Loop Id: 3172 | Module: exec | Source: par_csr_matop.c:937-989 [...] | Coverage: 0.28% |
---|
Loop Id: 3172 | Module: exec | Source: par_csr_matop.c:937-989 [...] | Coverage: 0.28% |
---|
0x4aa9b0 INC %RDX |
0x4aa9b3 MOV -0x60(%RBP),%RSI |
0x4aa9b7 MOV -0x38(%RBP),%R12 |
0x4aa9bb CMP (%RSI,%R12,8),%RDX |
0x4aa9bf JGE 4aa7b0 |
0x4aa9c5 MOV -0xe0(%RBP),%RSI |
0x4aa9cc MOV (%RSI,%RDX,8),%RSI |
0x4aa9d0 MOV -0xd8(%RBP),%R8 |
0x4aa9d7 VMOVSD (%R8,%RDX,8),%XMM0 |
0x4aa9dd MOV -0x80(%RBP),%R9 |
0x4aa9e1 MOV (%R9,%RSI,8),%R8 |
0x4aa9e5 MOV 0x8(%R9,%RSI,8),%R9 |
0x4aa9ea CMP %R9,%R8 |
0x4aa9ed JL 4aaa33 |
0x4aa9ef JMP 4aaa68 |
(3174) 0x4aaa00 MOV %RAX,(%RDI,%R10,8) |
(3174) 0x4aaa04 MOV -0xa8(%RBP),%R9 |
(3174) 0x4aaa0b VMULSD (%R9,%R8,8),%XMM0,%XMM1 |
(3174) 0x4aaa11 VMOVSD %XMM1,(%R15,%RAX,8) |
(3174) 0x4aaa17 MOV -0x50(%RBP),%R9 |
(3174) 0x4aaa1b MOV %R10,(%R9,%RAX,8) |
(3174) 0x4aaa1f INC %RAX |
(3174) 0x4aaa22 MOV -0x80(%RBP),%R9 |
(3174) 0x4aaa26 MOV 0x8(%R9,%RSI,8),%R9 |
(3174) 0x4aaa2b INC %R8 |
(3174) 0x4aaa2e CMP %R9,%R8 |
(3174) 0x4aaa31 JGE 4aaa68 |
(3174) 0x4aaa33 MOV -0x108(%RBP),%R10 |
(3174) 0x4aaa3a MOV (%R10,%R8,8),%R10 |
(3174) 0x4aaa3e MOV (%RDI,%R10,8),%R11 |
(3174) 0x4aaa42 CMP %R14,%R11 |
(3174) 0x4aaa45 JL 4aaa00 |
(3174) 0x4aaa47 MOV -0xa8(%RBP),%R10 |
(3174) 0x4aaa4e VMOVSD (%R10,%R8,8),%XMM1 |
(3174) 0x4aaa54 VFMADD213SD (%R15,%R11,8),%XMM0,%XMM1 |
(3174) 0x4aaa5a VMOVSD %XMM1,(%R15,%R11,8) |
(3174) 0x4aaa60 INC %R8 |
(3174) 0x4aaa63 CMP %R9,%R8 |
(3174) 0x4aaa66 JL 4aaa33 |
0x4aaa68 CMPQ $0,-0xd0(%RBP) |
0x4aaa70 JE 4aa9b0 |
0x4aaa76 MOV -0x68(%RBP),%R9 |
0x4aaa7a MOV (%R9,%RSI,8),%R8 |
0x4aaa7e MOV 0x8(%R9,%RSI,8),%R9 |
0x4aaa83 JMP 4aaaaf |
(3173) 0x4aaa90 MOV -0x88(%RBP),%R10 |
(3173) 0x4aaa97 VMOVSD (%R10,%R8,8),%XMM1 |
(3173) 0x4aaa9d VFMADD213SD (%RBX,%R11,8),%XMM0,%XMM1 |
(3173) 0x4aaaa3 VMOVSD %XMM1,(%RBX,%R11,8) |
(3173) 0x4aaaa9 MOV %R12,%R13 |
(3173) 0x4aaaac INC %R8 |
(3173) 0x4aaaaf CMP %R9,%R8 |
(3173) 0x4aaab2 JGE 4aa9b0 |
(3173) 0x4aaab8 MOV -0xe8(%RBP),%R10 |
(3173) 0x4aaabf MOV (%R10,%R8,8),%R10 |
(3173) 0x4aaac3 MOV -0xf0(%RBP),%R11 |
(3173) 0x4aaaca MOV (%R11,%R10,8),%R10 |
(3173) 0x4aaace MOV %R13,%R12 |
(3173) 0x4aaad1 ADD %R10,%R13 |
(3173) 0x4aaad4 MOV (%RDI,%R13,8),%R11 |
(3173) 0x4aaad8 CMP -0x30(%RBP),%R11 |
(3173) 0x4aaadc JGE 4aaa90 |
(3173) 0x4aaade MOV %RCX,(%RDI,%R13,8) |
(3173) 0x4aaae2 MOV -0x88(%RBP),%R9 |
(3173) 0x4aaae9 VMULSD (%R9,%R8,8),%XMM0,%XMM1 |
(3173) 0x4aaaef VMOVSD %XMM1,(%RBX,%RCX,8) |
(3173) 0x4aaaf4 MOV -0x90(%RBP),%R9 |
(3173) 0x4aaafb MOV %R10,(%R9,%RCX,8) |
(3173) 0x4aaaff INC %RCX |
(3173) 0x4aab02 MOV -0x68(%RBP),%R9 |
(3173) 0x4aab06 MOV 0x8(%R9,%RSI,8),%R9 |
(3173) 0x4aab0b JMP 4aaaa9 |
/home/eoseret/qaas_runs_CPU_9468/171-586-9096/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 937 - 989 |
-------------------------------------------------------------------------------- |
937: for (jj2 = A_diag_i[i1]; jj2 < A_diag_i[i1+1]; jj2++) |
938: { |
939: i2 = A_diag_j[jj2]; |
940: a_entry = A_diag_data[jj2]; |
[...] |
946: for (jj3 = B_diag_i[i2]; jj3 < B_diag_i[i2+1]; jj3++) |
947: { |
948: i3 = B_diag_j[jj3]; |
[...] |
956: if (B_marker[i3] < jj_row_begin_diag) |
957: { |
958: B_marker[i3] = jj_count_diag; |
959: C_diag_data[jj_count_diag] = a_entry*B_diag_data[jj3]; |
960: C_diag_j[jj_count_diag] = i3; |
961: jj_count_diag++; |
962: } |
963: else |
964: { |
965: C_diag_data[B_marker[i3]] += a_entry*B_diag_data[jj3]; |
966: } |
967: } |
968: if (num_cols_offd_B) |
969: { |
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]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.11 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.27 |
Bottlenecks | P2, P3, P11, |
Function | hypre_ParMatmul.extracted.12 |
Source | par_csr_matop.c:937-940,par_csr_matop.c:946-946,par_csr_matop.c:968-970 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.67 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 4.67 |
CQA cycles if fully vectorized | 0.58 |
Front-end cycles | 3.67 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 4.67 |
P2 cycles | 4.67 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 1.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 1.00 |
P10 cycles | 4.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 5.76 |
Stall cycles (UFS) | 1.98 |
Nb insns | 21.00 |
Nb uops | 21.00 |
Nb loads | 14.00 |
Nb stores | 0.00 |
Nb stack references | 7.00 |
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 | 112.00 |
Bytes stored | 0.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
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 | NA |
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 | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.11 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.27 |
Bottlenecks | P2, P3, P11, |
Function | hypre_ParMatmul.extracted.12 |
Source | par_csr_matop.c:937-940,par_csr_matop.c:946-946,par_csr_matop.c:968-970 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.67 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 4.67 |
CQA cycles if fully vectorized | 0.58 |
Front-end cycles | 3.67 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 4.67 |
P2 cycles | 4.67 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 1.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 1.00 |
P10 cycles | 4.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 5.76 |
Stall cycles (UFS) | 1.98 |
Nb insns | 21.00 |
Nb uops | 21.00 |
Nb loads | 14.00 |
Nb stores | 0.00 |
Nb stack references | 7.00 |
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 | 112.00 |
Bytes stored | 0.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
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 | NA |
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 | 12.50 |
Path / |
Function | hypre_ParMatmul.extracted.12 |
Source file and lines | par_csr_matop.c:937-989 |
Module | exec |
nb instructions | 21 |
nb uops | 21 |
loop length | 94 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 3.67 cycles |
front end | 3.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 4.67 | 4.67 | 0.00 | 1.00 | 1.50 | 0.00 | 0.00 | 0.00 | 1.00 | 4.67 |
cycles | 1.50 | 1.00 | 4.67 | 4.67 | 0.00 | 1.00 | 1.50 | 0.00 | 0.00 | 0.00 | 1.00 | 4.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 5.76 |
Stall cycles | 1.98 |
LM full (events) | 4.20 |
Front-end | 3.67 |
Dispatch | 4.67 |
Overall L1 | 4.67 |
all | 0% |
load | 0% |
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 | 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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
load | 12% |
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 | 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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
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) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x60(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x38(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RSI,%R12,8),%RDX | 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 4aa7b0 <hypre_ParMatmul.extracted.12+0x220> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0xe0(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RDX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0xd8(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%R8,%RDX,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x80(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9,%RSI,8),%R8 | 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 |
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 4aaa33 <hypre_ParMatmul.extracted.12+0x4a3> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 4aaa68 <hypre_ParMatmul.extracted.12+0x4d8> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
CMPQ $0,-0xd0(%RBP) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 4aa9b0 <hypre_ParMatmul.extracted.12+0x420> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x68(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9,%RSI,8),%R8 | 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 |
JMP 4aaaaf <hypre_ParMatmul.extracted.12+0x51f> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
Function | hypre_ParMatmul.extracted.12 |
Source file and lines | par_csr_matop.c:937-989 |
Module | exec |
nb instructions | 21 |
nb uops | 21 |
loop length | 94 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 3.67 cycles |
front end | 3.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 4.67 | 4.67 | 0.00 | 1.00 | 1.50 | 0.00 | 0.00 | 0.00 | 1.00 | 4.67 |
cycles | 1.50 | 1.00 | 4.67 | 4.67 | 0.00 | 1.00 | 1.50 | 0.00 | 0.00 | 0.00 | 1.00 | 4.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 5.76 |
Stall cycles | 1.98 |
LM full (events) | 4.20 |
Front-end | 3.67 |
Dispatch | 4.67 |
Overall L1 | 4.67 |
all | 0% |
load | 0% |
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 | 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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
load | 12% |
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 | 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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
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) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x60(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x38(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RSI,%R12,8),%RDX | 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 4aa7b0 <hypre_ParMatmul.extracted.12+0x220> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0xe0(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RDX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0xd8(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%R8,%RDX,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x80(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9,%RSI,8),%R8 | 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 |
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 4aaa33 <hypre_ParMatmul.extracted.12+0x4a3> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 4aaa68 <hypre_ParMatmul.extracted.12+0x4d8> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
CMPQ $0,-0xd0(%RBP) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 4aa9b0 <hypre_ParMatmul.extracted.12+0x420> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x68(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9,%RSI,8),%R8 | 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 |
JMP 4aaaaf <hypre_ParMatmul.extracted.12+0x51f> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |