Loop Id: 226 | Module: exec | Source: pack_kernel.cpp:122-124 | Coverage: 0.02% |
---|
Loop Id: 226 | Module: exec | Source: pack_kernel.cpp:122-124 | Coverage: 0.02% |
---|
0x42ff30 MOVSXD %ESI,%RSI |
0x42ff33 MOV %RCX,%RDI |
0x42ff36 SAR $0x20,%RDI |
0x42ff3a ADD %RDX,%RDI |
0x42ff3d VMOVQ (%RAX,%RDI,8),%XMM2 [2] |
0x42ff42 MOV %R14,%RDI |
0x42ff45 VMOVQ %XMM2,(%R15,%RSI,8) [1] |
0x42ff4b INC %ESI |
0x42ff4d ADD %R14,%RCX |
0x42ff50 DEC %RBX |
0x42ff53 JNE 42ff30 |
/scratch_na/users/xoserete/qaas_runs/171-415-4687/intel/CloverLeafCXX/build/CloverLeafCXX/src/omp/pack_kernel.cpp: 122 - 124 |
-------------------------------------------------------------------------------- |
122: for (int j = 0; j < depth; ++j) { |
123: int index = buffer_offset + j + k * depth; |
124: right_snd[index] = field(x_max + 1 - j, k); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
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 | 1.20 |
Bottlenecks | |
Function | clover_pack_message_right(global_variables&, int, int, int, int, clover::Buffer2D |
Source | pack_kernel.cpp:122-124 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 2.00 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 0.25 |
Front-end cycles | 1.67 |
DIV/SQRT cycles | 1.20 |
P0 cycles | 1.33 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 0.50 |
P4 cycles | 1.13 |
P5 cycles | 1.20 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 1.13 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 2.07 - 2.14 |
Stall cycles (UFS) | 0.00 - 0.01 |
Nb insns | 11.00 |
Nb uops | 10.00 |
Nb loads | 1.00 |
Nb stores | 1.00 |
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 | 8.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 8.00 |
Bytes stored | 8.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
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 | 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 | 12.50 |
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 | 1.20 |
Bottlenecks | |
Function | clover_pack_message_right(global_variables&, int, int, int, int, clover::Buffer2D |
Source | pack_kernel.cpp:122-124 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 2.00 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 0.25 |
Front-end cycles | 1.67 |
DIV/SQRT cycles | 1.20 |
P0 cycles | 1.33 |
P1 cycles | 0.33 |
P2 cycles | 0.33 |
P3 cycles | 0.50 |
P4 cycles | 1.13 |
P5 cycles | 1.20 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 1.13 |
P10 cycles | 0.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 2.07 - 2.14 |
Stall cycles (UFS) | 0.00 - 0.01 |
Nb insns | 11.00 |
Nb uops | 10.00 |
Nb loads | 1.00 |
Nb stores | 1.00 |
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 | 8.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 8.00 |
Bytes stored | 8.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
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 | 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 | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | clover_pack_message_right(global_variables&, int, int, int, int, clover::Buffer2D |
Source file and lines | pack_kernel.cpp:122-124 |
Module | exec |
nb instructions | 11 |
nb uops | 10 |
loop length | 37 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.67 cycles |
front end | 1.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.20 | 1.33 | 0.33 | 0.33 | 0.50 | 1.13 | 1.20 | 0.50 | 0.50 | 0.50 | 1.13 | 0.33 |
cycles | 1.20 | 1.33 | 0.33 | 0.33 | 0.50 | 1.13 | 1.20 | 0.50 | 0.50 | 0.50 | 1.13 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 2.07-2.14 |
Stall cycles | 0.00-0.01 |
Front-end | 1.67 |
Dispatch | 1.33 |
Data deps. | 2.00 |
Overall L1 | 2.00 |
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 | NA (no other vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD %ESI,%RSI | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SAR $0x20,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
ADD %RDX,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVQ (%RAX,%RDI,8),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VMOVQ %XMM2,(%R15,%RSI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %R14,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
DEC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 42ff30 <_Z25clover_pack_message_rightR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii.extracted+0x350> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | clover_pack_message_right(global_variables&, int, int, int, int, clover::Buffer2D |
Source file and lines | pack_kernel.cpp:122-124 |
Module | exec |
nb instructions | 11 |
nb uops | 10 |
loop length | 37 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.67 cycles |
front end | 1.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.20 | 1.33 | 0.33 | 0.33 | 0.50 | 1.13 | 1.20 | 0.50 | 0.50 | 0.50 | 1.13 | 0.33 |
cycles | 1.20 | 1.33 | 0.33 | 0.33 | 0.50 | 1.13 | 1.20 | 0.50 | 0.50 | 0.50 | 1.13 | 0.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 2.07-2.14 |
Stall cycles | 0.00-0.01 |
Front-end | 1.67 |
Dispatch | 1.33 |
Data deps. | 2.00 |
Overall L1 | 2.00 |
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 | NA (no other vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD %ESI,%RSI | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SAR $0x20,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
ADD %RDX,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VMOVQ (%RAX,%RDI,8),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VMOVQ %XMM2,(%R15,%RSI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %R14,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
DEC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 42ff30 <_Z25clover_pack_message_rightR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii.extracted+0x350> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |