Loop Id: 983 | Module: exec | Source: par_multi_interp.c:1782-1787 | Coverage: 0.03% |
---|
Loop Id: 983 | Module: exec | Source: par_multi_interp.c:1782-1787 | Coverage: 0.03% |
---|
0x4438e0 MOV (%R8),%RAX [1] |
0x4438e3 MOV %R12,(%RDX,%RAX,8) [2] |
0x4438e7 MOVQ $0,(%R14,%R12,8) [4] |
0x4438ef MOV %RAX,(%RCX,%R12,8) [3] |
0x4438f3 INC %R12 |
0x4438f6 ADD $0x8,%R8 |
0x4438fa CMP %R12,%RSI |
0x4438fd JNE 4438e0 |
/scratch_na/users/xoserete/qaas_runs/171-172-8218/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 1782 - 1787 |
-------------------------------------------------------------------------------- |
1782: for (j=j_start; j < j_end; j++) |
1783: { |
1784: k1 = P_diag_pass[pass][j]; |
1785: tmp_array[k1] = cnt; |
1786: P_diag_data[cnt] = 0; |
1787: P_diag_j[cnt++] = k1; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 9.60 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.29 |
Bottlenecks | P4, P7, P8, P9, |
Function | hypre_BoomerAMGBuildMultipass.extracted.28 |
Source | par_multi_interp.c:1782-1787 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 1.50 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.16 |
Front-end cycles | 1.17 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.00 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 1.50 |
P4 cycles | 0.00 |
P5 cycles | 0.50 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 0.00 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.60 |
Stall cycles (UFS) | 0.01 |
Nb insns | 8.00 |
Nb uops | 7.00 |
Nb loads | 1.00 |
Nb stores | 3.00 |
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 | 21.33 |
Bytes prefetched | 0.00 |
Bytes loaded | 8.00 |
Bytes stored | 24.00 |
Stride 0 | 0.00 |
Stride 1 | 3.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | NA |
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 | 10.42 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | 10.42 |
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 | 9.60 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.29 |
Bottlenecks | P4, P7, P8, P9, |
Function | hypre_BoomerAMGBuildMultipass.extracted.28 |
Source | par_multi_interp.c:1782-1787 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 1.50 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.16 |
Front-end cycles | 1.17 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.00 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 1.50 |
P4 cycles | 0.00 |
P5 cycles | 0.50 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 0.00 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.60 |
Stall cycles (UFS) | 0.01 |
Nb insns | 8.00 |
Nb uops | 7.00 |
Nb loads | 1.00 |
Nb stores | 3.00 |
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 | 21.33 |
Bytes prefetched | 0.00 |
Bytes loaded | 8.00 |
Bytes stored | 24.00 |
Stride 0 | 0.00 |
Stride 1 | 3.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | NA |
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 | 10.42 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | 10.42 |
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.28 |
Source file and lines | par_multi_interp.c:1782-1787 |
Module | exec |
nb instructions | 8 |
nb uops | 7 |
loop length | 31 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.17 cycles |
front end | 1.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.00 | 0.33 | 0.33 | 1.50 | 0.00 | 0.50 | 1.50 | 1.50 | 1.50 | 0.00 | 0.33 |
cycles | 0.50 | 0.00 | 0.33 | 0.33 | 1.50 | 0.00 | 0.50 | 1.50 | 1.50 | 1.50 | 0.00 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.60 |
Stall cycles | 0.01 |
RS full (events) | 0.03 |
Front-end | 1.17 |
Dispatch | 1.50 |
Data deps. | 1.00 |
Overall L1 | 1.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 10% |
load | NA (no load vectorizable/vectorized instructions) |
store | 10% |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R8),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12,(%RDX,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVQ $0,(%R14,%R12,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,(%RCX,%R12,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x8,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R12,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 4438e0 <hypre_BoomerAMGBuildMultipass.extracted.28+0x550> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_BoomerAMGBuildMultipass.extracted.28 |
Source file and lines | par_multi_interp.c:1782-1787 |
Module | exec |
nb instructions | 8 |
nb uops | 7 |
loop length | 31 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.17 cycles |
front end | 1.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.00 | 0.33 | 0.33 | 1.50 | 0.00 | 0.50 | 1.50 | 1.50 | 1.50 | 0.00 | 0.33 |
cycles | 0.50 | 0.00 | 0.33 | 0.33 | 1.50 | 0.00 | 0.50 | 1.50 | 1.50 | 1.50 | 0.00 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.60 |
Stall cycles | 0.01 |
RS full (events) | 0.03 |
Front-end | 1.17 |
Dispatch | 1.50 |
Data deps. | 1.00 |
Overall L1 | 1.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 10% |
load | NA (no load vectorizable/vectorized instructions) |
store | 10% |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R8),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12,(%RDX,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVQ $0,(%R14,%R12,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,(%RCX,%R12,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x8,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R12,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 4438e0 <hypre_BoomerAMGBuildMultipass.extracted.28+0x550> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |