Loop Id: 597 | Module: libkripke.so | Source: RangeSegment.hpp:120-120 [...] | Coverage: 0.02% |
---|
Loop Id: 597 | Module: libkripke.so | Source: RangeSegment.hpp:120-120 [...] | Coverage: 0.02% |
---|
0x60c4e MOV 0x38(%RSP),%RCX |
0x60c53 MOV 0x30(%RSP),%R11 |
0x60c58 MOV %R10,0x10(%RSP) |
0x60c5d MOV 0x60(%RSP),%R14 |
0x60c62 MOV 0x48(%RSP),%R8 |
0x60c67 MOV %RBX,0x8(%RSP) |
0x60c6c IMUL %R12,%RCX |
0x60c70 MOV 0x28(%RSP),%RSI |
0x60c75 MOV %R12,(%RSP) |
0x60c79 LEA (%R10,%R14,1),%RDI |
0x60c7d MOV 0x80(%RSP),%R14 |
0x60c85 MOV 0x98(%RSP),%RDX |
0x60c8d MOV %R9,0xc8(%RSP) |
0x60c95 ADD %RDI,%RSI |
0x60c98 ADD %R11,%RCX |
0x60c9b IMUL %RSI,%R14 |
0x60c9f MOV 0x58(%RSP),%R11 |
0x60ca4 MOV 0x88(%RSP),%RSI |
0x60cac ADD %RBX,%RCX |
0x60caf LEA (%R8,%RCX,8),%RAX |
0x60cb3 MOV 0x68(%RSP),%RCX |
0x60cb8 MOV %RAX,0x110(%RSP) |
0x60cc0 MOV 0x20(%RSP),%RAX |
0x60cc5 IMUL (%R11,%R12,8),%RCX |
0x60cca MOV 0x78(%RSP),%R11 |
0x60ccf ADD %RDX,%RAX |
0x60cd2 LEA (%RAX,%RSI,1),%R8 |
0x60cd6 MOV 0x70(%RSP),%RSI |
0x60cdb LEA (%R14,%RAX,1),%RDX |
0x60cdf IMUL %R11,%RDI |
0x60ce3 LEA (%R14,%RCX,1),%R14 |
0x60ce7 MOV %R8,0xc0(%RSP) |
0x60cef IMUL %R12,%RSI |
0x60cf3 MOV %RCX,0xb8(%RSP) |
0x60cfb MOV %R14,0xb0(%RSP) |
0x60d03 ADD %RDI,%RSI |
0x60d06 MOV 0x50(%RSP),%RDI |
0x60d0b ADD %RBX,%RSI |
0x60d0e LEA (%RDI,%RSI,8),%RSI |
0x60d12 MOV %RSI,0x100(%RSP) |
0x60d1a NOPW (%RAX,%RAX,1) |
(596) 0x60d20 MOV 0xb8(%RSP),%RBX |
(596) 0x60d28 MOV 0xe8(%RSP),%R9 |
(596) 0x60d30 MOV %RDX,0xd8(%RSP) |
(596) 0x60d38 XOR %ESI,%ESI |
(596) 0x60d3a MOV 0xb0(%RSP),%R8 |
(596) 0x60d42 MOV %RAX,0xd0(%RSP) |
(596) 0x60d4a LEA (%RDX,%RBX,1),%R10 |
(596) 0x60d4e LEA (%R9,%R10,8),%R12 |
(596) 0x60d52 LEA (%R8,%RAX,1),%R14 |
(596) 0x60d56 MOV %R12,0x118(%RSP) |
(596) 0x60d5e XCHG %AX,%AX |
(595) 0x60d60 MOV 0xf0(%RSP),%RAX |
(595) 0x60d68 MOV 0xf8(%RSP),%RCX |
(595) 0x60d70 MOV (%RAX,%RSI,8),%RDX |
(595) 0x60d74 MOVSXD (%RCX,%RSI,4),%R9 |
(595) 0x60d78 LEA (%R9,%RDX,1),%RBX |
(595) 0x60d7c MOV %R9,%R12 |
(595) 0x60d7f CMP %RBX,%RDX |
(595) 0x60d82 JGE 61100 |
(595) 0x60d88 LEA -0x1(%R9),%R11 |
(595) 0x60d8c CMP $0x2,%R11 |
(595) 0x60d90 JBE 61109 |
(595) 0x60d96 MOV %R9,%R11 |
(595) 0x60d99 LEA (,%RDX,8),%RCX |
(595) 0x60da1 XOR %EAX,%EAX |
(595) 0x60da3 XOR %EDI,%EDI |
(595) 0x60da5 SHR $0x2,%R11 |
(595) 0x60da9 LEA (%R15,%RCX,1),%R8 |
(595) 0x60dad VXORPD %XMM0,%XMM0,%XMM0 |
(595) 0x60db1 ADD %R13,%RCX |
(595) 0x60db4 MOV %R11,%R10 |
(595) 0x60db7 AND $0x3,%R10D |
(595) 0x60dbb JE 610f0 |
(595) 0x60dc1 CMP $0x1,%R10 |
(595) 0x60dc5 JE 60e5e |
(595) 0x60dcb CMP $0x2,%R10 |
(595) 0x60dcf JE 60e18 |
(595) 0x60dd1 VMOVDQU (%R8),%YMM5 |
(595) 0x60dd6 VMOVAPD %YMM2,%YMM12 |
(595) 0x60dda MOV $0x20,%EAX |
(595) 0x60ddf MOV 0x118(%RSP),%RDI |
(595) 0x60de7 VPSRLQ $0x20,%YMM5,%YMM4 |
(595) 0x60dec VPMULUDQ %YMM5,%YMM3,%YMM8 |
(595) 0x60df0 VPMULUDQ %YMM1,%YMM4,%YMM7 |
(595) 0x60df4 VPMULUDQ %YMM1,%YMM5,%YMM6 |
(595) 0x60df8 VPADDQ %YMM8,%YMM7,%YMM9 |
(595) 0x60dfd VPSLLQ $0x20,%YMM9,%YMM10 |
(595) 0x60e03 VPADDQ %YMM10,%YMM6,%YMM11 |
(595) 0x60e08 VGATHERQPD %YMM12,(%RDI,%YMM11,8),%YMM13 |
(595) 0x60e0e VFMADD231PD (%RCX),%YMM13,%YMM0 |
(595) 0x60e13 MOV $0x1,%EDI |
(595) 0x60e18 VMOVDQU (%R8,%RAX,1),%YMM14 |
(595) 0x60e1e MOV 0x118(%RSP),%R10 |
(595) 0x60e26 VMOVAPD %YMM2,%YMM10 |
(595) 0x60e2a INC %RDI |
(595) 0x60e2d VPSRLQ $0x20,%YMM14,%YMM5 |
(595) 0x60e33 VPMULUDQ %YMM14,%YMM3,%YMM4 |
(595) 0x60e38 VPMULUDQ %YMM1,%YMM5,%YMM6 |
(595) 0x60e3c VPMULUDQ %YMM1,%YMM14,%YMM15 |
(595) 0x60e40 VPADDQ %YMM4,%YMM6,%YMM7 |
(595) 0x60e44 VPSLLQ $0x20,%YMM7,%YMM8 |
(595) 0x60e49 VPADDQ %YMM8,%YMM15,%YMM9 |
(595) 0x60e4e VGATHERQPD %YMM10,(%R10,%YMM9,8),%YMM11 |
(595) 0x60e54 VFMADD231PD (%RCX,%RAX,1),%YMM11,%YMM0 |
(595) 0x60e5a ADD $0x20,%RAX |
(595) 0x60e5e VMOVDQU (%R8,%RAX,1),%YMM12 |
(595) 0x60e64 MOV 0x118(%RSP),%R10 |
(595) 0x60e6c VMOVAPD %YMM2,%YMM8 |
(595) 0x60e70 INC %RDI |
(595) 0x60e73 VPSRLQ $0x20,%YMM12,%YMM14 |
(595) 0x60e79 VPMULUDQ %YMM12,%YMM3,%YMM5 |
(595) 0x60e7e VPMULUDQ %YMM1,%YMM14,%YMM15 |
(595) 0x60e82 VPMULUDQ %YMM1,%YMM12,%YMM13 |
(595) 0x60e86 VPADDQ %YMM5,%YMM15,%YMM6 |
(595) 0x60e8a VPSLLQ $0x20,%YMM6,%YMM4 |
(595) 0x60e8f VPADDQ %YMM4,%YMM13,%YMM7 |
(595) 0x60e93 VGATHERQPD %YMM8,(%R10,%YMM7,8),%YMM9 |
(595) 0x60e99 VFMADD231PD (%RCX,%RAX,1),%YMM9,%YMM0 |
(595) 0x60e9f ADD $0x20,%RAX |
(595) 0x60ea3 CMP %R11,%RDI |
(595) 0x60ea6 JE 60faa |
(598) 0x60eac VMOVDQU (%R8,%RAX,1),%YMM10 |
(598) 0x60eb2 VMOVDQU 0x20(%R8,%RAX,1),%YMM8 |
(598) 0x60eb9 VMOVAPD %YMM2,%YMM7 |
(598) 0x60ebd ADD $0x4,%RDI |
(598) 0x60ec1 VPSRLQ $0x20,%YMM10,%YMM12 |
(598) 0x60ec7 VPMULUDQ %YMM10,%YMM3,%YMM14 |
(598) 0x60ecc VPMULUDQ %YMM1,%YMM12,%YMM13 |
(598) 0x60ed0 VPMULUDQ %YMM1,%YMM10,%YMM11 |
(598) 0x60ed4 VPSRLQ $0x20,%YMM8,%YMM10 |
(598) 0x60eda VPMULUDQ %YMM8,%YMM3,%YMM12 |
(598) 0x60edf VPMULUDQ %YMM1,%YMM8,%YMM9 |
(598) 0x60ee3 VPADDQ %YMM14,%YMM13,%YMM15 |
(598) 0x60ee8 VPSLLQ $0x20,%YMM15,%YMM5 |
(598) 0x60eee VPADDQ %YMM5,%YMM11,%YMM6 |
(598) 0x60ef2 VPMULUDQ %YMM1,%YMM10,%YMM11 |
(598) 0x60ef6 VMOVAPD %YMM2,%YMM5 |
(598) 0x60efa VGATHERQPD %YMM7,(%R10,%YMM6,8),%YMM4 |
(598) 0x60f00 VFMADD231PD (%RCX,%RAX,1),%YMM4,%YMM0 |
(598) 0x60f06 VMOVDQU 0x40(%R8,%RAX,1),%YMM7 |
(598) 0x60f0d VPMULUDQ %YMM7,%YMM3,%YMM4 |
(598) 0x60f11 VPMULUDQ %YMM1,%YMM7,%YMM8 |
(598) 0x60f15 VPADDQ %YMM12,%YMM11,%YMM13 |
(598) 0x60f1a VPSLLQ $0x20,%YMM13,%YMM14 |
(598) 0x60f20 VMOVAPD %YMM2,%YMM13 |
(598) 0x60f24 VPADDQ %YMM14,%YMM9,%YMM15 |
(598) 0x60f29 VGATHERQPD %YMM5,(%R10,%YMM15,8),%YMM6 |
(598) 0x60f2f VFMADD132PD 0x20(%RCX,%RAX,1),%YMM0,%YMM6 |
(598) 0x60f36 VMOVDQU 0x60(%R8,%RAX,1),%YMM15 |
(598) 0x60f3d VPSRLQ $0x20,%YMM7,%YMM0 |
(598) 0x60f42 VPMULUDQ %YMM1,%YMM0,%YMM9 |
(598) 0x60f46 VPMULUDQ %YMM1,%YMM15,%YMM5 |
(598) 0x60f4a VPADDQ %YMM4,%YMM9,%YMM10 |
(598) 0x60f4e VPSLLQ $0x20,%YMM10,%YMM11 |
(598) 0x60f54 VMOVAPD %YMM2,%YMM10 |
(598) 0x60f58 VPADDQ %YMM11,%YMM8,%YMM12 |
(598) 0x60f5d VPMULUDQ %YMM15,%YMM3,%YMM8 |
(598) 0x60f62 VGATHERQPD %YMM13,(%R10,%YMM12,8),%YMM14 |
(598) 0x60f68 VFMADD132PD 0x40(%RCX,%RAX,1),%YMM6,%YMM14 |
(598) 0x60f6f VPSRLQ $0x20,%YMM15,%YMM6 |
(598) 0x60f75 VPMULUDQ %YMM1,%YMM6,%YMM7 |
(598) 0x60f79 VPADDQ %YMM8,%YMM7,%YMM0 |
(598) 0x60f7e VPSLLQ $0x20,%YMM0,%YMM9 |
(598) 0x60f83 VPADDQ %YMM9,%YMM5,%YMM4 |
(598) 0x60f88 VGATHERQPD %YMM10,(%R10,%YMM4,8),%YMM0 |
(598) 0x60f8e VFMADD132PD 0x60(%RCX,%RAX,1),%YMM14,%YMM0 |
(598) 0x60f95 SUB $-0x80,%RAX |
(598) 0x60f99 CMP %R11,%RDI |
(598) 0x60f9c JNE 60eac |
(595) 0x60fa2 MOV %R10,0x118(%RSP) |
(595) 0x60faa VEXTRACTF128 $0x1,%YMM0,%XMM11 |
(595) 0x60fb0 AND $0x3,%R12D |
(595) 0x60fb4 VADDPD %XMM0,%XMM11,%XMM12 |
(595) 0x60fb8 VUNPCKHPD %XMM12,%XMM12,%XMM13 |
(595) 0x60fbd VADDPD %XMM12,%XMM13,%XMM0 |
(595) 0x60fc2 JE 6103f |
(595) 0x60fc4 AND $-0x4,%R9 |
(595) 0x60fc8 ADD %R9,%RDX |
(595) 0x60fcb MOV 0xe0(%RSP),%R12 |
(595) 0x60fd3 MOV (%R15,%RDX,8),%RCX |
(595) 0x60fd7 LEA 0x1(%RDX),%R8 |
(595) 0x60fdb LEA (,%RDX,8),%R9 |
(595) 0x60fe3 MOV 0xe8(%RSP),%R11 |
(595) 0x60feb VMOVSD (%R13,%RDX,8),%XMM14 |
(595) 0x60ff2 IMUL %R12,%RCX |
(595) 0x60ff6 ADD %R14,%RCX |
(595) 0x60ff9 VFMADD231SD (%R11,%RCX,8),%XMM14,%XMM0 |
(595) 0x60fff CMP %R8,%RBX |
(595) 0x61002 JLE 6103f |
(595) 0x61004 MOV 0x8(%R15,%R9,1),%RDI |
(595) 0x61009 ADD $0x2,%RDX |
(595) 0x6100d IMUL %R12,%RDI |
(595) 0x61011 ADD %R14,%RDI |
(595) 0x61014 VMOVSD (%R11,%RDI,8),%XMM15 |
(595) 0x6101a VFMADD231SD 0x8(%R13,%R9,1),%XMM15,%XMM0 |
(595) 0x61021 CMP %RDX,%RBX |
(595) 0x61024 JLE 6103f |
(595) 0x61026 IMUL 0x10(%R15,%R9,1),%R12 |
(595) 0x6102c MOV %R12,%RDI |
(595) 0x6102f ADD %R14,%RDI |
(595) 0x61032 VMOVSD (%R11,%RDI,8),%XMM5 |
(595) 0x61038 VFMADD231SD 0x10(%R13,%R9,1),%XMM5,%XMM0 |
(595) 0x6103f MOV 0x100(%RSP),%RBX |
(595) 0x61047 MOV 0x110(%RSP),%RDX |
(595) 0x6104f MOV 0x108(%RSP),%RAX |
(595) 0x61057 VMOVSD (%RBX,%RSI,8),%XMM6 |
(595) 0x6105c VFMADD132SD (%RDX,%RSI,8),%XMM6,%XMM0 |
(595) 0x61062 VMOVSD %XMM0,(%RBX,%RSI,8) |
(595) 0x61067 INC %RSI |
(595) 0x6106a CMP %RAX,%RSI |
(595) 0x6106d JNE 60d60 |
(596) 0x61073 MOV 0xd8(%RSP),%RDX |
(596) 0x6107b MOV 0xd0(%RSP),%RAX |
(596) 0x61083 MOV 0xc8(%RSP),%RSI |
(596) 0x6108b ADD %RSI,0x110(%RSP) |
(596) 0x61093 INC %RAX |
(596) 0x61096 INC %RDX |
(596) 0x61099 CMP %RAX,0xc0(%RSP) |
(596) 0x610a1 JNE 60d20 |
0x610a7 MOV 0x10(%RSP),%R10 |
0x610ac MOV 0x8(%RSP),%RBX |
0x610b1 MOV %RSI,%R9 |
0x610b4 MOV (%RSP),%R12 |
0x610b8 MOV 0x90(%RSP),%R14 |
0x610c0 CMP %R14,0x40(%RSP) |
0x610c5 JE 610de |
0x610c7 INC %R10 |
0x610ca CMP %R10,0x18(%RSP) |
0x610cf JLE 6111c |
0x610d1 INCQ 0x90(%RSP) |
0x610d9 JMP 60c4e |
(595) 0x610f0 MOV 0x118(%RSP),%R10 |
(595) 0x610f8 JMP 60eac |
(595) 0x61100 VXORPD %XMM0,%XMM0,%XMM0 |
(595) 0x61104 JMP 6103f |
(595) 0x61109 VXORPD %XMM0,%XMM0,%XMM0 |
(595) 0x6110d JMP 60fcb |
0x6111c INCQ 0xa8(%RSP) |
0x61124 MOV 0xa0(%RSP),%RCX |
0x6112c XOR %R10D,%R10D |
0x6112f MOV 0xa8(%RSP),%R12 |
0x61137 LEA (%R12,%RCX,1),%R12 |
0x6113b JMP 610d1 |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/RangeSegment.hpp: 120 - 120 |
-------------------------------------------------------------------------------- |
120: RAJA_HOST_DEVICE RAJA_INLINE ~TypedRangeSegment() {} |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp: 55 - 55 |
-------------------------------------------------------------------------------- |
55: return a * b; |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/loop/forall.hpp: 59 - 59 |
-------------------------------------------------------------------------------- |
59: for (decltype(distance_it) i = 0; i < distance_it; ++i) { |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp: 177 - 177 |
-------------------------------------------------------------------------------- |
177: return value_type(val + rhs); |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/src/Kripke/Kernel/Scattering.cpp: 84 - 97 |
-------------------------------------------------------------------------------- |
84: GlobalGroup global_g{*g+glower_dst}; |
85: GlobalGroup global_gp{*gp+glower_src}; |
86: |
87: MixElem mix_start = zone_to_mixelem(z); |
88: MixElem mix_stop = mix_start + zone_to_num_mixelem(z); |
89: |
90: double sigs_z = 0.0; |
91: for(MixElem mix = mix_start;mix < mix_stop;++ mix){ |
92: Material mat = mixelem_to_material(mix); |
93: double fraction = mixelem_to_fraction(mix); |
94: |
95: sigs_z += sigs(mat, n, global_g, global_gp) * fraction; |
96: } |
97: phi_out(nm, g, z) += sigs_z * phi(nm, gp, z); |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 307 - 307 |
-------------------------------------------------------------------------------- |
307: return Ret{lhs} + rhs; |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/IndexValue.hpp: 83 - 105 |
-------------------------------------------------------------------------------- |
83: value++; |
[...] |
105: return TYPE(value + a); |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp: 81 - 81 |
-------------------------------------------------------------------------------- |
81: #pragma omp parallel for private(i0, i1) firstprivate(privatizer) \ |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/View.hpp: 110 - 110 |
-------------------------------------------------------------------------------- |
110: return data[idx]; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
○100.00 | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.26 |
Bottlenecks | micro-operation queue, |
Function | void RAJA::internal::StatementExecutor |
Source | RangeSegment.hpp:120-120,Layout.hpp:55-55,forall.hpp:59-59,Iterators.hpp:177-177,Scattering.cpp:84-97,Operators.hpp:307-307,IndexValue.hpp:83-105,Collapse.hpp:81-81,View.hpp:110-110 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 15.75 |
CQA cycles if no scalar integer | 15.75 |
CQA cycles if FP arith vectorized | 15.75 |
CQA cycles if fully vectorized | 1.97 |
Front-end cycles | 15.75 |
DIV/SQRT cycles | 6.75 |
P0 cycles | 11.25 |
P1 cycles | 12.50 |
P2 cycles | 12.50 |
P3 cycles | 11.00 |
P4 cycles | 6.75 |
P5 cycles | 6.75 |
P6 cycles | 11.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 15.42 |
Stall cycles (UFS) | 0.00 |
Nb insns | 59.00 |
Nb uops | 63.00 |
Nb loads | 25.00 |
Nb stores | 11.00 |
Nb stack references | 28.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 18.29 |
Bytes prefetched | 0.00 |
Bytes loaded | 200.00 |
Bytes stored | 88.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.26 |
Bottlenecks | micro-operation queue, |
Function | void RAJA::internal::StatementExecutor |
Source | RangeSegment.hpp:120-120,Layout.hpp:55-55,forall.hpp:59-59,Iterators.hpp:177-177,Scattering.cpp:84-97,Operators.hpp:307-307,IndexValue.hpp:83-105,Collapse.hpp:81-81,View.hpp:110-110 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 15.75 |
CQA cycles if no scalar integer | 15.75 |
CQA cycles if FP arith vectorized | 15.75 |
CQA cycles if fully vectorized | 1.97 |
Front-end cycles | 15.75 |
DIV/SQRT cycles | 6.75 |
P0 cycles | 11.25 |
P1 cycles | 12.50 |
P2 cycles | 12.50 |
P3 cycles | 11.00 |
P4 cycles | 6.75 |
P5 cycles | 6.75 |
P6 cycles | 11.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 15.42 |
Stall cycles (UFS) | 0.00 |
Nb insns | 59.00 |
Nb uops | 63.00 |
Nb loads | 25.00 |
Nb stores | 11.00 |
Nb stack references | 28.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 18.29 |
Bytes prefetched | 0.00 |
Bytes loaded | 200.00 |
Bytes stored | 88.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Path / |
nb instructions | 59 |
nb uops | 63 |
loop length | 298 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 28 |
micro-operation queue | 15.75 cycles |
front end | 15.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 6.75 | 6.75 | 12.50 | 12.50 | 11.00 | 6.75 | 6.75 | 11.00 |
cycles | 6.75 | 11.25 | 12.50 | 12.50 | 11.00 | 6.75 | 6.75 | 11.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 15.42 |
Stall cycles | 0.00 |
Front-end | 15.75 |
Dispatch | 12.50 |
Overall L1 | 15.75 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x38(%RSP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x30(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,0x10(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x60(%RSP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x48(%RSP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,0x8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
IMUL %R12,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x28(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R10,%R14,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x80(%RSP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x98(%RSP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,0xc8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD %RDI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R11,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
IMUL %RSI,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x58(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x88(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RBX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%RCX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x68(%RSP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,0x110(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x20(%RSP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL (%R11,%R12,8),%RCX | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x78(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RAX,%RSI,1),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x70(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R14,%RAX,1),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
IMUL %R11,%RDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%R14,%RCX,1),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R8,0xc0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
IMUL %R12,%RSI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %RCX,0xb8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,0xb0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD %RDI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x50(%RSP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RBX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RDI,%RSI,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RSI,0x100(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x10(%RSP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RSP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RSP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x90(%RSP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R14,0x40(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 610de <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_5GroupElPSW_EESW_EESZ_NSO_INSQ_INSR_4ZoneElPS10_EES10_EEEEENSM_IJEEEJZNK14ScatteringSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdES1D_RKNSR_4Core3SetES1H_S1H_RNS1E_5FieldIdJSS_SW_S10_EEES1K_RNS1I_IdJNSR_8MaterialENSR_8LegendreENSR_11GlobalGroupES1N_EEERNS1I_INSR_7MixElemEJS10_EEERNS1I_IiJS10_EEERNS1I_IS1L_JS1Q_EEERNS1I_IdJS1Q_EEERNS1I_IS1M_JSS_EEEEUlSS_SW_SW_S10_E_EEEEEvOS1C_._omp_fn.0+0x6fe> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R10,0x18(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 6111c <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_5GroupElPSW_EESW_EESZ_NSO_INSQ_INSR_4ZoneElPS10_EES10_EEEEENSM_IJEEEJZNK14ScatteringSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdES1D_RKNSR_4Core3SetES1H_S1H_RNS1E_5FieldIdJSS_SW_S10_EEES1K_RNS1I_IdJNSR_8MaterialENSR_8LegendreENSR_11GlobalGroupES1N_EEERNS1I_INSR_7MixElemEJS10_EEERNS1I_IiJS10_EEERNS1I_IS1L_JS1Q_EEERNS1I_IdJS1Q_EEERNS1I_IS1M_JSS_EEEEUlSS_SW_SW_S10_E_EEEEEvOS1C_._omp_fn.0+0x73c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INCQ 0x90(%RSP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
JMP 60c4e <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_5GroupElPSW_EESW_EESZ_NSO_INSQ_INSR_4ZoneElPS10_EES10_EEEEENSM_IJEEEJZNK14ScatteringSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdES1D_RKNSR_4Core3SetES1H_S1H_RNS1E_5FieldIdJSS_SW_S10_EEES1K_RNS1I_IdJNSR_8MaterialENSR_8LegendreENSR_11GlobalGroupES1N_EEERNS1I_INSR_7MixElemEJS10_EEERNS1I_IiJS10_EEERNS1I_IS1L_JS1Q_EEERNS1I_IdJS1Q_EEERNS1I_IS1M_JSS_EEEEUlSS_SW_SW_S10_E_EEEEEvOS1C_._omp_fn.0+0x26e> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
INCQ 0xa8(%RSP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
MOV 0xa0(%RSP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xa8(%RSP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R12,%RCX,1),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 610d1 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_5GroupElPSW_EESW_EESZ_NSO_INSQ_INSR_4ZoneElPS10_EES10_EEEEENSM_IJEEEJZNK14ScatteringSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdES1D_RKNSR_4Core3SetES1H_S1H_RNS1E_5FieldIdJSS_SW_S10_EEES1K_RNS1I_IdJNSR_8MaterialENSR_8LegendreENSR_11GlobalGroupES1N_EEERNS1I_INSR_7MixElemEJS10_EEERNS1I_IiJS10_EEERNS1I_IS1L_JS1Q_EEERNS1I_IdJS1Q_EEERNS1I_IS1M_JSS_EEEEUlSS_SW_SW_S10_E_EEEEEvOS1C_._omp_fn.0+0x6f1> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
nb instructions | 59 |
nb uops | 63 |
loop length | 298 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 28 |
micro-operation queue | 15.75 cycles |
front end | 15.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 6.75 | 6.75 | 12.50 | 12.50 | 11.00 | 6.75 | 6.75 | 11.00 |
cycles | 6.75 | 11.25 | 12.50 | 12.50 | 11.00 | 6.75 | 6.75 | 11.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 15.42 |
Stall cycles | 0.00 |
Front-end | 15.75 |
Dispatch | 12.50 |
Overall L1 | 15.75 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x38(%RSP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x30(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,0x10(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x60(%RSP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x48(%RSP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,0x8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
IMUL %R12,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x28(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R10,%R14,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x80(%RSP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x98(%RSP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,0xc8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD %RDI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R11,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
IMUL %RSI,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x58(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x88(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RBX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%RCX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x68(%RSP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,0x110(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x20(%RSP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL (%R11,%R12,8),%RCX | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x78(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RAX,%RSI,1),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x70(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R14,%RAX,1),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
IMUL %R11,%RDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%R14,%RCX,1),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R8,0xc0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
IMUL %R12,%RSI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %RCX,0xb8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,0xb0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD %RDI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x50(%RSP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RBX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RDI,%RSI,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RSI,0x100(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x10(%RSP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RSP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RSP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x90(%RSP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R14,0x40(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 610de <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_5GroupElPSW_EESW_EESZ_NSO_INSQ_INSR_4ZoneElPS10_EES10_EEEEENSM_IJEEEJZNK14ScatteringSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdES1D_RKNSR_4Core3SetES1H_S1H_RNS1E_5FieldIdJSS_SW_S10_EEES1K_RNS1I_IdJNSR_8MaterialENSR_8LegendreENSR_11GlobalGroupES1N_EEERNS1I_INSR_7MixElemEJS10_EEERNS1I_IiJS10_EEERNS1I_IS1L_JS1Q_EEERNS1I_IdJS1Q_EEERNS1I_IS1M_JSS_EEEEUlSS_SW_SW_S10_E_EEEEEvOS1C_._omp_fn.0+0x6fe> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R10,0x18(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 6111c <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_5GroupElPSW_EESW_EESZ_NSO_INSQ_INSR_4ZoneElPS10_EES10_EEEEENSM_IJEEEJZNK14ScatteringSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdES1D_RKNSR_4Core3SetES1H_S1H_RNS1E_5FieldIdJSS_SW_S10_EEES1K_RNS1I_IdJNSR_8MaterialENSR_8LegendreENSR_11GlobalGroupES1N_EEERNS1I_INSR_7MixElemEJS10_EEERNS1I_IiJS10_EEERNS1I_IS1L_JS1Q_EEERNS1I_IdJS1Q_EEERNS1I_IS1M_JSS_EEEEUlSS_SW_SW_S10_E_EEEEEvOS1C_._omp_fn.0+0x73c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INCQ 0x90(%RSP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
JMP 60c4e <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_5GroupElPSW_EESW_EESZ_NSO_INSQ_INSR_4ZoneElPS10_EES10_EEEEENSM_IJEEEJZNK14ScatteringSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdES1D_RKNSR_4Core3SetES1H_S1H_RNS1E_5FieldIdJSS_SW_S10_EEES1K_RNS1I_IdJNSR_8MaterialENSR_8LegendreENSR_11GlobalGroupES1N_EEERNS1I_INSR_7MixElemEJS10_EEERNS1I_IiJS10_EEERNS1I_IS1L_JS1Q_EEERNS1I_IdJS1Q_EEERNS1I_IS1M_JSS_EEEEUlSS_SW_SW_S10_E_EEEEEvOS1C_._omp_fn.0+0x26e> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
INCQ 0xa8(%RSP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
MOV 0xa0(%RSP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xa8(%RSP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R12,%RCX,1),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 610d1 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_5GroupElPSW_EESW_EESZ_NSO_INSQ_INSR_4ZoneElPS10_EES10_EEEEENSM_IJEEEJZNK14ScatteringSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdES1D_RKNSR_4Core3SetES1H_S1H_RNS1E_5FieldIdJSS_SW_S10_EEES1K_RNS1I_IdJNSR_8MaterialENSR_8LegendreENSR_11GlobalGroupES1N_EEERNS1I_INSR_7MixElemEJS10_EEERNS1I_IiJS10_EEERNS1I_IS1L_JS1Q_EEERNS1I_IdJS1Q_EEERNS1I_IS1M_JSS_EEEEUlSS_SW_SW_S10_E_EEEEEvOS1C_._omp_fn.0+0x6f1> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |