Loop Id: 3593 | Module: exec | Source: par_csr_matop.c:970-989 [...] | Coverage: 0.01% |
---|
Loop Id: 3593 | Module: exec | Source: par_csr_matop.c:970-989 [...] | Coverage: 0.01% |
---|
0x4bd880 VADDSD (%R13,%R15,8),%XMM1,%XMM1 [5] |
0x4bd887 VMOVSD %XMM1,(%R13,%R15,8) [5] |
0x4bd88e INC %R8 |
0x4bd891 CMP %R9,%R8 |
0x4bd894 JGE 4bd7a0 |
0x4bd89a MOV -0xf8(%RBP),%R10 [8] |
0x4bd8a1 MOV (%R10,%R8,8),%R10 [3] |
0x4bd8a5 MOV -0x100(%RBP),%R11 [8] |
0x4bd8ac MOV (%R11,%R10,8),%R10 [1] |
0x4bd8b0 MOV -0x48(%RBP),%R11 [8] |
0x4bd8b4 ADD %R10,%R11 |
0x4bd8b7 MOV (%RDI,%R11,8),%R15 [4] |
0x4bd8bb VMULSD (%R14,%R8,8),%XMM0,%XMM1 [6] |
0x4bd8c1 CMP -0x30(%RBP),%R15 [8] |
0x4bd8c5 JGE 4bd880 |
0x4bd8c7 MOV %RCX,(%RDI,%R11,8) [4] |
0x4bd8cb VMOVSD %XMM1,(%R13,%RCX,8) [7] |
0x4bd8d2 MOV %R10,(%RDX,%RCX,8) [9] |
0x4bd8d6 INC %RCX |
0x4bd8d9 MOV -0x78(%RBP),%R9 [8] |
0x4bd8dd MOV 0x8(%R9,%RSI,8),%R9 [2] |
0x4bd8e2 INC %R8 |
0x4bd8e5 CMP %R9,%R8 |
0x4bd8e8 JL 4bd89a |
/scratch_na/users/xoserete/qaas_runs/171-415-3872/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 970 - 989 |
-------------------------------------------------------------------------------- |
970: for (jj3 = B_offd_i[i2]; jj3 < B_offd_i[i2+1]; jj3++) |
971: { |
972: i3 = num_cols_diag_B+map_B_to_C[B_offd_j[jj3]]; |
[...] |
980: if (B_marker[i3] < jj_row_begin_offd) |
981: { |
982: B_marker[i3] = jj_count_offd; |
983: C_offd_data[jj_count_offd] = a_entry*B_offd_data[jj3]; |
984: C_offd_j[jj_count_offd] = i3-num_cols_diag_B; |
985: jj_count_offd++; |
986: } |
987: else |
988: { |
989: C_offd_data[B_marker[i3]] += a_entry*B_offd_data[jj3]; |
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 | 2.11 |
CQA speedup if FP arith vectorized | 2.58 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.09 |
Bottlenecks | |
Function | hypre_ParMatmul.extracted.12 |
Source | par_csr_matop.c:970-972,par_csr_matop.c:980-989 |
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 | 3.17 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.23 |
CQA cycles if fully vectorized | 0.40 |
Front-end cycles | 2.92 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.05 |
P1 cycles | 3.17 |
P2 cycles | 3.17 |
P3 cycles | 1.00 |
P4 cycles | 0.95 |
P5 cycles | 1.10 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.90 |
P10 cycles | 3.17 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 4.33 |
Stall cycles (UFS) | 1.21 |
Nb insns | 17.00 |
Nb uops | 16.00 |
Nb loads | 9.50 |
Nb stores | 2.00 |
Nb stack references | 4.50 |
FLOP/cycle | 0.47 |
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 | 28.93 |
Bytes prefetched | 0.00 |
Bytes loaded | 76.00 |
Bytes stored | 16.00 |
Stride 0 | 1.00 |
Stride 1 | 3.00 |
Stride n | 0.00 |
Stride unknown | 2.00 |
Stride indirect | 1.00 |
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 | 2.22 |
CQA speedup if FP arith vectorized | 2.22 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.05 |
Bottlenecks | P2, P3, P11, |
Function | hypre_ParMatmul.extracted.12 |
Source | par_csr_matop.c:970-972,par_csr_matop.c:980-989 |
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 | 3.33 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.42 |
Front-end cycles | 3.17 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 0.90 |
P1 cycles | 3.33 |
P2 cycles | 3.33 |
P3 cycles | 1.50 |
P4 cycles | 0.80 |
P5 cycles | 1.00 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 0.80 |
P10 cycles | 3.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 4.28 |
Stall cycles (UFS) | 0.91 |
Nb insns | 19.00 |
Nb uops | 18.00 |
Nb loads | 10.00 |
Nb stores | 3.00 |
Nb stack references | 5.00 |
FLOP/cycle | 0.30 |
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 | 31.20 |
Bytes prefetched | 0.00 |
Bytes loaded | 80.00 |
Bytes stored | 24.00 |
Stride 0 | 1.00 |
Stride 1 | 4.00 |
Stride n | 0.00 |
Stride unknown | 2.00 |
Stride indirect | 1.00 |
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 | 2.00 |
CQA speedup if FP arith vectorized | 3.13 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.12 |
Bottlenecks | P2, P3, P11, |
Function | hypre_ParMatmul.extracted.12 |
Source | par_csr_matop.c:970-972,par_csr_matop.c:980-989 |
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 | 3.00 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 0.96 |
CQA cycles if fully vectorized | 0.38 |
Front-end cycles | 2.67 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.20 |
P1 cycles | 3.00 |
P2 cycles | 3.00 |
P3 cycles | 0.50 |
P4 cycles | 1.10 |
P5 cycles | 1.20 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 1.00 |
P10 cycles | 3.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 4.39 |
Stall cycles (UFS) | 1.52 |
Nb insns | 15.00 |
Nb uops | 14.00 |
Nb loads | 9.00 |
Nb stores | 1.00 |
Nb stack references | 4.00 |
FLOP/cycle | 0.67 |
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 | 26.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 72.00 |
Bytes stored | 8.00 |
Stride 0 | 1.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 2.00 |
Stride indirect | 1.00 |
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_ParMatmul.extracted.12 |
Source file and lines | par_csr_matop.c:970-989 |
Module | exec |
nb instructions | 17 |
nb uops | 16 |
loop length | 75.50 |
used x86 registers | 10.50 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 4.50 |
micro-operation queue | 2.92 cycles |
front end | 2.92 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.05 | 3.17 | 3.17 | 1.00 | 0.95 | 1.10 | 1.00 | 1.00 | 1.00 | 0.90 | 3.17 |
cycles | 1.50 | 1.05 | 3.17 | 3.17 | 1.00 | 0.95 | 1.10 | 1.00 | 1.00 | 1.00 | 0.90 | 3.17 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 4.33 |
Stall cycles | 1.21 |
LM full (events) | 2.53 |
Front-end | 2.92 |
Dispatch | 3.17 |
Data deps. | 1.00 |
Overall L1 | 3.17 |
all | 0% |
load | 0% |
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 | 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) |
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_ParMatmul.extracted.12 |
Source file and lines | par_csr_matop.c:970-989 |
Module | exec |
nb instructions | 19 |
nb uops | 18 |
loop length | 80 |
used x86 registers | 12 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 3.17 cycles |
front end | 3.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 0.90 | 3.33 | 3.33 | 1.50 | 0.80 | 1.00 | 1.50 | 1.50 | 1.50 | 0.80 | 3.33 |
cycles | 1.50 | 0.90 | 3.33 | 3.33 | 1.50 | 0.80 | 1.00 | 1.50 | 1.50 | 1.50 | 0.80 | 3.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 4.28 |
Stall cycles | 0.91 |
LM full (events) | 2.06 |
Front-end | 3.17 |
Dispatch | 3.33 |
Data deps. | 1.00 |
Overall L1 | 3.33 |
all | 0% |
load | 0% |
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 | 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) |
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 -0xf8(%RBP),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R10,%R8,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x100(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R11,%R10,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x48(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R10,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV (%RDI,%R11,8),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMULSD (%R14,%R8,8),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
CMP -0x30(%RBP),%R15 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JGE 4bd880 <hypre_ParMatmul.extracted.12+0x520> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %RCX,(%RDI,%R11,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD %XMM1,(%R13,%RCX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R10,(%RDX,%RCX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x78(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%R9,%RSI,8),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INC %R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R9,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JL 4bd89a <hypre_ParMatmul.extracted.12+0x53a> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_ParMatmul.extracted.12 |
Source file and lines | par_csr_matop.c:970-989 |
Module | exec |
nb instructions | 15 |
nb uops | 14 |
loop length | 71 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 4 |
ADD-SUB / MUL ratio | 1.00 |
micro-operation queue | 2.67 cycles |
front end | 2.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.20 | 3.00 | 3.00 | 0.50 | 1.10 | 1.20 | 0.50 | 0.50 | 0.50 | 1.00 | 3.00 |
cycles | 1.50 | 1.20 | 3.00 | 3.00 | 0.50 | 1.10 | 1.20 | 0.50 | 0.50 | 0.50 | 1.00 | 3.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 4.39 |
Stall cycles | 1.52 |
LM full (events) | 2.99 |
Front-end | 2.67 |
Dispatch | 3.00 |
Data deps. | 1.00 |
Overall L1 | 3.00 |
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 (%R13,%R15,8),%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,(%R13,%R15,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R9,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JGE 4bd7a0 <hypre_ParMatmul.extracted.12+0x440> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0xf8(%RBP),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R10,%R8,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x100(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R11,%R10,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x48(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %R10,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV (%RDI,%R11,8),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMULSD (%R14,%R8,8),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
CMP -0x30(%RBP),%R15 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JGE 4bd880 <hypre_ParMatmul.extracted.12+0x520> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |