Loop Id: 868 | Module: exec | Source: par_multi_interp.c:1167-1173 | Coverage: 0.01% |
---|
Loop Id: 868 | Module: exec | Source: par_multi_interp.c:1167-1173 | Coverage: 0.01% |
---|
0x4438c0 MOV -0x18(%RSI),%RCX [12] |
0x4438c4 MOV (%RBX,%RCX,8),%R11 [16] |
0x4438c8 MOV (%R13,%RCX,8),%RDX [7] |
0x4438cd MOV %RDX,(%R15,%R11,8) [4] |
0x4438d1 MOV (%RBX,%RCX,8),%RCX [16] |
0x4438d5 MOV %R10,(%R12,%RCX,8) [14] |
0x4438d9 MOV -0x10(%RSI),%RCX [12] |
0x4438dd MOV (%RBX,%RCX,8),%R11 [9] |
0x4438e1 MOV (%R13,%RCX,8),%RDX [15] |
0x4438e6 MOV %RDX,(%R15,%R11,8) [6] |
0x4438ea MOV (%RBX,%RCX,8),%RCX [9] |
0x4438ee MOV %R10,(%R12,%RCX,8) [2] |
0x4438f2 MOV -0x8(%RSI),%RCX [12] |
0x4438f6 MOV (%RBX,%RCX,8),%R11 [13] |
0x4438fa MOV (%R13,%RCX,8),%RDX [1] |
0x4438ff MOV %RDX,(%R15,%R11,8) [8] |
0x443903 MOV (%RBX,%RCX,8),%RCX [13] |
0x443907 MOV %R10,(%R12,%RCX,8) [3] |
0x44390b MOV (%RSI),%RCX [12] |
0x44390e MOV (%RBX,%RCX,8),%R11 [17] |
0x443912 MOV (%R13,%RCX,8),%RDX [10] |
0x443917 MOV %RDX,(%R15,%R11,8) [11] |
0x44391b MOV (%RBX,%RCX,8),%RCX [17] |
0x44391f MOV %R10,(%R12,%RCX,8) [5] |
0x443923 ADD $0x20,%RSI |
0x443927 DEC %RDI |
0x44392a JNE 4438c0 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 1167 - 1173 |
-------------------------------------------------------------------------------- |
1167: #pragma omp parallel for private(i,i1) HYPRE_SMP_SCHEDULE |
1168: #endif |
1169: for (i=0; i < n_coarse; i++) |
1170: { |
1171: i1 = C_array[i]; |
1172: P_diag_j[P_diag_i[i1]] = fine_to_coarse[i1]; |
1173: P_diag_data[P_diag_i[i1]] = 1.0; |
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:1167 | 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 | 1.23 |
Bottlenecks | P2, P3, P4, P7, |
Function | hypre_BoomerAMGBuildMultipass.extracted.31 |
Source | par_multi_interp.c:1167-1173 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 8.00 |
CQA cycles if no scalar integer | 8.00 |
CQA cycles if FP arith vectorized | 8.00 |
CQA cycles if fully vectorized | 1.00 |
Front-end cycles | 6.50 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.50 |
P1 cycles | 8.00 |
P2 cycles | 8.00 |
P3 cycles | 8.00 |
P4 cycles | 0.50 |
P5 cycles | 0.50 |
P6 cycles | 8.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 9.46 |
Stall cycles (UFS) | 2.78 |
Nb insns | 27.00 |
Nb uops | 26.00 |
Nb loads | 16.00 |
Nb stores | 8.00 |
Nb stack references | 0.00 |
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 | 24.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 64.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 4.00 |
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 | NA |
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 | NA |
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 | 1.23 |
Bottlenecks | P2, P3, P4, P7, |
Function | hypre_BoomerAMGBuildMultipass.extracted.31 |
Source | par_multi_interp.c:1167-1173 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 8.00 |
CQA cycles if no scalar integer | 8.00 |
CQA cycles if FP arith vectorized | 8.00 |
CQA cycles if fully vectorized | 1.00 |
Front-end cycles | 6.50 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.50 |
P1 cycles | 8.00 |
P2 cycles | 8.00 |
P3 cycles | 8.00 |
P4 cycles | 0.50 |
P5 cycles | 0.50 |
P6 cycles | 8.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 9.46 |
Stall cycles (UFS) | 2.78 |
Nb insns | 27.00 |
Nb uops | 26.00 |
Nb loads | 16.00 |
Nb stores | 8.00 |
Nb stack references | 0.00 |
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 | 24.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 64.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 4.00 |
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 | NA |
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 | NA |
Path / |
Function | hypre_BoomerAMGBuildMultipass.extracted.31 |
Source file and lines | par_multi_interp.c:1167-1173 |
Module | exec |
nb instructions | 27 |
nb uops | 26 |
loop length | 108 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 6.50 cycles |
front end | 6.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.50 | 8.00 | 8.00 | 8.00 | 0.50 | 0.50 | 8.00 |
cycles | 0.50 | 0.50 | 8.00 | 8.00 | 8.00 | 0.50 | 0.50 | 8.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 9.46 |
Stall cycles | 2.78 |
LM full (events) | 6.56 |
Front-end | 6.50 |
Dispatch | 8.00 |
Data deps. | 1.00 |
Overall L1 | 8.00 |
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 | NA (no other vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x18(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RCX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R13,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%R15,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RBX,%RCX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,(%R12,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x10(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RCX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R13,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%R15,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RBX,%RCX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,(%R12,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x8(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RCX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R13,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%R15,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RBX,%RCX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,(%R12,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RCX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R13,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%R15,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RBX,%RCX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,(%R12,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x20,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
DEC %RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 4438c0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | hypre_BoomerAMGBuildMultipass.extracted.31 |
Source file and lines | par_multi_interp.c:1167-1173 |
Module | exec |
nb instructions | 27 |
nb uops | 26 |
loop length | 108 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 6.50 cycles |
front end | 6.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.50 | 8.00 | 8.00 | 8.00 | 0.50 | 0.50 | 8.00 |
cycles | 0.50 | 0.50 | 8.00 | 8.00 | 8.00 | 0.50 | 0.50 | 8.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 9.46 |
Stall cycles | 2.78 |
LM full (events) | 6.56 |
Front-end | 6.50 |
Dispatch | 8.00 |
Data deps. | 1.00 |
Overall L1 | 8.00 |
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 | NA (no other vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x18(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RCX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R13,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%R15,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RBX,%RCX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,(%R12,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x10(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RCX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R13,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%R15,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RBX,%RCX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,(%R12,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x8(%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RCX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R13,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%R15,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RBX,%RCX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,(%R12,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RSI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RCX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R13,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%R15,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RBX,%RCX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,(%R12,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x20,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
DEC %RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 4438c0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |