+ |
323: sCoef1*( d2A[ 6]*tp2 + d2A[ 7])+ |
324: sCoef2*( d2A[10]*tp2 + d2A[11])+ |
325: sCoef3*( d2A[14]*tp2 + d2A[15])); |
326: |
327: gradArray[iScatter] = DeltaRInv * rinv * |
328: (sCoef0*( dA[ 1]*tp1 + dA[ 2]*tp2 + dA[ 3])+ |
329: sCoef1*( dA[ 5]*tp1 + dA[ 6]*tp2 + dA[ 7])+ |
330: sCoef2*( dA[ 9]*tp1 + dA[10]*tp2 + dA[11])+ |
331: sCoef3*( dA[13]*tp1 + dA[14]*tp2 + dA[15])); |
332: |
333: valArray[iScatter] = (sCoef0*(A[ 0]*tp0 + A[ 1]*tp1 + A[ 2]*tp2 + A[ 3])+ |
334: sCoef1*(A[ 4]*tp0 + A[ 5]*tp1 + A[ 6]*tp2 + A[ 7])+ |
335: sCoef2*(A[ 8]*tp0 + A[ 9]*tp1 + A[10]*tp2 + A[11])+ |
336: sCoef3*(A[12]*tp0 + A[13]*tp1 + A[14]*tp2 + A[15])); |
337: // clang-format on |
338: } |
339: } |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/stl_vector.h: 1145 - 1145 |
-------------------------------------------------------------------------------- |
1145: return *(this->_M_impl._M_start + __n); |
0x41aa40 PUSH %RBP |
0x41aa41 MOV %RSP,%RBP |
0x41aa44 PUSH %R15 |
0x41aa46 PUSH %R14 |
0x41aa48 PUSH %R13 |
0x41aa4a PUSH %R12 |
0x41aa4c PUSH %RBX |
0x41aa4d AND $-0x40,%RSP |
0x41aa51 SUB $0x700,%RSP |
0x41aa58 SUB %EDX,%ECX |
0x41aa5a TEST %ECX,%ECX |
0x41aa5c JLE 41b5fe |
0x41aa62 MOV 0x28(%RBP),%R13 |
0x41aa66 MOV 0x20(%RBP),%R14 |
0x41aa6a MOVSXD %EDX,%R11 |
0x41aa6d VMOVSD 0x8(%RDI),%XMM0 |
0x41aa72 MOV %ECX,%ECX |
0x41aa74 MOV $-0x10,%EBX |
0x41aa79 AND %RCX,%RBX |
0x41aa7c JE 41b2e6 |
0x41aa82 MOV %RCX,0x300(%RSP) |
0x41aa8a VPBROADCASTD %ESI,%ZMM1 |
0x41aa90 VBROADCASTSD %XMM0,%ZMM2 |
0x41aa96 MOV %EDX,%R15D |
0x41aa99 MOV %R11,0x2c0(%RSP) |
0x41aaa1 MOV %R8,0x280(%RSP) |
0x41aaa9 LEA (%R8,%R11,8),%R12 |
0x41aaad VPXOR %XMM6,%XMM6,%XMM6 |
0x41aab1 XOR %EAX,%EAX |
0x41aab3 VMOVDQU64 0x74cc3(%RIP),%ZMM3 |
0x41aabd VPXOR %XMM4,%XMM4,%XMM4 |
0x41aac1 VPTERNLOGD $-0x1,%ZMM5,%ZMM5,%ZMM5 |
0x41aac8 JMP 41ab18 |
0x41aaca NOPW (%RAX,%RAX,1) |
(227) 0x41aad0 VMOVDQA32 %ZMM9,%ZMM6{%K1} |
(227) 0x41aad6 VEXTRACTI64X4 $0x1,%ZMM6,%YMM7 |
(227) 0x41aadd VPADDD %ZMM7,%ZMM6,%ZMM6 |
(227) 0x41aae3 VEXTRACTI128 $0x1,%YMM6,%XMM7 |
(227) 0x41aae9 VPADDD %ZMM7,%ZMM6,%ZMM6 |
(227) 0x41aaef VPSHUFD $-0x12,%XMM6,%XMM7 |
(227) 0x41aaf4 VPADDD %ZMM7,%ZMM6,%ZMM6 |
(227) 0x41aafa VPSHUFD $0x55,%XMM6,%XMM7 |
(227) 0x41aaff VPADDD %ZMM7,%ZMM6,%ZMM7 |
(227) 0x41ab05 VPBLENDW $0x3,%XMM7,%XMM4,%XMM6 |
(227) 0x41ab0b ADD $0x10,%RAX |
(227) 0x41ab0f CMP %RBX,%RAX |
(227) 0x41ab12 JAE 41abaf |
(227) 0x41ab18 VMOVUPD (%R12,%RAX,8),%ZMM7 |
(227) 0x41ab1f VMOVUPD 0x40(%R12,%RAX,8),%ZMM8 |
(227) 0x41ab27 LEA (%R15,%RAX,1),%ECX |
(227) 0x41ab2b VPBROADCASTD %ECX,%ZMM9 |
(227) 0x41ab31 VPADDD %ZMM3,%ZMM9,%ZMM9 |
(227) 0x41ab37 VCMPPD $0x1,%ZMM2,%ZMM7,%K0 |
(227) 0x41ab3e VCMPPD $0x1,%ZMM2,%ZMM8,%K1 |
(227) 0x41ab45 KUNPCKBW %K0,%K1,%K1 |
(227) 0x41ab49 VPCMPNEQD %ZMM1,%ZMM9,%K1{%K1} |
(227) 0x41ab50 KORTESTW %K1,%K1 |
(227) 0x41ab54 VPXOR %XMM9,%XMM9,%XMM9 |
(227) 0x41ab59 JE 41aad0 |
(227) 0x41ab5f VMOVD %XMM6,%ECX |
(227) 0x41ab63 MOVSXD %ECX,%R10 |
(227) 0x41ab66 VPBROADCASTD %EAX,%ZMM9 |
(227) 0x41ab6c VPORD %ZMM3,%ZMM9,%ZMM9 |
(227) 0x41ab72 VPCOMPRESSD %ZMM9,(%R13,%R10,4){%K1} |
(227) 0x41ab7a MOV %R13,%R8 |
(227) 0x41ab7d LEA (%R14,%R10,8),%R13 |
(227) 0x41ab81 KSHIFTRW $0x8,%K1,%K2 |
(227) 0x41ab87 KMOVB %K1,%R11D |
(227) 0x41ab8b XOR %ECX,%ECX |
(227) 0x41ab8d POPCNT %R11D,%ECX |
(227) 0x41ab92 VCOMPRESSPD %ZMM8,(%R13,%RCX,8){%K2} |
(227) 0x41ab9a MOV %R8,%R13 |
(227) 0x41ab9d VCOMPRESSPD %ZMM7,(%R14,%R10,8){%K1} |
(227) 0x41aba4 VPSUBD %ZMM5,%ZMM6,%ZMM9 |
(227) 0x41abaa JMP 41aad0 |
0x41abaf VMOVD %XMM7,%EAX |
0x41abb3 MOV 0x300(%RSP),%RCX |
0x41abbb CMP %RCX,%RBX |
0x41abbe MOV 0x2c0(%RSP),%R11 |
0x41abc6 MOV 0x280(%RSP),%R8 |
0x41abce JNE 41b2ea |
0x41abd4 TEST %EAX,%EAX |
0x41abd6 JLE 41b5fe |
0x41abdc VMOVSD 0x238(%RDI),%XMM0 |
0x41abe4 MOV 0x18(%RBP),%RDX |
0x41abe8 MOV 0x10(%RBP),%R10 |
0x41abec VMOVSD 0x128(%RDI),%XMM18 |
0x41abf3 VMOVSD 0x130(%RDI),%XMM16 |
0x41abfa VMOVSD 0x148(%RDI),%XMM15 |
0x41ac02 VMOVSD 0x150(%RDI),%XMM19 |
0x41ac09 VMOVSD 0x168(%RDI),%XMM6 |
0x41ac11 VMOVSD 0x170(%RDI),%XMM7 |
0x41ac19 VMOVSD 0x188(%RDI),%XMM2 |
0x41ac21 VMOVSD 0x190(%RDI),%XMM1 |
0x41ac29 VMOVSD 0xa0(%RDI),%XMM9 |
0x41ac31 VMOVSD 0xa8(%RDI),%XMM5 |
0x41ac39 VMOVSD 0xb0(%RDI),%XMM31 |
0x41ac40 VMOVSD 0xc0(%RDI),%XMM4 |
0x41ac48 VMOVSD 0xc8(%RDI),%XMM29 |
0x41ac4f VMOVSD 0xd0(%RDI),%XMM8 |
0x41ac57 VMOVSD 0xe0(%RDI),%XMM3 |
0x41ac5f VMOVUPS %XMM3,0x20(%RSP) |
0x41ac65 VMOVSD 0xe8(%RDI),%XMM17 |
0x41ac6c VMOVSD 0xf0(%RDI),%XMM3 |
0x41ac74 VMOVUPS %XMM3,0x30(%RSP) |
0x41ac7a VMOVSD 0x100(%RDI),%XMM26 |
0x41ac81 VMOVSD 0x108(%RDI),%XMM3 |
0x41ac89 VMOVUPS %XMM3,0x40(%RSP) |
0x41ac8f VMOVSD 0x110(%RDI),%XMM24 |
0x41ac96 VMOVSD 0x18(%RDI),%XMM23 |
0x41ac9d VMOVSD 0x20(%RDI),%XMM20 |
0x41aca4 VMOVSD 0x28(%RDI),%XMM21 |
0x41acab VMOVSD 0x30(%RDI),%XMM30 |
0x41acb2 VMOVSD 0x38(%RDI),%XMM10 |
0x41acb7 VMOVSD 0x40(%RDI),%XMM11 |
0x41acbc VMOVSD 0x48(%RDI),%XMM12 |
0x41acc1 VMOVSD 0x50(%RDI),%XMM14 |
0x41acc6 VMOVSD 0x58(%RDI),%XMM28 |
0x41accd VMOVSD 0x60(%RDI),%XMM25 |
0x41acd4 MOV 0x218(%RDI),%RCX |
0x41acdb VMOVSD 0x68(%RDI),%XMM3 |
0x41ace0 VMOVUPS %XMM3,0x70(%RSP) |
0x41ace6 MOV %EAX,%EAX |
0x41ace8 VMOVSD 0x70(%RDI),%XMM13 |
0x41aced VMOVSD 0x78(%RDI),%XMM3 |
0x41acf2 VMOVUPS %XMM3,0x60(%RSP) |
0x41acf8 VMOVSD 0x80(%RDI),%XMM3 |
0x41ad00 VMOVUPS %XMM3,0x80(%RSP) |
0x41ad09 VMOVSD 0x88(%RDI),%XMM3 |
0x41ad11 VMOVUPS %XMM3,0x90(%RSP) |
0x41ad1a MOV $-0x8,%ESI |
0x41ad1f VMOVSD 0x90(%RDI),%XMM3 |
0x41ad27 VMOVUPS %XMM3,0xa0(%RSP) |
0x41ad30 MOV %RAX,%RDI |
0x41ad33 VMULSD %XMM0,%XMM0,%XMM22 |
0x41ad39 VPBROADCASTQ %R11,%ZMM27 |
0x41ad3f AND %RAX,%RSI |
0x41ad42 VMOVUPS %XMM17,0x270(%RSP) |
0x41ad4a VMOVUPD %XMM8,0x260(%RSP) |
0x41ad53 VMOVUPD %XMM4,0x250(%RSP) |
0x41ad5c VMOVUPD %XMM29,0x240(%RSP) |
0x41ad64 VMOVUPD %XMM31,0x230(%RSP) |
0x41ad6c VMOVUPD %XMM9,0x220(%RSP) |
0x41ad75 VMOVUPS %XMM5,0x210(%RSP) |
0x41ad7e VMOVUPS %XMM2,0x200(%RSP) |
0x41ad87 VMOVUPD %XMM1,0x1f0(%RSP) |
0x41ad90 VMOVUPS %XMM6,0x1e0(%RSP) |
0x41ad99 VMOVUPD %XMM7,0x1d0(%RSP) |
0x41ada2 VMOVUPD %XMM15,0x1c0(%RSP) |
0x41adab JE 41b32c |
0x41adb1 VMOVUPD %XMM13,0x50(%RSP) |
0x41adb7 VMOVAPD %XMM22,%XMM13 |
0x41adbd VMOVAPD %XMM19,%XMM22 |
0x41adc3 VMOVAPD %XMM15,%XMM19 |
0x41adc9 VMOVUPD %XMM0,0xc0(%RSP) |
0x41add2 VBROADCASTSD %XMM0,%ZMM15 |
0x41add8 VMOVUPD %XMM18,0xe0(%RSP) |
0x41ade0 VBROADCASTSD %XMM18,%ZMM0 |
0x41ade6 VMOVUPD %ZMM0,0x300(%RSP) |
0x41adee VMOVUPD %XMM16,0xd0(%RSP) |
0x41adf6 VBROADCASTSD %XMM16,%ZMM0 |
0x41adfc VMOVUPD %ZMM0,0x2c0(%RSP) |
0x41ae04 VBROADCASTSD %XMM19,%ZMM0 |
0x41ae0a VMOVUPD %ZMM0,0x280(%RSP) |
0x41ae12 VMOVUPD %XMM22,0xf0(%RSP) |
0x41ae1a VBROADCASTSD %XMM22,%ZMM0 |
0x41ae20 VMOVUPD %ZMM0,0x680(%RSP) |
0x41ae28 VBROADCASTSD %XMM6,%ZMM0 |
0x41ae2e VMOVUPS %ZMM0,0x640(%RSP) |
0x41ae36 VBROADCASTSD %XMM7,%ZMM0 |
0x41ae3c VMOVUPD %ZMM0,0x600(%RSP) |
0x41ae44 VBROADCASTSD %XMM2,%ZMM0 |
0x41ae4a VMOVUPS %ZMM0,0x5c0(%RSP) |
0x41ae52 VBROADCASTSD %XMM1,%ZMM0 |
0x41ae58 VMOVUPD %ZMM0,0x580(%RSP) |
0x41ae60 VMOVUPD %XMM13,0xb0(%RSP) |
0x41ae69 VBROADCASTSD %XMM13,%ZMM0 |
0x41ae6f VMOVUPD %ZMM0,0x540(%RSP) |
0x41ae77 VBROADCASTSD %XMM9,%ZMM0 |
0x41ae7d VMOVUPD %ZMM0,0x500(%RSP) |
0x41ae85 VBROADCASTSD %XMM5,%ZMM0 |
0x41ae8b VMOVUPS %ZMM0,0x4c0(%RSP) |
0x41ae93 VBROADCASTSD %XMM31,%ZMM0 |
0x41ae99 VMOVUPD %ZMM0,0x480(%RSP) |
0x41aea1 VBROADCASTSD %XMM4,%ZMM0 |
0x41aea7 VMOVUPD %ZMM0,0x440(%RSP) |
0x41aeaf VBROADCASTSD %XMM29,%ZMM0 |
0x41aeb5 VMOVUPD %ZMM0,0x400(%RSP) |
0x41aebd VBROADCASTSD %XMM8,%ZMM0 |
0x41aec3 VMOVUPD %ZMM0,0x3c0(%RSP) |
0x41aecb VBROADCASTSD 0x20(%RSP),%ZMM0 |
0x41aed3 VMOVUPS %ZMM0,0x380(%RSP) |
0x41aedb VBROADCASTSD %XMM17,%ZMM0 |
0x41aee1 VMOVUPS %ZMM0,0x340(%RSP) |
0x41aee9 VBROADCASTSD 0x30(%RSP),%ZMM5 |
0x41aef1 VMOVUPD %XMM26,0x100(%RSP) |
0x41aef9 VBROADCASTSD %XMM26,%ZMM1 |
0x41aeff VBROADCASTSD 0x40(%RSP),%ZMM6 |
0x41af07 VMOVUPD %XMM24,0x110(%RSP) |
0x41af0f VBROADCASTSD %XMM24,%ZMM2 |
0x41af15 VMOVUPD %XMM23,0x130(%RSP) |
0x41af1d VBROADCASTSD %XMM23,%ZMM7 |
0x41af23 VMOVUPD %XMM20,0x120(%RSP) |
0x41af2b VBROADCASTSD %XMM20,%ZMM3 |
0x41af31 VMOVUPD %XMM21,0x140(%RSP) |
0x41af39 VBROADCASTSD %XMM21,%ZMM8 |
0x41af3f VMOVUPD %XMM30,0x150(%RSP) |
0x41af47 VBROADCASTSD %XMM30,%ZMM9 |
0x41af4d VMOVUPD %XMM10,0x170(%RSP) |
0x41af56 VBROADCASTSD %XMM10,%ZMM10 |
0x41af5c VMOVUPD %XMM11,0x160(%RSP) |
0x41af65 VBROADCASTSD %XMM11,%ZMM11 |
0x41af6b VMOVUPD %XMM12,0x180(%RSP) |
0x41af74 VBROADCASTSD %XMM12,%ZMM12 |
0x41af7a VMOVUPD %XMM14,0x190(%RSP) |
0x41af83 VBROADCASTSD %XMM14,%ZMM14 |
0x41af89 VMOVUPD %XMM28,0x1b0(%RSP) |
0x41af91 VBROADCASTSD %XMM28,%ZMM13 |
0x41af97 VMOVUPD %XMM25,0x1a0(%RSP) |
0x41af9f VBROADCASTSD %XMM25,%ZMM0 |
0x41afa5 XOR %EBX,%EBX |
0x41afa7 VMOVUPD 0x70(%RSP),%XMM16 |
0x41afaf VBROADCASTSD %XMM16,%ZMM16 |
0x41afb5 VBROADCASTSD 0x50(%RSP),%ZMM17 |
0x41afbd VMOVUPD 0x60(%RSP),%XMM18 |
0x41afc5 VBROADCASTSD %XMM18,%ZMM18 |
0x41afcb VMOVUPD 0x80(%RSP),%XMM19 |
0x41afd3 VBROADCASTSD %XMM19,%ZMM19 |
0x41afd9 VMOVUPD 0x90(%RSP),%XMM20 |
0x41afe1 VBROADCASTSD %XMM20,%ZMM20 |
0x41afe7 VMOVUPD 0xa0(%RSP),%XMM21 |
0x41afef VBROADCASTSD %XMM21,%ZMM21 |
0x41aff5 NOPW %CS:(%RAX,%RAX,1) |
(225) 0x41b000 VMOVUPD (%R14,%RBX,8),%ZMM22 |
(225) 0x41b007 VMULPD %ZMM15,%ZMM22,%ZMM24 |
(225) 0x41b00d VMOVDQA64 %ZMM27,%ZMM4 |
(225) 0x41b013 VCVTTPD2DQ %ZMM24,%YMM27 |
(225) 0x41b019 VXORPD %XMM28,%XMM28,%XMM28 |
(225) 0x41b01f KXNORW %K0,%K0,%K1 |
(225) 0x41b023 VGATHERDPD (%RCX,%YMM27,8),%ZMM28{%K1} |
(225) 0x41b02a VXORPD %XMM26,%XMM26,%XMM26 |
(225) 0x41b030 KXNORW %K0,%K0,%K1 |
(225) 0x41b034 VXORPD %XMM25,%XMM25,%XMM25 |
(225) 0x41b03a KXNORW %K0,%K0,%K2 |
(225) 0x41b03e VGATHERDPD 0x8(%RCX,%YMM27,8),%ZMM26{%K1} |
(225) 0x41b046 VXORPD %XMM23,%XMM23,%XMM23 |
(225) 0x41b04c VGATHERDPD 0x10(%RCX,%YMM27,8),%ZMM25{%K2} |
(225) 0x41b054 KXNORW %K0,%K0,%K1 |
(225) 0x41b058 VGATHERDPD 0x18(%RCX,%YMM27,8),%ZMM23{%K1} |
(225) 0x41b060 VRNDSCALEPD $0xb,%ZMM24,%ZMM27 |
(225) 0x41b067 VSUBPD %ZMM27,%ZMM24,%ZMM29 |
(225) 0x41b06d VMOVAPD %ZMM29,%ZMM27 |
(225) 0x41b073 VMOVUPD 0x4c0(%RSP),%ZMM24 |
(225) 0x41b07b VFMADD132PD 0x500(%RSP),%ZMM24,%ZMM27 |
(225) 0x41b083 VFMADD213PD 0x480(%RSP),%ZMM29,%ZMM27 |
(225) 0x41b08b VMOVAPD %ZMM29,%ZMM30 |
(225) 0x41b091 VMOVAPD %ZMM29,%ZMM24 |
(225) 0x41b097 VMOVUPD 0x2c0(%RSP),%ZMM31 |
(225) 0x41b09f VFMADD132PD 0x300(%RSP),%ZMM31,%ZMM24 |
(225) 0x41b0a7 VMULPD %ZMM28,%ZMM24,%ZMM24 |
(225) 0x41b0ad VMOVUPD 0x680(%RSP),%ZMM31 |
(225) 0x41b0b5 VFMADD132PD 0x280(%RSP),%ZMM31,%ZMM30 |
(225) 0x41b0bd VFMADD213PD %ZMM24,%ZMM26,%ZMM30 |
(225) 0x41b0c3 VMOVAPD %ZMM29,%ZMM24 |
(225) 0x41b0c9 VFMADD213PD %ZMM3,%ZMM7,%ZMM24 |
(225) 0x41b0cf VFMADD213PD %ZMM8,%ZMM29,%ZMM24 |
(225) 0x41b0d5 VFMADD213PD %ZMM9,%ZMM29,%ZMM24 |
(225) 0x41b0db VMULPD %ZMM28,%ZMM27,%ZMM27 |
(225) 0x41b0e1 VMULPD %ZMM28,%ZMM24,%ZMM24 |
(225) 0x41b0e7 VMOVAPD %ZMM29,%ZMM28 |
(225) 0x41b0ed VMOVUPD 0x400(%RSP),%ZMM31 |
(225) 0x41b0f5 VFMADD132PD 0x440(%RSP),%ZMM31,%ZMM28 |
(225) 0x41b0fd VFMADD213PD 0x3c0(%RSP),%ZMM29,%ZMM28 |
(225) 0x41b105 VFMADD213PD %ZMM27,%ZMM26,%ZMM28 |
(225) 0x41b10b VMOVAPD %ZMM29,%ZMM27 |
(225) 0x41b111 VFMADD213PD %ZMM11,%ZMM10,%ZMM27 |
(225) 0x41b117 VFMADD213PD %ZMM12,%ZMM29,%ZMM27 |
(225) 0x41b11d VFMADD213PD %ZMM14,%ZMM29,%ZMM27 |
(225) 0x41b123 VFMADD213PD %ZMM24,%ZMM26,%ZMM27 |
(225) 0x41b129 VMOVAPD %ZMM29,%ZMM24 |
(225) 0x41b12f VMOVUPD 0x600(%RSP),%ZMM26 |
(225) 0x41b137 VFMADD132PD 0x640(%RSP),%ZMM26,%ZMM24 |
(225) 0x41b13f VFMADD213PD %ZMM30,%ZMM25,%ZMM24 |
(225) 0x41b145 VMOVAPD %ZMM29,%ZMM26 |
(225) 0x41b14b VMOVUPD 0x340(%RSP),%ZMM30 |
(225) 0x41b153 VFMADD132PD 0x380(%RSP),%ZMM30,%ZMM26 |
(225) 0x41b15b VFMADD213PD %ZMM5,%ZMM29,%ZMM26 |
(225) 0x41b161 VFMADD213PD %ZMM28,%ZMM25,%ZMM26 |
(225) 0x41b167 VMOVAPD %ZMM29,%ZMM28 |
(225) 0x41b16d VFMADD213PD %ZMM0,%ZMM13,%ZMM28 |
(225) 0x41b173 VFMADD213PD %ZMM16,%ZMM29,%ZMM28 |
(225) 0x41b179 VFMADD213PD %ZMM17,%ZMM29,%ZMM28 |
(225) 0x41b17f VFMADD213PD %ZMM27,%ZMM25,%ZMM28 |
(225) 0x41b185 VMOVDQA64 %ZMM4,%ZMM27 |
(225) 0x41b18b VMOVAPD %ZMM29,%ZMM25 |
(225) 0x41b191 VMOVUPD 0x580(%RSP),%ZMM4 |
(225) 0x41b199 VFMADD132PD 0x5c0(%RSP),%ZMM4,%ZMM25 |
(225) 0x41b1a1 VFMADD213PD %ZMM24,%ZMM23,%ZMM25 |
(225) 0x41b1a7 VMOVAPD %ZMM29,%ZMM24 |
(225) 0x41b1ad VFMADD213PD %ZMM6,%ZMM1,%ZMM24 |
(225) 0x41b1b3 VFMADD213PD %ZMM2,%ZMM29,%ZMM24 |
(225) 0x41b1b9 VFMADD213PD %ZMM26,%ZMM23,%ZMM24 |
(225) 0x41b1bf VPMOVSXDQ (%R13,%RBX,4),%ZMM26 |
(225) 0x41b1c7 VMULPD 0x540(%RSP),%ZMM25,%ZMM25 |
(225) 0x41b1cf VPADDQ %ZMM26,%ZMM27,%ZMM26 |
(225) 0x41b1d5 KXNORW %K0,%K0,%K1 |
(225) 0x41b1d9 VSCATTERQPD %ZMM25,(%RDX,%ZMM26,8){%K1} |
(225) 0x41b1e0 VMULPD %ZMM15,%ZMM24,%ZMM24 |
(225) 0x41b1e6 VDIVPD %ZMM22,%ZMM24,%ZMM22 |
(225) 0x41b1ec KXNORW %K0,%K0,%K1 |
(225) 0x41b1f0 VSCATTERQPD %ZMM22,(%R10,%ZMM26,8){%K1} |
(225) 0x41b1f7 VMOVAPD %ZMM29,%ZMM22 |
(225) 0x41b1fd VFMADD213PD %ZMM19,%ZMM18,%ZMM22 |
(225) 0x41b203 VFMADD213PD %ZMM20,%ZMM29,%ZMM22 |
(225) 0x41b209 VFMADD213PD %ZMM21,%ZMM29,%ZMM22 |
(225) 0x41b20f VFMADD213PD %ZMM28,%ZMM23,%ZMM22 |
(225) 0x41b215 KXNORW %K0,%K0,%K1 |
(225) 0x41b219 VSCATTERQPD %ZMM22,(%R9,%ZMM26,8){%K1} |
(225) 0x41b220 ADD $0x8,%RBX |
(225) 0x41b224 CMP %RSI,%RBX |
(225) 0x41b227 JB 41b000 |
0x41b22d CMP %RDI,%RSI |
0x41b230 VMOVUPD 0x1b0(%RSP),%XMM28 |
0x41b238 VMOVUPD 0x1a0(%RSP),%XMM25 |
0x41b240 VMOVUPD 0x50(%RSP),%XMM13 |
0x41b246 VMOVUPD 0x190(%RSP),%XMM14 |
0x41b24f VMOVUPD 0x180(%RSP),%XMM12 |
0x41b258 VMOVUPD 0x170(%RSP),%XMM10 |
0x41b261 VMOVUPD 0x160(%RSP),%XMM11 |
0x41b26a VMOVUPD 0x150(%RSP),%XMM30 |
0x41b272 VMOVUPD 0x140(%RSP),%XMM17 |
0x41b27a VMOVUPD 0x130(%RSP),%XMM23 |
0x41b282 VMOVUPD 0x120(%RSP),%XMM20 |
0x41b28a VMOVUPD 0x110(%RSP),%XMM24 |
0x41b292 VMOVUPD 0x100(%RSP),%XMM6 |
0x41b29b VMOVUPD 0x40(%RSP),%XMM26 |
0x41b2a3 VMOVUPD 0x30(%RSP),%XMM5 |
0x41b2a9 VMOVUPD 0x20(%RSP),%XMM3 |
0x41b2af VMOVUPD 0xf0(%RSP),%XMM19 |
0x41b2b7 VMOVUPD 0xe0(%RSP),%XMM18 |
0x41b2bf VMOVUPD 0xd0(%RSP),%XMM16 |
0x41b2c7 VMOVUPD 0xc0(%RSP),%XMM0 |
0x41b2d0 VMOVUPD 0xb0(%RSP),%XMM22 |
0x41b2d8 JE 41b5fe |
0x41b2de VPBROADCASTQ %RDI,%ZMM2 |
0x41b2e4 JMP 41b354 |
0x41b2e6 XOR %EBX,%EBX |
0x41b2e8 XOR %EAX,%EAX |
0x41b2ea SUB %EDX,%ESI |
0x41b2ec LEA (%R8,%R11,8),%RDX |
0x41b2f0 JMP 41b30c |
0x41b2f2 NOPW %CS:(%RAX,%RAX,1) |
(226) 0x41b300 INC %RBX |
(226) 0x41b303 CMP %RBX,%RCX |
(226) 0x41b306 JE 41abd4 |
(226) 0x41b30c VMOVSD (%RDX,%RBX,8),%XMM1 |
(226) 0x41b311 VUCOMISD %XMM1,%XMM0 |
(226) 0x41b315 JBE 41b300 |
(226) 0x41b317 CMP %EBX,%ESI |
(226) 0x41b319 JE 41b300 |
(226) 0x41b31b CLTQ |
(226) 0x41b31d MOV %EBX,(%R13,%RAX,4) |
(226) 0x41b322 VMOVSD %XMM1,(%R14,%RAX,8) |
(226) 0x41b328 INC %EAX |
(226) 0x41b32a JMP 41b300 |
0x41b32c VPBROADCASTQ %RDI,%ZMM2 |
0x41b332 XOR %ESI,%ESI |
0x41b334 VMOVAPD %XMM21,%XMM17 |
0x41b33a VMOVAPD %XMM26,%XMM6 |
0x41b340 VMOVUPD 0x40(%RSP),%XMM26 |
0x41b348 VMOVUPD 0x30(%RSP),%XMM5 |
0x41b34e VMOVUPD 0x20(%RSP),%XMM3 |
0x41b354 VPBROADCASTQ %RSI,%ZMM1 |
0x41b35a VPORQ 0x7445c(%RIP),%ZMM1,%ZMM1 |
0x41b364 VPCMPLTUQ %ZMM2,%ZMM1,%K1 |
0x41b36b KORTESTB %K1,%K1 |
0x41b36f JE 41b5fe |
0x41b375 VBROADCASTSD %XMM0,%ZMM2 |
0x41b37b KMOVQ %K1,%K2 |
0x41b380 VMOVUPD (%R14,%RSI,8),%ZMM21{%K1}{z} |
0x41b387 VMULPD %ZMM2,%ZMM21,%ZMM1 |
0x41b38d VCVTTPD2DQ %ZMM1,%YMM7 |
0x41b393 VXORPD %XMM4,%XMM4,%XMM4 |
0x41b397 VGATHERDPD (%RCX,%YMM7,8),%ZMM4{%K2} |
0x41b39e KMOVQ %K1,%K2 |
0x41b3a3 VXORPD %XMM29,%XMM29,%XMM29 |
0x41b3a9 VGATHERDPD 0x8(%RCX,%YMM7,8),%ZMM29{%K2} |
0x41b3b1 KMOVQ %K1,%K2 |
0x41b3b6 VXORPD %XMM15,%XMM15,%XMM15 |
0x41b3bb VGATHERDPD 0x10(%RCX,%YMM7,8),%ZMM15{%K2} |
0x41b3c3 KMOVQ %K1,%K2 |
0x41b3c8 VXORPD %XMM0,%XMM0,%XMM0 |
0x41b3cc VGATHERDPD 0x18(%RCX,%YMM7,8),%ZMM0{%K2} |
0x41b3d4 VRNDSCALEPD $0xb,%ZMM1,%ZMM7 |
0x41b3db VSUBPD %ZMM7,%ZMM1,%ZMM1 |
0x41b3e1 VBROADCASTSD %XMM18,%ZMM7 |
0x41b3e7 VBROADCASTSD %XMM16,%ZMM8 |
0x41b3ed VFMADD231PD %ZMM7,%ZMM1,%ZMM8 |
0x41b3f3 VBROADCASTSD 0x1c0(%RSP),%ZMM7 |
0x41b3fb VBROADCASTSD %XMM19,%ZMM9 |
0x41b401 VFMADD231PD %ZMM7,%ZMM1,%ZMM9 |
0x41b407 VMULPD %ZMM4,%ZMM8,%ZMM7 |
0x41b40d VFMADD213PD %ZMM7,%ZMM29,%ZMM9 |
0x41b413 VBROADCASTSD 0x1e0(%RSP),%ZMM7 |
0x41b41b VBROADCASTSD 0x1d0(%RSP),%ZMM8 |
0x41b423 VFMADD231PD %ZMM7,%ZMM1,%ZMM8 |
0x41b429 VFMADD213PD %ZMM9,%ZMM15,%ZMM8 |
0x41b42f VBROADCASTSD 0x200(%RSP),%ZMM7 |
0x41b437 VBROADCASTSD 0x1f0(%RSP),%ZMM9 |
0x41b43f VFMADD231PD %ZMM7,%ZMM1,%ZMM9 |
0x41b445 VFMADD213PD %ZMM8,%ZMM0,%ZMM9 |
0x41b44b VBROADCASTSD %XMM22,%ZMM7 |
0x41b451 VMULPD %ZMM9,%ZMM7,%ZMM7 |
0x41b457 VMOVDQU32 (%R13,%RSI,4),%YMM8{%K1}{z} |
0x41b45f VPMOVSXDQ %YMM8,%ZMM8 |
0x41b465 VPADDQ %ZMM8,%ZMM27,%ZMM27{%K1} |
0x41b46b KMOVQ %K1,%K2 |
0x41b470 VSCATTERQPD %ZMM7,(%RDX,%ZMM27,8){%K2} |
0x41b477 VBROADCASTSD 0x220(%RSP),%ZMM7 |
0x41b47f VBROADCASTSD 0x210(%RSP),%ZMM8 |
0x41b487 VFMADD231PD %ZMM7,%ZMM1,%ZMM8 |
0x41b48d VBROADCASTSD 0x230(%RSP),%ZMM7 |
0x41b495 VFMADD213PD %ZMM7,%ZMM1,%ZMM8 |
0x41b49b VBROADCASTSD 0x250(%RSP),%ZMM7 |
0x41b4a3 VBROADCASTSD 0x240(%RSP),%ZMM9 |
0x41b4ab VFMADD231PD %ZMM7,%ZMM1,%ZMM9 |
0x41b4b1 VBROADCASTSD 0x260(%RSP),%ZMM7 |
0x41b4b9 VFMADD213PD %ZMM7,%ZMM1,%ZMM9 |
0x41b4bf VMULPD %ZMM4,%ZMM8,%ZMM7 |
0x41b4c5 VFMADD213PD %ZMM7,%ZMM29,%ZMM9 |
0x41b4cb VBROADCASTSD %XMM3,%ZMM7 |
0x41b4d1 VBROADCASTSD 0x270(%RSP),%ZMM8 |
0x41b4d9 VFMADD231PD %ZMM7,%ZMM1,%ZMM8 |
0x41b4df VBROADCASTSD %XMM5,%ZMM7 |
0x41b4e5 VFMADD213PD %ZMM7,%ZMM1,%ZMM8 |
0x41b4eb VFMADD213PD %ZMM9,%ZMM15,%ZMM8 |
0x41b4f1 VBROADCASTSD %XMM6,%ZMM7 |
0x41b4f7 VBROADCASTSD %XMM26,%ZMM9 |
0x41b4fd VFMADD231PD %ZMM7,%ZMM1,%ZMM9 |
0x41b503 VBROADCASTSD %XMM24,%ZMM7 |
0x41b509 VFMADD213PD %ZMM7,%ZMM1,%ZMM9 |
0x41b50f VFMADD213PD %ZMM8,%ZMM0,%ZMM9 |
0x41b515 VMULPD %ZMM2,%ZMM9,%ZMM5 |
0x41b51b VDIVPD %ZMM21,%ZMM5,%ZMM5 |
0x41b521 KMOVQ %K1,%K2 |
0x41b526 VSCATTERQPD %ZMM5,(%R10,%ZMM27,8){%K2} |
0x41b52d VBROADCASTSD %XMM23,%ZMM5 |
0x41b533 VBROADCASTSD %XMM20,%ZMM6 |
0x41b539 VFMADD231PD %ZMM5,%ZMM1,%ZMM6 |
0x41b53f VBROADCASTSD %XMM17,%ZMM5 |
0x41b545 VFMADD213PD %ZMM5,%ZMM1,%ZMM6 |
0x41b54b VBROADCASTSD %XMM30,%ZMM5 |
0x41b551 VFMADD213PD %ZMM5,%ZMM1,%ZMM6 |
0x41b557 VMULPD %ZMM4,%ZMM6,%ZMM4 |
0x41b55d VBROADCASTSD %XMM10,%ZMM5 |
0x41b563 VBROADCASTSD %XMM11,%ZMM6 |
0x41b569 VFMADD231PD %ZMM5,%ZMM1,%ZMM6 |
0x41b56f VBROADCASTSD %XMM12,%ZMM5 |
0x41b575 VFMADD213PD %ZMM5,%ZMM1,%ZMM6 |
0x41b57b VBROADCASTSD %XMM14,%ZMM5 |
0x41b581 VFMADD213PD %ZMM5,%ZMM1,%ZMM6 |
0x41b587 VFMADD213PD %ZMM4,%ZMM29,%ZMM6 |
0x41b58d VBROADCASTSD %XMM28,%ZMM3 |
0x41b593 VBROADCASTSD %XMM25,%ZMM4 |
0x41b599 VFMADD231PD %ZMM3,%ZMM1,%ZMM4 |
0x41b59f VBROADCASTSD 0x70(%RSP),%ZMM3 |
0x41b5a7 VFMADD213PD %ZMM3,%ZMM1,%ZMM4 |
0x41b5ad VBROADCASTSD %XMM13,%ZMM3 |
0x41b5b3 VFMADD213PD %ZMM3,%ZMM1,%ZMM4 |
0x41b5b9 VFMADD213PD %ZMM6,%ZMM15,%ZMM4 |
0x41b5bf VBROADCASTSD 0x60(%RSP),%ZMM2 |
0x41b5c7 VBROADCASTSD 0x80(%RSP),%ZMM3 |
0x41b5cf VFMADD231PD %ZMM2,%ZMM1,%ZMM3 |
0x41b5d5 VBROADCASTSD 0x90(%RSP),%ZMM2 |
0x41b5dd VFMADD213PD %ZMM2,%ZMM1,%ZMM3 |
0x41b5e3 VBROADCASTSD 0xa0(%RSP),%ZMM2 |
0x41b5eb VFMADD213PD %ZMM2,%ZMM1,%ZMM3 |
0x41b5f1 VFMADD213PD %ZMM4,%ZMM0,%ZMM3 |
0x41b5f7 VSCATTERQPD %ZMM3,(%R9,%ZMM27,8){%K1} |
0x41b5fe LEA -0x28(%RBP),%RSP |
0x41b602 POP %RBX |
0x41b603 POP %R12 |
0x41b605 POP %R13 |
0x41b607 POP %R14 |
0x41b609 POP %R15 |
0x41b60b POP %RBP |
0x41b60c VZEROUPPER |
0x41b60f RET |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►52.11+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:271 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:207 | 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 | |
►30.99+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:271 | exec |
○ | qmcplusplus::WaveFunction::acc[...] | NewTimer.h:249 | 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 | |
►8.45+ | miniqmcreference::OneBodyJastr[...] | OneBodyJastrowRef.h:222 | exec |
○ | miniqmcreference::OneBodyJastr[...] | stl_vector.h:1258 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:207 | 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 | |
►8.45+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:271 | exec |
○ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:409 | exec |
○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:181 | exec |
○ | main.extracted.107 | miniqmc.cpp:375 | 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 / |
Source file and lines | BsplineFunctor.h:275-339 |
Module | exec |
nb instructions | 346 |
nb uops | 441 |
loop length | 2200 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 31 |
used ymm registers | 2 |
used zmm registers | 24 |
nb stack references | 60 |
ADD-SUB / MUL ratio | 0.14 |
micro-operation queue | 110.25 cycles |
front end | 110.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 61.00 | 14.00 | 81.00 | 81.00 | 88.00 | 69.00 | 14.00 | 65.00 |
cycles | 61.00 | 20.50 | 81.00 | 81.00 | 88.00 | 69.00 | 14.00 | 65.00 |
Cycles executing div or sqrt instructions | 16.00 |
FE+BE cycles | 179.39 |
Stall cycles | 90.23 |
ROB full (events) | 49.02 |
LM full (events) | 1.02 |
SB full (events) | 43.96 |
Front-end | 110.25 |
Dispatch | 88.00 |
DIV/SQRT | 16.00 |
Overall L1 | 110.25 |
all | 35% |
load | 100% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 31% |
all | 55% |
load | 36% |
store | 100% |
mul | 85% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 16% |
all | 53% |
load | 38% |
store | 95% |
mul | 85% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 19% |
all | 30% |
load | 83% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 25% |
all | 39% |
load | 21% |
store | 50% |
mul | 87% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 19% |
all | 38% |
load | 23% |
store | 48% |
mul | 87% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 20% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
AND $-0x40,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0x700,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB %EDX,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST %ECX,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 41b5fe | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x28(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD %EDX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD 0x8(%RDI),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $-0x10,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND %RCX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41b2e6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,0x300(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VPBROADCASTD %ESI,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VBROADCASTSD %XMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
MOV %EDX,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R11,0x2c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,0x280(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R8,%R11,8),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM6,%XMM6,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQU64 0x74cc3(%RIP),%ZMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VPXOR %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPTERNLOGD $-0x1,%ZMM5,%ZMM5,%ZMM5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 41ab18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVD %XMM7,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
MOV 0x300(%RSP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RCX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x2c0(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x280(%RSP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 41b2ea | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 41b5fe | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD 0x238(%RDI),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x128(%RDI),%XMM18 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x130(%RDI),%XMM16 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x148(%RDI),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x150(%RDI),%XMM19 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x168(%RDI),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x170(%RDI),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x188(%RDI),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x190(%RDI),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xa0(%RDI),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xa8(%RDI),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xb0(%RDI),%XMM31 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xc0(%RDI),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xc8(%RDI),%XMM29 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xd0(%RDI),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xe0(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x20(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0xe8(%RDI),%XMM17 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xf0(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x30(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x100(%RDI),%XMM26 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x108(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x40(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x110(%RDI),%XMM24 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x18(%RDI),%XMM23 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x20(%RDI),%XMM20 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x28(%RDI),%XMM21 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x30(%RDI),%XMM30 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x38(%RDI),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x40(%RDI),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x48(%RDI),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x50(%RDI),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x58(%RDI),%XMM28 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x60(%RDI),%XMM25 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x218(%RDI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x68(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x70(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVSD 0x70(%RDI),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x78(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x60(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x80(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x80(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x88(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x90(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $-0x8,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD 0x90(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0xa0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMULSD %XMM0,%XMM0,%XMM22 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPBROADCASTQ %R11,%ZMM27 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
AND %RAX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVUPS %XMM17,0x270(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM8,0x260(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM4,0x250(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM29,0x240(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM31,0x230(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM9,0x220(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPS %XMM5,0x210(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPS %XMM2,0x200(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM1,0x1f0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPS %XMM6,0x1e0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM7,0x1d0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM15,0x1c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JE 41b32c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVUPD %XMM13,0x50(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVAPD %XMM22,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM19,%XMM22 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM15,%XMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD %XMM0,0xc0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM0,%ZMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM18,0xe0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM18,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x300(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM16,0xd0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM16,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x2c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM19,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x280(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM22,0xf0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM22,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x680(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM6,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPS %ZMM0,0x640(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM7,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x600(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM2,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPS %ZMM0,0x5c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM1,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x580(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM13,0xb0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM13,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x540(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM9,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x500(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM5,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPS %ZMM0,0x4c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM31,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x480(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM4,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x440(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM29,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x400(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM8,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x3c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD 0x20(%RSP),%ZMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VMOVUPS %ZMM0,0x380(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM17,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPS %ZMM0,0x340(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD 0x30(%RSP),%ZMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VMOVUPD %XMM26,0x100(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM26,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD 0x40(%RSP),%ZMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VMOVUPD %XMM24,0x110(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM24,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM23,0x130(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM23,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM20,0x120(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM20,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM21,0x140(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM21,%ZMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM30,0x150(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM30,%ZMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM10,0x170(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM10,%ZMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM11,0x160(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM11,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM12,0x180(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM12,%ZMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM14,0x190(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM14,%ZMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM28,0x1b0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM28,%ZMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM25,0x1a0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM25,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD 0x70(%RSP),%XMM16 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM16,%ZMM16 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD 0x50(%RSP),%ZMM17 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VMOVUPD 0x60(%RSP),%XMM18 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM18,%ZMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD 0x80(%RSP),%XMM19 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM19,%ZMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD 0x90(%RSP),%XMM20 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM20,%ZMM20 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD 0xa0(%RSP),%XMM21 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM21,%ZMM21 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RDI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVUPD 0x1b0(%RSP),%XMM28 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x1a0(%RSP),%XMM25 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x50(%RSP),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x190(%RSP),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x180(%RSP),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x170(%RSP),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x160(%RSP),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x150(%RSP),%XMM30 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x140(%RSP),%XMM17 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x130(%RSP),%XMM23 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x120(%RSP),%XMM20 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x110(%RSP),%XMM24 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x100(%RSP),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x40(%RSP),%XMM26 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x30(%RSP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x20(%RSP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xf0(%RSP),%XMM19 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xe0(%RSP),%XMM18 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xd0(%RSP),%XMM16 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xc0(%RSP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xb0(%RSP),%XMM22 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 41b5fe | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VPBROADCASTQ %RDI,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
JMP 41b354 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %EDX,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%R11,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 41b30c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPBROADCASTQ %RDI,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM21,%XMM17 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM26,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD 0x40(%RSP),%XMM26 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x30(%RSP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x20(%RSP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VPBROADCASTQ %RSI,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPORQ 0x7445c(%RIP),%ZMM1,%ZMM1 | 1 | 0.50 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPCMPLTUQ %ZMM2,%ZMM1,%K1 | |||||||||||
KORTESTB %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JE 41b5fe | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VBROADCASTSD %XMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VMOVUPD (%R14,%RSI,8),%ZMM21{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMULPD %ZMM2,%ZMM21,%ZMM1 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VCVTTPD2DQ %ZMM1,%YMM7 | 2 | 0.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 7 | 1 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD (%RCX,%YMM7,8),%ZMM4{%K2} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM29,%XMM29,%XMM29 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD 0x8(%RCX,%YMM7,8),%ZMM29{%K2} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KMOVQ %K1,%K2 | 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 0x10(%RCX,%YMM7,8),%ZMM15{%K2} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD 0x18(%RCX,%YMM7,8),%ZMM0{%K2} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
VRNDSCALEPD $0xb,%ZMM1,%ZMM7 | 2 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 8 | 1 |
VSUBPD %ZMM7,%ZMM1,%ZMM1 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM18,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM16,%ZMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x1c0(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD %XMM19,%ZMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMULPD %ZMM4,%ZMM8,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM7,%ZMM29,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x1e0(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x1d0(%RSP),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM9,%ZMM15,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x200(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x1f0(%RSP),%ZMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM8,%ZMM0,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM22,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMULPD %ZMM9,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMOVDQU32 (%R13,%RSI,4),%YMM8{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VPMOVSXDQ %YMM8,%ZMM8 | |||||||||||
VPADDQ %ZMM8,%ZMM27,%ZMM27{%K1} | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM7,(%RDX,%ZMM27,8){%K2} | 27 | 0 | 0 | 4 | 4 | 8 | 1 | 0 | 0 | 15 | 11 |
VBROADCASTSD 0x220(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x210(%RSP),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x230(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x250(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x240(%RSP),%ZMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x260(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMULPD %ZMM4,%ZMM8,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM7,%ZMM29,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM3,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD 0x270(%RSP),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM5,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM9,%ZMM15,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM6,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM26,%ZMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM24,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM8,%ZMM0,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMULPD %ZMM2,%ZMM9,%ZMM5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VDIVPD %ZMM21,%ZMM5,%ZMM5 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 24 | 16 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM5,(%R10,%ZMM27,8){%K2} | 27 | 0 | 0 | 4 | 4 | 8 | 1 | 0 | 0 | 15 | 11 |
VBROADCASTSD %XMM23,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM20,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM17,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM30,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMULPD %ZMM4,%ZMM6,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM10,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM11,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM12,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM14,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM4,%ZMM29,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM28,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM25,%ZMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM3,%ZMM1,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x70(%RSP),%ZMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM3,%ZMM1,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM13,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM3,%ZMM1,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM6,%ZMM15,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x60(%RSP),%ZMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x80(%RSP),%ZMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM2,%ZMM1,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x90(%RSP),%ZMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM2,%ZMM1,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0xa0(%RSP),%ZMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM2,%ZMM1,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM4,%ZMM0,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VSCATTERQPD %ZMM3,(%R9,%ZMM27,8){%K1} | 27 | 0 | 0 | 4 | 4 | 8 | 1 | 0 | 0 | 15 | 11 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
Source file and lines | BsplineFunctor.h:275-339 |
Module | exec |
nb instructions | 346 |
nb uops | 441 |
loop length | 2200 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 31 |
used ymm registers | 2 |
used zmm registers | 24 |
nb stack references | 60 |
ADD-SUB / MUL ratio | 0.14 |
micro-operation queue | 110.25 cycles |
front end | 110.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 61.00 | 14.00 | 81.00 | 81.00 | 88.00 | 69.00 | 14.00 | 65.00 |
cycles | 61.00 | 20.50 | 81.00 | 81.00 | 88.00 | 69.00 | 14.00 | 65.00 |
Cycles executing div or sqrt instructions | 16.00 |
FE+BE cycles | 179.39 |
Stall cycles | 90.23 |
ROB full (events) | 49.02 |
LM full (events) | 1.02 |
SB full (events) | 43.96 |
Front-end | 110.25 |
Dispatch | 88.00 |
DIV/SQRT | 16.00 |
Overall L1 | 110.25 |
all | 35% |
load | 100% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 31% |
all | 55% |
load | 36% |
store | 100% |
mul | 85% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 16% |
all | 53% |
load | 38% |
store | 95% |
mul | 85% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 19% |
all | 30% |
load | 83% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 25% |
all | 39% |
load | 21% |
store | 50% |
mul | 87% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 19% |
all | 38% |
load | 23% |
store | 48% |
mul | 87% |
add-sub | 100% |
fma | 100% |
div/sqrt | 100% |
other | 20% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
AND $-0x40,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0x700,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB %EDX,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST %ECX,%ECX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 41b5fe | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x28(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD %EDX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD 0x8(%RDI),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $-0x10,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND %RCX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41b2e6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,0x300(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VPBROADCASTD %ESI,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VBROADCASTSD %XMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
MOV %EDX,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R11,0x2c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,0x280(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R8,%R11,8),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM6,%XMM6,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVDQU64 0x74cc3(%RIP),%ZMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VPXOR %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPTERNLOGD $-0x1,%ZMM5,%ZMM5,%ZMM5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 41ab18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVD %XMM7,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
MOV 0x300(%RSP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RCX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x2c0(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x280(%RSP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 41b2ea | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 41b5fe | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD 0x238(%RDI),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x128(%RDI),%XMM18 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x130(%RDI),%XMM16 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x148(%RDI),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x150(%RDI),%XMM19 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x168(%RDI),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x170(%RDI),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x188(%RDI),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x190(%RDI),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xa0(%RDI),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xa8(%RDI),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xb0(%RDI),%XMM31 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xc0(%RDI),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xc8(%RDI),%XMM29 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xd0(%RDI),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xe0(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x20(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0xe8(%RDI),%XMM17 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0xf0(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x30(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x100(%RDI),%XMM26 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x108(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x40(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x110(%RDI),%XMM24 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x18(%RDI),%XMM23 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x20(%RDI),%XMM20 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x28(%RDI),%XMM21 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x30(%RDI),%XMM30 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x38(%RDI),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x40(%RDI),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x48(%RDI),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x50(%RDI),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x58(%RDI),%XMM28 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x60(%RDI),%XMM25 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x218(%RDI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x68(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x70(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVSD 0x70(%RDI),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x78(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x60(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x80(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x80(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x88(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0x90(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $-0x8,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD 0x90(%RDI),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM3,0xa0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMULSD %XMM0,%XMM0,%XMM22 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPBROADCASTQ %R11,%ZMM27 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
AND %RAX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVUPS %XMM17,0x270(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM8,0x260(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM4,0x250(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM29,0x240(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM31,0x230(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM9,0x220(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPS %XMM5,0x210(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPS %XMM2,0x200(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM1,0x1f0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPS %XMM6,0x1e0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM7,0x1d0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM15,0x1c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JE 41b32c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVUPD %XMM13,0x50(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVAPD %XMM22,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM19,%XMM22 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM15,%XMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD %XMM0,0xc0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM0,%ZMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM18,0xe0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM18,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x300(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM16,0xd0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM16,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x2c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM19,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x280(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM22,0xf0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM22,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x680(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM6,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPS %ZMM0,0x640(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM7,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x600(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM2,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPS %ZMM0,0x5c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM1,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x580(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM13,0xb0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM13,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x540(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM9,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x500(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM5,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPS %ZMM0,0x4c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM31,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x480(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM4,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x440(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM29,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x400(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM8,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %ZMM0,0x3c0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD 0x20(%RSP),%ZMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VMOVUPS %ZMM0,0x380(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM17,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPS %ZMM0,0x340(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD 0x30(%RSP),%ZMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VMOVUPD %XMM26,0x100(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM26,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD 0x40(%RSP),%ZMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VMOVUPD %XMM24,0x110(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM24,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM23,0x130(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM23,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM20,0x120(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM20,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM21,0x140(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM21,%ZMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM30,0x150(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM30,%ZMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM10,0x170(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM10,%ZMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM11,0x160(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM11,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM12,0x180(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM12,%ZMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM14,0x190(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM14,%ZMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM28,0x1b0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM28,%ZMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD %XMM25,0x1a0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VBROADCASTSD %XMM25,%ZMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD 0x70(%RSP),%XMM16 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM16,%ZMM16 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD 0x50(%RSP),%ZMM17 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VMOVUPD 0x60(%RSP),%XMM18 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM18,%ZMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD 0x80(%RSP),%XMM19 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM19,%ZMM19 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD 0x90(%RSP),%XMM20 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM20,%ZMM20 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMOVUPD 0xa0(%RSP),%XMM21 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM21,%ZMM21 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RDI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVUPD 0x1b0(%RSP),%XMM28 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x1a0(%RSP),%XMM25 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x50(%RSP),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x190(%RSP),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x180(%RSP),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x170(%RSP),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x160(%RSP),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x150(%RSP),%XMM30 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x140(%RSP),%XMM17 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x130(%RSP),%XMM23 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x120(%RSP),%XMM20 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x110(%RSP),%XMM24 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x100(%RSP),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x40(%RSP),%XMM26 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x30(%RSP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x20(%RSP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xf0(%RSP),%XMM19 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xe0(%RSP),%XMM18 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xd0(%RSP),%XMM16 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xc0(%RSP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0xb0(%RSP),%XMM22 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 41b5fe | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VPBROADCASTQ %RDI,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
JMP 41b354 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %EDX,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%R11,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 41b30c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPBROADCASTQ %RDI,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM21,%XMM17 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVAPD %XMM26,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD 0x40(%RSP),%XMM26 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x30(%RSP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD 0x20(%RSP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VPBROADCASTQ %RSI,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPORQ 0x7445c(%RIP),%ZMM1,%ZMM1 | 1 | 0.50 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPCMPLTUQ %ZMM2,%ZMM1,%K1 | |||||||||||
KORTESTB %K1,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JE 41b5fe | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VBROADCASTSD %XMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VMOVUPD (%R14,%RSI,8),%ZMM21{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMULPD %ZMM2,%ZMM21,%ZMM1 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VCVTTPD2DQ %ZMM1,%YMM7 | 2 | 0.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 7 | 1 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD (%RCX,%YMM7,8),%ZMM4{%K2} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM29,%XMM29,%XMM29 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD 0x8(%RCX,%YMM7,8),%ZMM29{%K2} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KMOVQ %K1,%K2 | 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 0x10(%RCX,%YMM7,8),%ZMM15{%K2} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VGATHERDPD 0x18(%RCX,%YMM7,8),%ZMM0{%K2} | 4 | 1 | 0 | 4 | 4 | 0 | 1 | 0 | 0 | 21 | 5 |
VRNDSCALEPD $0xb,%ZMM1,%ZMM7 | 2 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 8 | 1 |
VSUBPD %ZMM7,%ZMM1,%ZMM1 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM18,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM16,%ZMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x1c0(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD %XMM19,%ZMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMULPD %ZMM4,%ZMM8,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM7,%ZMM29,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x1e0(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x1d0(%RSP),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM9,%ZMM15,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x200(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x1f0(%RSP),%ZMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM8,%ZMM0,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM22,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VMULPD %ZMM9,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMOVDQU32 (%R13,%RSI,4),%YMM8{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VPMOVSXDQ %YMM8,%ZMM8 | |||||||||||
VPADDQ %ZMM8,%ZMM27,%ZMM27{%K1} | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM7,(%RDX,%ZMM27,8){%K2} | 27 | 0 | 0 | 4 | 4 | 8 | 1 | 0 | 0 | 15 | 11 |
VBROADCASTSD 0x220(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x210(%RSP),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x230(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x250(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x240(%RSP),%ZMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x260(%RSP),%ZMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMULPD %ZMM4,%ZMM8,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM7,%ZMM29,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM3,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD 0x270(%RSP),%ZMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM5,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM7,%ZMM1,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM9,%ZMM15,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM6,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM26,%ZMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM24,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM7,%ZMM1,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM8,%ZMM0,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMULPD %ZMM2,%ZMM9,%ZMM5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VDIVPD %ZMM21,%ZMM5,%ZMM5 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 24 | 16 |
KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VSCATTERQPD %ZMM5,(%R10,%ZMM27,8){%K2} | 27 | 0 | 0 | 4 | 4 | 8 | 1 | 0 | 0 | 15 | 11 |
VBROADCASTSD %XMM23,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM20,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM17,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM30,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VMULPD %ZMM4,%ZMM6,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM10,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM11,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM12,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM14,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM5,%ZMM1,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM4,%ZMM29,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM28,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VBROADCASTSD %XMM25,%ZMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD231PD %ZMM3,%ZMM1,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x70(%RSP),%ZMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM3,%ZMM1,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD %XMM13,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VFMADD213PD %ZMM3,%ZMM1,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM6,%ZMM15,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x60(%RSP),%ZMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VBROADCASTSD 0x80(%RSP),%ZMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD231PD %ZMM2,%ZMM1,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0x90(%RSP),%ZMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM2,%ZMM1,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VBROADCASTSD 0xa0(%RSP),%ZMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5 | 0.50 |
VFMADD213PD %ZMM2,%ZMM1,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VFMADD213PD %ZMM4,%ZMM0,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
VSCATTERQPD %ZMM3,(%R9,%ZMM27,8){%K1} | 27 | 0 | 0 | 4 | 4 | 8 | 1 | 0 | 0 | 15 | 11 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼qmcplusplus::BsplineFunctor | 0.59 | 0.35 |
○Loop 227 - BsplineFunctor.h:291-298 - exec | 0.43 | 0.25 |
○Loop 225 - BsplineFunctor.h:302-335 - exec | 0.14 | 0.09 |
○Loop 226 - BsplineFunctor.h:291-298 - exec | 0 | 0 |