Loop Id: 1791 | Module: exec | Source: SoaDistanceTableAAOMPTarget.h:440-442 [...] | Coverage: 1.77% |
---|
Loop Id: 1791 | Module: exec | Source: SoaDistanceTableAAOMPTarget.h:440-442 [...] | Coverage: 1.77% |
---|
0x2c14d0 VMOVSD (%RSI,%R11,8),%XMM1 [6] |
0x2c14d6 MOV (%RCX,%R10,8),%RBX [8] |
0x2c14da VMOVSD %XMM1,(%RBX,%R13,8) [9] |
0x2c14e0 VMOVSD (%RDI,%R11,8),%XMM1 [2] |
0x2c14e6 VMOVSD (%R9,%R11,8),%XMM2 [5] |
0x2c14ec VMOVSD (%R8,%R11,8),%XMM3 [3] |
0x2c14f2 MOV (%RDX,%R10,8),%R14 [4] |
0x2c14f6 MOV -0x10(%RDX,%R10,8),%RBX [4] |
0x2c14fb INC %R11 |
0x2c14fe ADD $0x5,%R10 |
0x2c1502 LEA (%R14,%R13,8),%R15 |
0x2c1506 VXORPS %XMM0,%XMM1,%XMM1 |
0x2c150a VXORPS %XMM0,%XMM2,%XMM2 |
0x2c150e VXORPS %XMM0,%XMM3,%XMM3 |
0x2c1512 VMOVLPS %XMM1,(%R14,%R13,8) [7] |
0x2c1518 VMOVLPS %XMM2,(%R15,%RBX,8) [1] |
0x2c151e SAL $0x4,%RBX |
0x2c1522 VMOVLPS %XMM3,(%RBX,%R15,1) [10] |
0x2c1528 CMP %R11,%RAX |
0x2c152b JNE 2c14d0 |
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 244 - 263 |
-------------------------------------------------------------------------------- |
244: *(_base + M * i) = rhs[i]; |
[...] |
263: inline Accessor operator()(size_t i) { return Accessor(myData + i, nGhosts); } |
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 182 - 182 |
-------------------------------------------------------------------------------- |
182: inverse[d] = -X[d]; |
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 223 |
-------------------------------------------------------------------------------- |
223: return X[i]; |
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h: 440 - 442 |
-------------------------------------------------------------------------------- |
440: for (size_t i = iat + 1; i < num_targets_; ++i) |
441: { |
442: distances_[i][iat] = temp_r_[i]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.37 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 4.89 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.16 |
Bottlenecks | P5, P6, P7, |
Function | _ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi |
Source | VectorSoAContainer.h:244-244,VectorSoAContainer.h:263-263,TinyVector.h:182-182,OhmmsVector.h:223-223,SoaDistanceTableAAOMPTarget.h:440-442 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.67 |
CQA cycles if no scalar integer | 2.67 |
CQA cycles if FP arith vectorized | 3.67 |
CQA cycles if fully vectorized | 0.75 |
Front-end cycles | 3.17 |
DIV/SQRT cycles | 1.25 |
P0 cycles | 1.25 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 0.50 |
P4 cycles | 3.67 |
P5 cycles | 3.67 |
P6 cycles | 3.67 |
P7 cycles | 0.75 |
P8 cycles | 0.75 |
P9 cycles | 0.75 |
P10 cycles | 0.75 |
P11 cycles | 2.00 |
P12 cycles | 2.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 20.00 |
Nb uops | 19.00 |
Nb loads | 7.00 |
Nb stores | 4.00 |
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 | 56.00 |
Bytes stored | 32.00 |
Stride 0 | 0.00 |
Stride 1 | 4.00 |
Stride n | 2.00 |
Stride unknown | 2.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 54.55 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 75.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 15.91 |
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 | 25.00 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.37 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 4.89 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.16 |
Bottlenecks | P5, P6, P7, |
Function | _ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi |
Source | VectorSoAContainer.h:244-244,VectorSoAContainer.h:263-263,TinyVector.h:182-182,OhmmsVector.h:223-223,SoaDistanceTableAAOMPTarget.h:440-442 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.67 |
CQA cycles if no scalar integer | 2.67 |
CQA cycles if FP arith vectorized | 3.67 |
CQA cycles if fully vectorized | 0.75 |
Front-end cycles | 3.17 |
DIV/SQRT cycles | 1.25 |
P0 cycles | 1.25 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 0.50 |
P4 cycles | 3.67 |
P5 cycles | 3.67 |
P6 cycles | 3.67 |
P7 cycles | 0.75 |
P8 cycles | 0.75 |
P9 cycles | 0.75 |
P10 cycles | 0.75 |
P11 cycles | 2.00 |
P12 cycles | 2.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 20.00 |
Nb uops | 19.00 |
Nb loads | 7.00 |
Nb stores | 4.00 |
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 | 56.00 |
Bytes stored | 32.00 |
Stride 0 | 0.00 |
Stride 1 | 4.00 |
Stride n | 2.00 |
Stride unknown | 2.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 54.55 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 75.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 15.91 |
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 | 25.00 |
Path / |
Function | _ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi |
Source file and lines | SoaDistanceTableAAOMPTarget.h:440-442 |
Module | exec |
nb instructions | 20 |
nb uops | 19 |
loop length | 93 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.17 cycles |
front end | 3.17 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.25 | 1.25 | 1.00 | 1.00 | 0.50 | 3.67 | 3.67 | 3.67 | 0.75 | 0.75 | 0.75 | 0.75 | 2.00 | 2.00 |
cycles | 1.25 | 1.25 | 1.00 | 1.00 | 0.50 | 3.67 | 3.67 | 3.67 | 0.75 | 0.75 | 0.75 | 0.75 | 2.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
Front-end | 3.17 |
Dispatch | 3.67 |
Data deps. | 1.00 |
Overall L1 | 3.67 |
all | 54% |
load | 0% |
store | 75% |
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 | 100% |
all | 15% |
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 | 25% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%RSI,%R11,8),%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOV (%RCX,%R10,8),%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
VMOVSD %XMM1,(%RBX,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
VMOVSD (%RDI,%R11,8),%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R9,%R11,8),%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R11,8),%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOV (%RDX,%R10,8),%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV -0x10(%RDX,%R10,8),%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
INC %R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD $0x5,%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LEA (%R14,%R13,8),%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VXORPS %XMM0,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VXORPS %XMM0,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VXORPS %XMM0,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VMOVLPS %XMM1,(%R14,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
VMOVLPS %XMM2,(%R15,%RBX,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
SAL $0x4,%RBX | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VMOVLPS %XMM3,(%RBX,%R15,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
CMP %R11,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
JNE 2c14d0 <_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi+0x140> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
Function | _ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi |
Source file and lines | SoaDistanceTableAAOMPTarget.h:440-442 |
Module | exec |
nb instructions | 20 |
nb uops | 19 |
loop length | 93 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.17 cycles |
front end | 3.17 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.25 | 1.25 | 1.00 | 1.00 | 0.50 | 3.67 | 3.67 | 3.67 | 0.75 | 0.75 | 0.75 | 0.75 | 2.00 | 2.00 |
cycles | 1.25 | 1.25 | 1.00 | 1.00 | 0.50 | 3.67 | 3.67 | 3.67 | 0.75 | 0.75 | 0.75 | 0.75 | 2.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
Front-end | 3.17 |
Dispatch | 3.67 |
Data deps. | 1.00 |
Overall L1 | 3.67 |
all | 54% |
load | 0% |
store | 75% |
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 | 100% |
all | 15% |
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 | 25% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%RSI,%R11,8),%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOV (%RCX,%R10,8),%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
VMOVSD %XMM1,(%RBX,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
VMOVSD (%RDI,%R11,8),%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R9,%R11,8),%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R8,%R11,8),%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOV (%RDX,%R10,8),%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV -0x10(%RDX,%R10,8),%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
INC %R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD $0x5,%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LEA (%R14,%R13,8),%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VXORPS %XMM0,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VXORPS %XMM0,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VXORPS %XMM0,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VMOVLPS %XMM1,(%R14,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
VMOVLPS %XMM2,(%R15,%RBX,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
SAL $0x4,%RBX | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VMOVLPS %XMM3,(%RBX,%R15,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
CMP %R11,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
JNE 2c14d0 <_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi+0x140> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |