Loop Id: 3593 | Module: exec | Source: vector.c:449-452 | Coverage: 1.01% |
---|
Loop Id: 3593 | Module: exec | Source: vector.c:449-452 | Coverage: 1.01% |
---|
0x4f1eb0 VMOVSD -0x18(%R15,%RDI,1),%XMM1 [1] |
0x4f1eb7 VFMADD213SD -0x18(%R14,%RDI,1),%XMM0,%XMM1 [2] |
0x4f1ebe VMOVSD %XMM1,-0x18(%R14,%RDI,1) [2] |
0x4f1ec5 VMOVSD -0x10(%R15,%RDI,1),%XMM1 [1] |
0x4f1ecc VFMADD213SD -0x10(%R14,%RDI,1),%XMM0,%XMM1 [2] |
0x4f1ed3 VMOVSD %XMM1,-0x10(%R14,%RDI,1) [2] |
0x4f1eda VMOVSD -0x8(%R15,%RDI,1),%XMM1 [1] |
0x4f1ee1 VFMADD213SD -0x8(%R14,%RDI,1),%XMM0,%XMM1 [2] |
0x4f1ee8 VMOVSD %XMM1,-0x8(%R14,%RDI,1) [2] |
0x4f1eef VMOVSD (%R15,%RDI,1),%XMM1 [1] |
0x4f1ef5 VFMADD213SD (%R14,%RDI,1),%XMM0,%XMM1 [2] |
0x4f1efb VMOVSD %XMM1,(%R14,%RDI,1) [2] |
0x4f1f01 ADD $0x20,%RDI |
0x4f1f05 DEC %RSI |
0x4f1f08 JNE 4f1eb0 |
/scratch_na/users/xoserete/qaas_runs/171-172-8218/intel/AMG/build/AMG/AMG/seq_mv/vector.c: 449 - 452 |
-------------------------------------------------------------------------------- |
449: #pragma omp parallel for private(i) HYPRE_SMP_SCHEDULE |
450: #endif |
451: for (i = 0; i < size; i++) |
452: y_data[i] += alpha * x_data[i]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.06 |
CQA speedup if FP arith vectorized | 1.12 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.12 |
Bottlenecks | micro-operation queue, |
Function | hypre_SeqVectorAxpy.extracted |
Source | vector.c:449-452 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 3.00 |
CQA cycles if no scalar integer | 2.83 |
CQA cycles if FP arith vectorized | 2.67 |
CQA cycles if fully vectorized | 0.38 |
Front-end cycles | 3.00 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 2.00 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 2.00 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 0.00 |
P10 cycles | 2.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 3.16 |
Stall cycles (UFS) | 0.00 |
Nb insns | 15.00 |
Nb uops | 14.00 |
Nb loads | 8.00 |
Nb stores | 4.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.67 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 4.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 32.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 32.00 |
Stride 0 | 0.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
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 | 1.06 |
CQA speedup if FP arith vectorized | 1.12 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.12 |
Bottlenecks | micro-operation queue, |
Function | hypre_SeqVectorAxpy.extracted |
Source | vector.c:449-452 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 3.00 |
CQA cycles if no scalar integer | 2.83 |
CQA cycles if FP arith vectorized | 2.67 |
CQA cycles if fully vectorized | 0.38 |
Front-end cycles | 3.00 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 2.00 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 2.00 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 0.00 |
P10 cycles | 2.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 3.16 |
Stall cycles (UFS) | 0.00 |
Nb insns | 15.00 |
Nb uops | 14.00 |
Nb loads | 8.00 |
Nb stores | 4.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.67 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 4.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 32.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 32.00 |
Stride 0 | 0.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
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_SeqVectorAxpy.extracted |
Source file and lines | vector.c:449-452 |
Module | exec |
nb instructions | 15 |
nb uops | 14 |
loop length | 90 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.00 cycles |
front end | 3.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 2.67 | 2.67 | 2.00 | 0.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 2.67 |
cycles | 2.00 | 2.00 | 2.67 | 2.67 | 2.00 | 0.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 2.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 3.16 |
Stall cycles | 0.00 |
Front-end | 3.00 |
Dispatch | 2.67 |
Data deps. | 1.00 |
Overall L1 | 3.00 |
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 -0x18(%R15,%RDI,1),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD -0x18(%R14,%RDI,1),%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,-0x18(%R14,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD -0x10(%R15,%RDI,1),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD -0x10(%R14,%RDI,1),%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,-0x10(%R14,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD -0x8(%R15,%RDI,1),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD -0x8(%R14,%RDI,1),%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,-0x8(%R14,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R15,%RDI,1),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD (%R14,%RDI,1),%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,(%R14,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x20,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 4f1eb0 <hypre_SeqVectorAxpy.extracted+0xe0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_SeqVectorAxpy.extracted |
Source file and lines | vector.c:449-452 |
Module | exec |
nb instructions | 15 |
nb uops | 14 |
loop length | 90 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.00 cycles |
front end | 3.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 2.67 | 2.67 | 2.00 | 0.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 2.67 |
cycles | 2.00 | 2.00 | 2.67 | 2.67 | 2.00 | 0.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 2.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 3.16 |
Stall cycles | 0.00 |
Front-end | 3.00 |
Dispatch | 2.67 |
Data deps. | 1.00 |
Overall L1 | 3.00 |
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 -0x18(%R15,%RDI,1),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD -0x18(%R14,%RDI,1),%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,-0x18(%R14,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD -0x10(%R15,%RDI,1),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD -0x10(%R14,%RDI,1),%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,-0x10(%R14,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD -0x8(%R15,%RDI,1),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD -0x8(%R14,%RDI,1),%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,-0x8(%R14,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R15,%RDI,1),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD (%R14,%RDI,1),%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,(%R14,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x20,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 4f1eb0 <hypre_SeqVectorAxpy.extracted+0xe0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |