Loop Id: 4165 | Module: exec | Source: csr_matop.c:286-298 | Coverage: 0.32% |
---|
Loop Id: 4165 | Module: exec | Source: csr_matop.c:286-298 | Coverage: 0.32% |
---|
0x4d98a0 VADDSD (%R8,%R11,8),%XMM1,%XMM1 [2] |
0x4d98a6 VMOVSD %XMM1,(%R8,%R11,8) [2] |
0x4d98ac INC %RDI |
0x4d98af CMP %R9,%RDI |
0x4d98b2 JGE 4d9860 |
0x4d98b4 MOV (%R15,%RDI,8),%R10 [7] |
0x4d98b8 MOV (%R12,%R10,8),%R11 [9] |
0x4d98bc VMULSD (%RBX,%RDI,8),%XMM0,%XMM1 [5] |
0x4d98c1 CMP %RCX,%R11 |
0x4d98c4 JGE 4d98a0 |
0x4d98c6 LEA (%R12,%R10,8),%R9 |
0x4d98ca MOV %RAX,(%R9) [1] |
0x4d98cd MOV -0x70(%RBP),%R11 [8] |
0x4d98d1 MOV (%R11),%R11 [10] |
0x4d98d4 MOV %R10,(%R11,%RAX,8) [6] |
0x4d98d8 MOV (%R9),%R9 [1] |
0x4d98db VMOVSD %XMM1,(%R8,%R9,8) [3] |
0x4d98e1 INC %RAX |
0x4d98e4 MOV 0x8(%R14,%RSI,8),%R9 [4] |
0x4d98e9 INC %RDI |
0x4d98ec CMP %R9,%RDI |
0x4d98ef JL 4d98b4 |
/scratch_na/users/xoserete/qaas_runs/171-415-3872/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c: 286 - 298 |
-------------------------------------------------------------------------------- |
286: for (ib = B_i[ja]; ib < B_i[ja+1]; ib++) |
287: { |
288: jb = B_j[ib]; |
289: b_entry = B_data[ib]; |
290: if (B_marker[jb] < row_start) |
291: { |
292: B_marker[jb] = counter; |
293: C_j[B_marker[jb]] = jb; |
294: C_data[B_marker[jb]] = a_entry*b_entry; |
295: counter++; |
296: } |
297: else |
298: C_data[B_marker[jb]] += a_entry*b_entry; |
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 | 1.56 |
CQA speedup if FP arith vectorized | 2.07 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.22 |
Bottlenecks | |
Function | hypre_CSRMatrixMultiply.extracted |
Source | csr_matop.c:286-298 |
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 | 2.33 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.13 |
CQA cycles if fully vectorized | 0.29 |
Front-end cycles | 2.33 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 0.75 |
P1 cycles | 1.83 |
P2 cycles | 1.83 |
P3 cycles | 1.00 |
P4 cycles | 0.65 |
P5 cycles | 1.00 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.60 |
P10 cycles | 1.83 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.56 |
Stall cycles (UFS) | 0.00 |
Nb insns | 13.50 |
Nb uops | 12.50 |
Nb loads | 5.50 |
Nb stores | 2.00 |
Nb stack references | 0.50 |
FLOP/cycle | 0.64 |
Nb FLOP add-sub | 0.50 |
Nb FLOP mul | 1.00 |
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 | 25.03 |
Bytes prefetched | 0.00 |
Bytes loaded | 44.00 |
Bytes stored | 16.00 |
Stride 0 | 1.00 |
Stride 1 | 2.50 |
Stride n | 0.00 |
Stride unknown | 1.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.89 |
CQA speedup if FP arith vectorized | 1.89 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.21 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMultiply.extracted |
Source | csr_matop.c:286-298 |
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 | 2.83 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.35 |
Front-end cycles | 2.83 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 0.50 |
P1 cycles | 2.33 |
P2 cycles | 2.33 |
P3 cycles | 1.50 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 0.40 |
P10 cycles | 2.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 3.01 |
Stall cycles (UFS) | 0.00 |
Nb insns | 17.00 |
Nb uops | 16.00 |
Nb loads | 7.00 |
Nb stores | 3.00 |
Nb stack references | 1.00 |
FLOP/cycle | 0.35 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 1.00 |
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 | 28.24 |
Bytes prefetched | 0.00 |
Bytes loaded | 56.00 |
Bytes stored | 24.00 |
Stride 0 | 2.00 |
Stride 1 | 3.00 |
Stride n | 0.00 |
Stride unknown | 2.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.22 |
CQA speedup if FP arith vectorized | 2.44 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.22 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMultiply.extracted |
Source | csr_matop.c:286-298 |
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 | 1.83 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 0.75 |
CQA cycles if fully vectorized | 0.23 |
Front-end cycles | 1.83 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.50 |
P4 cycles | 0.70 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.80 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.11 |
Stall cycles (UFS) | 0.00 |
Nb insns | 10.00 |
Nb uops | 9.00 |
Nb loads | 4.00 |
Nb stores | 1.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.09 |
Nb FLOP add-sub | 1.00 |
Nb FLOP mul | 1.00 |
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 | 21.82 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
Bytes stored | 8.00 |
Stride 0 | 0.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Path / |
Function | hypre_CSRMatrixMultiply.extracted |
Source file and lines | csr_matop.c:286-298 |
Module | exec |
nb instructions | 13.50 |
nb uops | 12.50 |
loop length | 49.50 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0.50 |
micro-operation queue | 2.33 cycles |
front end | 2.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 0.75 | 1.83 | 1.83 | 1.00 | 0.65 | 1.00 | 1.00 | 1.00 | 1.00 | 0.60 | 1.83 |
cycles | 1.50 | 0.75 | 1.83 | 1.83 | 1.00 | 0.65 | 1.00 | 1.00 | 1.00 | 1.00 | 0.60 | 1.83 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.56 |
Stall cycles | 0.00 |
LM full (events) | 0.01 |
Front-end | 2.33 |
Dispatch | 1.92 |
Data deps. | 1.00 |
Overall L1 | 2.33 |
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) |
other | 0% |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
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 | 0% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
load | NA (no load vectorizable/vectorized instructions) |
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) |
other | 12% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
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) |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Function | hypre_CSRMatrixMultiply.extracted |
Source file and lines | csr_matop.c:286-298 |
Module | exec |
nb instructions | 17 |
nb uops | 16 |
loop length | 61 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 2.83 cycles |
front end | 2.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 0.50 | 2.33 | 2.33 | 1.50 | 0.60 | 1.00 | 1.50 | 1.50 | 1.50 | 0.40 | 2.33 |
cycles | 1.50 | 0.50 | 2.33 | 2.33 | 1.50 | 0.60 | 1.00 | 1.50 | 1.50 | 1.50 | 0.40 | 2.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 3.01 |
Stall cycles | 0.00 |
Front-end | 2.83 |
Dispatch | 2.33 |
Data deps. | 1.00 |
Overall L1 | 2.83 |
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) |
other | 0% |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
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 | 0% |
load | 0% |
store | 0% |
mul | 0% |
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 | 0% |
all | 12% |
load | NA (no load vectorizable/vectorized instructions) |
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) |
other | 12% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
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 | 12% |
load | 12% |
store | 12% |
mul | 12% |
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 | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R15,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R12,%R10,8),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMULSD (%RBX,%RDI,8),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
CMP %RCX,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JGE 4d98a0 <hypre_CSRMatrixMultiply.extracted+0x520> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA (%R12,%R10,8),%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %RAX,(%R9) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x70(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R11),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R10,(%R11,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV (%R9),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM1,(%R8,%R9,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x8(%R14,%RSI,8),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INC %RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R9,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JL 4d98b4 <hypre_CSRMatrixMultiply.extracted+0x534> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_CSRMatrixMultiply.extracted |
Source file and lines | csr_matop.c:286-298 |
Module | exec |
nb instructions | 10 |
nb uops | 9 |
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 |
ADD-SUB / MUL ratio | 1.00 |
micro-operation queue | 1.83 cycles |
front end | 1.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 1.33 | 1.33 | 0.50 | 0.70 | 1.00 | 0.50 | 0.50 | 0.50 | 0.80 | 1.33 |
cycles | 1.50 | 1.00 | 1.33 | 1.33 | 0.50 | 0.70 | 1.00 | 0.50 | 0.50 | 0.50 | 0.80 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.11 |
Stall cycles | 0.00 |
LM full (events) | 0.02 |
Front-end | 1.83 |
Dispatch | 1.50 |
Data deps. | 1.00 |
Overall L1 | 1.83 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
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 | 0% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
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) |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VADDSD (%R8,%R11,8),%XMM1,%XMM1 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVSD %XMM1,(%R8,%R11,8) | 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 %R9,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JGE 4d9860 <hypre_CSRMatrixMultiply.extracted+0x4e0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%R15,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R12,%R10,8),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMULSD (%RBX,%RDI,8),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
CMP %RCX,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JGE 4d98a0 <hypre_CSRMatrixMultiply.extracted+0x520> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |