Loop Id: 899 | Module: exec | Source: par_multi_interp.c:917-970 [...] | Coverage: 1.28% |
---|
Loop Id: 899 | Module: exec | Source: par_multi_interp.c:917-970 [...] | Coverage: 1.28% |
---|
0x449760 MOV -0x48(%RBP),%R10 |
0x449764 INC %R11 |
0x449767 MOV -0xb8(%RBP),%RAX |
0x44976e CMP 0x8(%RAX,%RDI,8),%R11 |
0x449773 JGE 449ac0 |
0x449779 MOV -0x128(%RBP),%RAX |
0x449780 MOV (%RAX,%R11,8),%RSI |
0x449784 MOV -0x118(%RBP),%RAX |
0x44978b CMP %R10,(%RAX,%RSI,8) |
0x44978f JNE 449764 |
0x449791 MOV -0x30(%RBP),%RAX |
0x449795 MOV 0x8(%RAX,%RSI,8),%R10 |
0x44979a TEST %R10,%R10 |
0x44979d JLE 449947 |
0x4497a3 MOV -0x68(%RBP),%RAX |
0x4497a7 MOV %RSI,-0x90(%RBP) |
0x4497ae MOV (%RAX,%RSI,8),%RDX |
0x4497b2 ADD %RDX,%R10 |
0x4497b5 MOV -0x40(%RBP),%RAX |
0x4497b9 MOV -0x50(%RBP),%RCX |
0x4497bd MOV -0x8(%RAX,%RCX,8),%R9 |
0x4497c2 LEA 0x1(%RDX),%RAX |
0x4497c6 CMP %RAX,%R10 |
0x4497c9 CMOVLE %RAX,%R10 |
0x4497cd MOV %R10,%RAX |
0x4497d0 SUB %RDX,%RAX |
0x4497d3 CMP $0x4,%RAX |
0x4497d7 MOV %RAX,-0x88(%RBP) |
0x4497de JAE 449860 |
0x4497e4 MOV -0x88(%RBP),%RCX |
0x4497eb MOV %RCX,%RAX |
0x4497ee AND $-0x4,%RAX |
0x4497f2 CMP %RCX,%RAX |
0x4497f5 JAE 449940 |
0x4497fb ADD %RAX,%RDX |
0x4497fe MOV -0x90(%RBP),%RSI |
0x449805 MOV -0x30(%RBP),%RCX |
0x449809 JMP 44982c |
(902) 0x449820 INC %RDX |
(902) 0x449823 CMP %RDX,%R10 |
(902) 0x449826 JE 449947 |
(902) 0x44982c MOV (%R9,%RDX,8),%RAX |
(902) 0x449830 CMP %RDI,(%R14,%RAX,8) |
(902) 0x449834 JE 449820 |
(902) 0x449836 INC %R12 |
(902) 0x449839 INCQ 0x8(%RCX,%RDI,8) |
(902) 0x44983e MOV %RDI,(%R14,%RAX,8) |
(902) 0x449842 JMP 449820 |
0x449860 MOV %RAX,%RSI |
0x449863 SHR $0x2,%RSI |
0x449867 LEA (%R9,%RDX,8),%RAX |
0x44986b ADD $0x18,%RAX |
0x44986f MOV -0x30(%RBP),%R8 |
0x449873 JMP 44988d |
(903) 0x449880 ADD $0x20,%RAX |
(903) 0x449884 DEC %RSI |
(903) 0x449887 JE 4497e4 |
(903) 0x44988d MOV -0x18(%RAX),%RCX |
(903) 0x449891 CMP %RDI,(%R14,%RCX,8) |
(903) 0x449895 JNE 4498c0 |
(903) 0x449897 MOV -0x10(%RAX),%RCX |
(903) 0x44989b CMP %RDI,(%R14,%RCX,8) |
(903) 0x44989f JNE 4498d6 |
(903) 0x4498a1 MOV -0x8(%RAX),%RCX |
(903) 0x4498a5 CMP %RDI,(%R14,%RCX,8) |
(903) 0x4498a9 JNE 4498f0 |
(903) 0x4498ab MOV (%RAX),%RCX |
(903) 0x4498ae CMP %RDI,(%R14,%RCX,8) |
(903) 0x4498b2 JE 449880 |
(903) 0x4498b4 JMP 44990d |
(903) 0x4498c0 INC %R12 |
(903) 0x4498c3 INCQ 0x8(%R8,%RDI,8) |
(903) 0x4498c8 MOV %RDI,(%R14,%RCX,8) |
(903) 0x4498cc MOV -0x10(%RAX),%RCX |
(903) 0x4498d0 CMP %RDI,(%R14,%RCX,8) |
(903) 0x4498d4 JE 4498a1 |
(903) 0x4498d6 INC %R12 |
(903) 0x4498d9 MOV -0x30(%RBP),%RBX |
(903) 0x4498dd INCQ 0x8(%RBX,%RDI,8) |
(903) 0x4498e2 MOV %RDI,(%R14,%RCX,8) |
(903) 0x4498e6 MOV -0x8(%RAX),%RCX |
(903) 0x4498ea CMP %RDI,(%R14,%RCX,8) |
(903) 0x4498ee JE 4498ab |
(903) 0x4498f0 INC %R12 |
(903) 0x4498f3 MOV -0x30(%RBP),%RBX |
(903) 0x4498f7 INCQ 0x8(%RBX,%RDI,8) |
(903) 0x4498fc MOV %RDI,(%R14,%RCX,8) |
(903) 0x449900 MOV (%RAX),%RCX |
(903) 0x449903 CMP %RDI,(%R14,%RCX,8) |
(903) 0x449907 JE 449880 |
(903) 0x44990d INC %R12 |
(903) 0x449910 MOV -0x30(%RBP),%RBX |
(903) 0x449914 INCQ 0x8(%RBX,%RDI,8) |
(903) 0x449919 MOV %RDI,(%R14,%RCX,8) |
(903) 0x44991d JMP 449880 |
0x449940 MOV -0x90(%RBP),%RSI |
0x449947 MOV -0x70(%RBP),%RAX |
0x44994b MOV 0x8(%RAX,%RSI,8),%R8 |
0x449950 TEST %R8,%R8 |
0x449953 JLE 449760 |
0x449959 MOV -0x60(%RBP),%RAX |
0x44995d MOV (%RAX,%RSI,8),%RDX |
0x449961 ADD %RDX,%R8 |
0x449964 MOV -0x38(%RBP),%RAX |
0x449968 MOV -0x50(%RBP),%RCX |
0x44996c MOV -0x8(%RAX,%RCX,8),%R9 |
0x449971 LEA 0x1(%RDX),%RAX |
0x449975 CMP %RAX,%R8 |
0x449978 CMOVLE %RAX,%R8 |
0x44997c MOV %R8,%R10 |
0x44997f SUB %RDX,%R10 |
0x449982 CMP $0x4,%R10 |
0x449986 JAE 449a00 |
0x449988 MOV -0x70(%RBP),%RBX |
0x44998c MOV %R10,%RAX |
0x44998f AND $-0x4,%RAX |
0x449993 CMP %R10,%RAX |
0x449996 JAE 449760 |
0x44999c ADD %RAX,%RDX |
0x44999f MOV -0x48(%RBP),%R10 |
0x4499a3 JMP 4499cc |
(900) 0x4499c0 INC %RDX |
(900) 0x4499c3 CMP %RDX,%R8 |
(900) 0x4499c6 JE 449764 |
(900) 0x4499cc MOV (%R9,%RDX,8),%RAX |
(900) 0x4499d0 CMP %RDI,(%R15,%RAX,8) |
(900) 0x4499d4 JE 4499c0 |
(900) 0x4499d6 INC %R13 |
(900) 0x4499d9 INCQ 0x8(%RBX,%RDI,8) |
(900) 0x4499de MOV %RDI,(%R15,%RAX,8) |
(900) 0x4499e2 JMP 4499c0 |
0x449a00 MOV %R10,%RSI |
0x449a03 SHR $0x2,%RSI |
0x449a07 LEA (%R9,%RDX,8),%RAX |
0x449a0b ADD $0x18,%RAX |
0x449a0f MOV -0x70(%RBP),%RBX |
0x449a13 JMP 449a2d |
(901) 0x449a20 ADD $0x20,%RAX |
(901) 0x449a24 DEC %RSI |
(901) 0x449a27 JE 44998c |
(901) 0x449a2d MOV -0x18(%RAX),%RCX |
(901) 0x449a31 CMP %RDI,(%R15,%RCX,8) |
(901) 0x449a35 JNE 449a60 |
(901) 0x449a37 MOV -0x10(%RAX),%RCX |
(901) 0x449a3b CMP %RDI,(%R15,%RCX,8) |
(901) 0x449a3f JNE 449a76 |
(901) 0x449a41 MOV -0x8(%RAX),%RCX |
(901) 0x449a45 CMP %RDI,(%R15,%RCX,8) |
(901) 0x449a49 JNE 449a8c |
(901) 0x449a4b MOV (%RAX),%RCX |
(901) 0x449a4e CMP %RDI,(%R15,%RCX,8) |
(901) 0x449a52 JE 449a20 |
(901) 0x449a54 JMP 449aa5 |
(901) 0x449a60 INC %R13 |
(901) 0x449a63 INCQ 0x8(%RBX,%RDI,8) |
(901) 0x449a68 MOV %RDI,(%R15,%RCX,8) |
(901) 0x449a6c MOV -0x10(%RAX),%RCX |
(901) 0x449a70 CMP %RDI,(%R15,%RCX,8) |
(901) 0x449a74 JE 449a41 |
(901) 0x449a76 INC %R13 |
(901) 0x449a79 INCQ 0x8(%RBX,%RDI,8) |
(901) 0x449a7e MOV %RDI,(%R15,%RCX,8) |
(901) 0x449a82 MOV -0x8(%RAX),%RCX |
(901) 0x449a86 CMP %RDI,(%R15,%RCX,8) |
(901) 0x449a8a JE 449a4b |
(901) 0x449a8c INC %R13 |
(901) 0x449a8f INCQ 0x8(%RBX,%RDI,8) |
(901) 0x449a94 MOV %RDI,(%R15,%RCX,8) |
(901) 0x449a98 MOV (%RAX),%RCX |
(901) 0x449a9b CMP %RDI,(%R15,%RCX,8) |
(901) 0x449a9f JE 449a20 |
(901) 0x449aa5 INC %R13 |
(901) 0x449aa8 INCQ 0x8(%RBX,%RDI,8) |
(901) 0x449aad MOV %RDI,(%R15,%RCX,8) |
(901) 0x449ab1 JMP 449a20 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 917 - 970 |
-------------------------------------------------------------------------------- |
917: for (i=0; i < n_coarse; i++) |
[...] |
944: for (j=S_diag_i[i1]; j < S_diag_i[i1+1]; j++) |
945: { |
946: j1 = S_diag_j[j]; |
947: if (assigned[j1] == pass-1) |
948: { |
949: j_start = P_diag_start[j1]; |
950: j_end = j_start+P_diag_i[j1+1]; |
951: for (k=j_start; k < j_end; k++) |
952: { |
953: k1 = P_diag_pass[pass-1][k]; |
954: if (P_marker[k1] != i1) |
955: { |
956: cnt_nz++; |
957: P_diag_i[i1+1]++; |
958: P_marker[k1] = i1; |
959: } |
960: } |
961: j_start = P_offd_start[j1]; |
962: j_end = j_start+P_offd_i[j1+1]; |
963: for (k=j_start; k < j_end; k++) |
964: { |
965: k1 = P_offd_pass[pass-1][k]; |
966: if (P_marker_offd[k1] != i1) |
967: { |
968: cnt_nz_offd++; |
969: P_offd_i[i1+1]++; |
970: P_marker_offd[k1] = i1; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_BoomerAMGBuildMultipass | par_multi_interp.c:891 | exec |
○ | hypre_BoomerAMGSetup | par_amg_setup.c:737 | exec |
○ | hypre_PCGSetup | pcg.c:234 | exec |
○ | main | amg.c:398 | exec |
○ | __libc_init_first | libc.so.6 |
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 | 1.34 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGBuildMultipass.extracted.34 |
Source | par_multi_interp.c:917-970 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 19.50 |
CQA cycles if no scalar integer | 19.50 |
CQA cycles if FP arith vectorized | 19.50 |
CQA cycles if fully vectorized | 2.44 |
Front-end cycles | 19.50 |
DIV/SQRT cycles | 10.25 |
P0 cycles | 10.25 |
P1 cycles | 14.50 |
P2 cycles | 14.50 |
P3 cycles | 2.00 |
P4 cycles | 10.25 |
P5 cycles | 10.25 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 19.70 |
Stall cycles (UFS) | 0.00 |
Nb insns | 76.00 |
Nb uops | 76.00 |
Nb loads | 29.00 |
Nb stores | 2.00 |
Nb stack references | 13.00 |
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 | 12.72 |
Bytes prefetched | 0.00 |
Bytes loaded | 232.00 |
Bytes stored | 16.00 |
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 | 0.00 |
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 | 12.50 |
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 | 1.34 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGBuildMultipass.extracted.34 |
Source | par_multi_interp.c:917-970 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 19.50 |
CQA cycles if no scalar integer | 19.50 |
CQA cycles if FP arith vectorized | 19.50 |
CQA cycles if fully vectorized | 2.44 |
Front-end cycles | 19.50 |
DIV/SQRT cycles | 10.25 |
P0 cycles | 10.25 |
P1 cycles | 14.50 |
P2 cycles | 14.50 |
P3 cycles | 2.00 |
P4 cycles | 10.25 |
P5 cycles | 10.25 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 19.70 |
Stall cycles (UFS) | 0.00 |
Nb insns | 76.00 |
Nb uops | 76.00 |
Nb loads | 29.00 |
Nb stores | 2.00 |
Nb stack references | 13.00 |
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 | 12.72 |
Bytes prefetched | 0.00 |
Bytes loaded | 232.00 |
Bytes stored | 16.00 |
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 | 0.00 |
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 | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Path / |
Function | hypre_BoomerAMGBuildMultipass.extracted.34 |
Source file and lines | par_multi_interp.c:917-970 |
Module | exec |
nb instructions | 76 |
nb uops | 76 |
loop length | 314 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 13 |
micro-operation queue | 19.50 cycles |
front end | 19.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 10.25 | 10.25 | 14.50 | 14.50 | 2.00 | 10.25 | 10.25 | 2.00 |
cycles | 10.25 | 10.25 | 14.50 | 14.50 | 2.00 | 10.25 | 10.25 | 2.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 19.70 |
Stall cycles | 0.00 |
Front-end | 19.50 |
Dispatch | 14.50 |
Overall L1 | 19.50 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
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 | 12% |
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 -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xb8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP 0x8(%RAX,%RDI,8),%R11 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 449ac0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x128(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R11,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x118(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R10,(%RAX,%RSI,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 449764 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RSI,8),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R10,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 449947 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RAX,%RSI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x8(%RAX,%RCX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%RDX),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RAX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVLE %RAX,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RDX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,-0x88(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JAE 449860 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x88(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 449940 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RAX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x90(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 44982c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RSI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R9,%RDX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x30(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 44988d | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x90(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RSI,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 449760 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x60(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RSI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x8(%RAX,%RCX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%RDX),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVLE %RAX,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R8,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RDX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x4,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 449a00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x70(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 449760 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RAX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4499cc | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %R10,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RSI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R9,%RDX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x70(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 449a2d | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | hypre_BoomerAMGBuildMultipass.extracted.34 |
Source file and lines | par_multi_interp.c:917-970 |
Module | exec |
nb instructions | 76 |
nb uops | 76 |
loop length | 314 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 13 |
micro-operation queue | 19.50 cycles |
front end | 19.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 10.25 | 10.25 | 14.50 | 14.50 | 2.00 | 10.25 | 10.25 | 2.00 |
cycles | 10.25 | 10.25 | 14.50 | 14.50 | 2.00 | 10.25 | 10.25 | 2.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 19.70 |
Stall cycles | 0.00 |
Front-end | 19.50 |
Dispatch | 14.50 |
Overall L1 | 19.50 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
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 | 12% |
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 -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xb8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP 0x8(%RAX,%RDI,8),%R11 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 449ac0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x128(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R11,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x118(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R10,(%RAX,%RSI,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 449764 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RSI,8),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R10,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 449947 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RAX,%RSI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x8(%RAX,%RCX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%RDX),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RAX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVLE %RAX,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RDX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,-0x88(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JAE 449860 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x88(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 449940 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RAX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x90(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 44982c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RSI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R9,%RDX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x30(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 44988d | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x90(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RSI,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 449760 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x60(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RSI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x8(%RAX,%RCX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%RDX),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVLE %RAX,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R8,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RDX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x4,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 449a00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x70(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 449760 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RAX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4499cc | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %R10,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RSI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R9,%RDX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x70(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 449a2d | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |