Loop Id: 4342 | Module: exec | Source: csr_matvec.c:564-567 | Coverage: 0.57% |
---|
Loop Id: 4342 | Module: exec | Source: csr_matvec.c:564-567 | Coverage: 0.57% |
---|
0x4df740 VMOVSD (%R15,%RSI,8),%XMM0 [2] |
0x4df746 VMOVSD (%R12,%RDI,8),%XMM1 [1] |
0x4df74c MOV (%R14,%RDI,8),%RAX [4] |
0x4df750 ADD %R13,%RAX |
0x4df753 VFMADD213SD (%RBX,%RAX,8),%XMM0,%XMM1 [3] |
0x4df759 VMOVSD %XMM1,(%RBX,%RAX,8) [3] |
0x4df75e INC %RDI |
0x4df761 CMP %RDI,%R8 |
0x4df764 JNE 4df740 |
/scratch_na/users/xoserete/qaas_runs/171-172-8218/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c: 564 - 567 |
-------------------------------------------------------------------------------- |
564: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
565: { |
566: j = A_j[jj]; |
567: y_data_expand[offset + j] += A_data[jj] * x_data[i]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.29 |
CQA speedup if FP arith vectorized | 1.44 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.13 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source | csr_matvec.c:564-567 |
Source loop unroll info | unrolled by 4 |
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 | 1.17 |
CQA cycles if FP arith vectorized | 1.04 |
CQA cycles if fully vectorized | 0.19 |
Front-end cycles | 1.50 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.50 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.50 |
P4 cycles | 0.60 |
P5 cycles | 0.50 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.40 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.74 |
Stall cycles (UFS) | 0.00 |
Nb insns | 9.00 |
Nb uops | 8.00 |
Nb loads | 4.00 |
Nb stores | 1.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.33 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 1.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 26.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
Bytes stored | 8.00 |
Stride 0 | 1.00 |
Stride 1 | 2.00 |
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 | NA |
Vectorization ratio fma | 0.00 |
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 | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.29 |
CQA speedup if FP arith vectorized | 1.44 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.13 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source | csr_matvec.c:564-567 |
Source loop unroll info | unrolled by 4 |
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 | 1.17 |
CQA cycles if FP arith vectorized | 1.04 |
CQA cycles if fully vectorized | 0.19 |
Front-end cycles | 1.50 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.50 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.50 |
P4 cycles | 0.60 |
P5 cycles | 0.50 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.40 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.74 |
Stall cycles (UFS) | 0.00 |
Nb insns | 9.00 |
Nb uops | 8.00 |
Nb loads | 4.00 |
Nb stores | 1.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.33 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 1.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 26.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
Bytes stored | 8.00 |
Stride 0 | 1.00 |
Stride 1 | 2.00 |
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 | NA |
Vectorization ratio fma | 0.00 |
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 | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source file and lines | csr_matvec.c:564-567 |
Module | exec |
nb instructions | 9 |
nb uops | 8 |
loop length | 38 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.50 cycles |
front end | 1.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.50 | 1.33 | 1.33 | 0.50 | 0.60 | 0.50 | 0.50 | 0.50 | 0.50 | 0.40 | 1.33 |
cycles | 1.00 | 0.50 | 1.33 | 1.33 | 0.50 | 0.60 | 0.50 | 0.50 | 0.50 | 0.50 | 0.40 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.74 |
Stall cycles | 0.00 |
Front-end | 1.50 |
Dispatch | 1.33 |
Data deps. | 1.00 |
Overall L1 | 1.50 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 0% |
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 | 12% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%R15,%RSI,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%R12,%RDI,8),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R14,%RDI,8),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R13,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VFMADD213SD (%RBX,%RAX,8),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVSD %XMM1,(%RBX,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RDI,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 4df740 <hypre_CSRMatrixMatvecT.extracted.49+0x330> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_CSRMatrixMatvecT.extracted.49 |
Source file and lines | csr_matvec.c:564-567 |
Module | exec |
nb instructions | 9 |
nb uops | 8 |
loop length | 38 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.50 cycles |
front end | 1.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.50 | 1.33 | 1.33 | 0.50 | 0.60 | 0.50 | 0.50 | 0.50 | 0.50 | 0.40 | 1.33 |
cycles | 1.00 | 0.50 | 1.33 | 1.33 | 0.50 | 0.60 | 0.50 | 0.50 | 0.50 | 0.50 | 0.40 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.74 |
Stall cycles | 0.00 |
Front-end | 1.50 |
Dispatch | 1.33 |
Data deps. | 1.00 |
Overall L1 | 1.50 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 0% |
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 | 12% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%R15,%RSI,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%R12,%RDI,8),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R14,%RDI,8),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R13,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
VFMADD213SD (%RBX,%RAX,8),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVSD %XMM1,(%RBX,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RDI,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 4df740 <hypre_CSRMatrixMatvecT.extracted.49+0x330> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |