Loop Id: 18 | Module: libparcsr_mv.so | Source: par_csr_matop.c:865-989 [...] | Coverage: 0.03% |
---|
Loop Id: 18 | Module: libparcsr_mv.so | Source: par_csr_matop.c:865-989 [...] | Coverage: 0.03% |
---|
0x759d CMPQ $0,-0x118(%RBP) |
0x75a5 MOV -0x40(%RBP),%RSI |
0x75a9 MOV %R12,%RDX |
0x75ac JNE 76f5 |
0x75b2 MOV -0xb0(%RBP),%R11 |
0x75b9 MOV -0xa0(%RBP),%R14 |
0x75c0 MOV (%R11,%R14,8),%RDI |
0x75c4 CMP 0x8(%R11,%R14,8),%RDI |
0x75c9 JGE 7695 |
0x75cf MOV -0x128(%RBP),%R11 |
0x75d6 MOV -0x130(%RBP),%R13 |
0x75dd MOV %RSI,-0xa8(%RBP) |
0x75e4 MOV %RDI,-0x48(%RBP) |
0x75e8 NOPL (%RAX,%RAX,1) |
(23) 0x75f0 MOV -0x48(%RBP),%R9 |
(23) 0x75f4 MOV -0xc8(%RBP),%RCX |
(23) 0x75fb MOV -0xd0(%RBP),%RSI |
(23) 0x7602 MOV -0xc0(%RBP),%R10 |
(23) 0x7609 MOV (%RCX,%R9,8),%RDI |
(23) 0x760d VMOVSD (%RSI,%R9,8),%XMM7 |
(23) 0x7613 LEA 0x8(,%RDI,8),%R9 |
(23) 0x761b MOV (%R10,%RDI,8),%RAX |
(23) 0x761f LEA (%R10,%R9,1),%R14 |
(23) 0x7623 MOV (%R14),%R10 |
(23) 0x7626 CMP %R10,%RAX |
(23) 0x7629 JGE 765f |
(23) 0x762b NOPL (%RAX,%RAX,1) |
(25) 0x7630 MOV (%R11,%RAX,8),%RCX |
(25) 0x7634 VMULSD (%R13,%RAX,8),%XMM7,%XMM8 |
(25) 0x763b LEA (%R8,%RCX,8),%RSI |
(25) 0x763f MOV (%RSI),%R15 |
(25) 0x7642 CMP %R15,%R12 |
(25) 0x7645 JG 7830 |
(25) 0x764b LEA (%RBX,%R15,8),%RCX |
(25) 0x764f INC %RAX |
(25) 0x7652 VADDSD (%RCX),%XMM8,%XMM9 |
(25) 0x7656 VMOVSD %XMM9,(%RCX) |
(25) 0x765a CMP %R10,%RAX |
(25) 0x765d JL 7630 |
(23) 0x765f CMPQ $0,-0xb8(%RBP) |
(23) 0x7667 JNE 7860 |
(23) 0x766d INCQ -0x48(%RBP) |
(23) 0x7671 MOV -0xb0(%RBP),%R14 |
(23) 0x7678 MOV -0xa0(%RBP),%RSI |
(23) 0x767f MOV -0x48(%RBP),%RAX |
(23) 0x7683 CMP %RAX,0x8(%R14,%RSI,8) |
(23) 0x7688 JG 75f0 |
0x768e MOV -0xa8(%RBP),%RSI |
0x7695 INCQ -0xa0(%RBP) |
0x769c MOV -0xa0(%RBP),%R12 |
0x76a3 CMP %R12,-0x120(%RBP) |
0x76aa JE 797f |
0x76b0 CMPQ $0,-0x110(%RBP) |
0x76b8 MOV %RSI,-0x40(%RBP) |
0x76bc MOV %RDX,%R12 |
0x76bf JE 759d |
0x76f5 MOV -0xe0(%RBP),%R15 |
0x76fc MOV -0xa0(%RBP),%RAX |
0x7703 MOV (%R15,%RAX,8),%R14 |
0x7707 CMP 0x8(%R15,%RAX,8),%R14 |
0x770c JGE 75b2 |
0x7712 MOV %R12,-0x48(%RBP) |
0x7716 MOV -0x50(%RBP),%R11 |
0x771a MOV %R14,%RDI |
0x771d MOV -0x58(%RBP),%R12 |
0x7721 NOPL (%RAX) |
(19) 0x7728 MOV -0x100(%RBP),%R13 |
(19) 0x772f MOV -0xe8(%RBP),%R10 |
(19) 0x7736 MOV -0x108(%RBP),%RCX |
(19) 0x773d MOV (%R13,%RDI,8),%R14 |
(19) 0x7742 VMOVSD (%RCX,%RDI,8),%XMM2 |
(19) 0x7747 LEA 0x8(,%R14,8),%R13 |
(19) 0x774f MOV (%R10,%R14,8),%RAX |
(19) 0x7753 ADD %R13,%R10 |
(19) 0x7756 MOV %R10,-0xa8(%RBP) |
(19) 0x775d MOV (%R10),%R10 |
(19) 0x7760 CMP %R10,%RAX |
(19) 0x7763 JGE 77b1 |
(19) 0x7765 MOV %RDX,-0xd8(%RBP) |
(19) 0x776c NOPL (%RAX) |
(21) 0x7770 MOV -0x60(%RBP),%R9 |
(21) 0x7774 MOV (%R9,%RAX,8),%RCX |
(21) 0x7778 LEA (%R12,%RCX,1),%RDX |
(21) 0x777c LEA (%R8,%RDX,8),%R9 |
(21) 0x7780 MOV -0x68(%RBP),%RDX |
(21) 0x7784 MOV (%R9),%R15 |
(21) 0x7787 VMULSD (%RDX,%RAX,8),%XMM2,%XMM1 |
(21) 0x778c CMP %R15,-0x40(%RBP) |
(21) 0x7790 JG 7950 |
(21) 0x7796 LEA (%R11,%R15,8),%RCX |
(21) 0x779a INC %RAX |
(21) 0x779d VADDSD (%RCX),%XMM1,%XMM4 |
(21) 0x77a1 VMOVSD %XMM4,(%RCX) |
(21) 0x77a5 CMP %R10,%RAX |
(21) 0x77a8 JL 7770 |
(19) 0x77aa MOV -0xd8(%RBP),%RDX |
(19) 0x77b1 MOV -0xf0(%RBP),%RCX |
(19) 0x77b8 MOV (%RCX,%R14,8),%RAX |
(19) 0x77bc ADD %R13,%RCX |
(19) 0x77bf MOV (%RCX),%R13 |
(19) 0x77c2 MOV %RCX,%R15 |
(19) 0x77c5 CMP %R13,%RAX |
(19) 0x77c8 JGE 7807 |
(19) 0x77ca NOPW (%RAX,%RAX,1) |
(20) 0x77d0 MOV -0x70(%RBP),%R14 |
(20) 0x77d4 MOV -0x78(%RBP),%R9 |
(20) 0x77d8 MOV (%R14,%RAX,8),%RCX |
(20) 0x77dc VMULSD (%R9,%RAX,8),%XMM2,%XMM5 |
(20) 0x77e2 LEA (%R8,%RCX,8),%R10 |
(20) 0x77e6 MOV (%R10),%R14 |
(20) 0x77e9 CMP %R14,-0x48(%RBP) |
(20) 0x77ed JG 7920 |
(20) 0x77f3 LEA (%RBX,%R14,8),%RCX |
(20) 0x77f7 INC %RAX |
(20) 0x77fa VADDSD (%RCX),%XMM5,%XMM6 |
(20) 0x77fe VMOVSD %XMM6,(%RCX) |
(20) 0x7802 CMP %R13,%RAX |
(20) 0x7805 JL 77d0 |
(19) 0x7807 MOV -0xe0(%RBP),%RAX |
(19) 0x780e MOV -0xa0(%RBP),%R15 |
(19) 0x7815 INC %RDI |
(19) 0x7818 CMP %RDI,0x8(%RAX,%R15,8) |
(19) 0x781d JG 7728 |
0x7823 MOV -0x48(%RBP),%R12 |
0x7827 JMP 75b2 |
(25) 0x7830 MOV -0x38(%RBP),%R10 |
(25) 0x7834 MOV %RDX,(%RSI) |
(25) 0x7837 INC %RAX |
(25) 0x783a VMOVSD %XMM8,(%RBX,%RDX,8) |
(25) 0x783f MOV %RCX,(%R10,%RDX,8) |
(25) 0x7843 INC %RDX |
(25) 0x7846 MOV (%R14),%R10 |
(25) 0x7849 CMP %RAX,%R10 |
(25) 0x784c JG 7630 |
(23) 0x7852 CMPQ $0,-0xb8(%RBP) |
(23) 0x785a JE 766d |
(23) 0x7860 MOV -0xf8(%RBP),%R14 |
(23) 0x7867 MOV (%R14,%RDI,8),%RAX |
(23) 0x786b LEA (%R14,%R9,1),%R14 |
(23) 0x786f MOV (%R14),%R10 |
(23) 0x7872 CMP %R10,%RAX |
(23) 0x7875 JGE 766d |
(23) 0x787b MOV -0xa8(%RBP),%RSI |
(23) 0x7882 NOPW (%RAX,%RAX,1) |
(24) 0x7888 MOV -0x90(%RBP),%RDI |
(24) 0x788f MOV -0x88(%RBP),%R15 |
(24) 0x7896 MOV (%RDI,%RAX,8),%R9 |
(24) 0x789a MOV -0x58(%RBP),%RDI |
(24) 0x789e MOV (%R15,%R9,8),%RCX |
(24) 0x78a2 MOV -0x98(%RBP),%R15 |
(24) 0x78a9 VMULSD (%R15,%RAX,8),%XMM7,%XMM10 |
(24) 0x78af ADD %RCX,%RDI |
(24) 0x78b2 LEA (%R8,%RDI,8),%RDI |
(24) 0x78b6 MOV (%RDI),%R9 |
(24) 0x78b9 CMP %R9,-0x40(%RBP) |
(24) 0x78bd JG 78e8 |
(24) 0x78bf MOV -0x50(%RBP),%RCX |
(24) 0x78c3 INC %RAX |
(24) 0x78c6 LEA (%RCX,%R9,8),%RDI |
(24) 0x78ca VADDSD (%RDI),%XMM10,%XMM11 |
(24) 0x78ce VMOVSD %XMM11,(%RDI) |
(24) 0x78d2 CMP %R10,%RAX |
(24) 0x78d5 JL 7888 |
(23) 0x78d7 MOV %RSI,-0xa8(%RBP) |
(23) 0x78de JMP 766d |
(24) 0x78e8 MOV -0x50(%RBP),%R10 |
(24) 0x78ec MOV -0x80(%RBP),%R9 |
(24) 0x78f0 MOV %RSI,(%RDI) |
(24) 0x78f3 INC %RAX |
(24) 0x78f6 VMOVSD %XMM10,(%R10,%RSI,8) |
(24) 0x78fc MOV %RCX,(%R9,%RSI,8) |
(24) 0x7900 INC %RSI |
(24) 0x7903 MOV (%R14),%R10 |
(24) 0x7906 CMP %RAX,%R10 |
(24) 0x7909 JG 7888 |
(23) 0x790f MOV %RSI,-0xa8(%RBP) |
(23) 0x7916 JMP 766d |
(20) 0x7920 MOV -0x38(%RBP),%R13 |
(20) 0x7924 MOV %RDX,(%R10) |
(20) 0x7927 INC %RAX |
(20) 0x792a VMOVSD %XMM5,(%RBX,%RDX,8) |
(20) 0x792f MOV %RCX,(%R13,%RDX,8) |
(20) 0x7934 INC %RDX |
(20) 0x7937 MOV (%R15),%R13 |
(20) 0x793a CMP %RAX,%R13 |
(20) 0x793d JG 77d0 |
(19) 0x7943 JMP 7807 |
(21) 0x7950 MOV -0x80(%RBP),%R10 |
(21) 0x7954 MOV %RSI,(%R9) |
(21) 0x7957 INC %RAX |
(21) 0x795a VMOVSD %XMM1,(%R11,%RSI,8) |
(21) 0x7960 MOV -0xa8(%RBP),%R9 |
(21) 0x7967 MOV %RCX,(%R10,%RSI,8) |
(21) 0x796b INC %RSI |
(21) 0x796e MOV (%R9),%R10 |
(21) 0x7971 CMP %R10,%RAX |
(21) 0x7974 JL 7770 |
(19) 0x797a JMP 77aa |
/scratch_na/users/xoserete/qaas_runs/171-415-3872/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 865 - 989 |
-------------------------------------------------------------------------------- |
865: for (i1 = ns; i1 < ne; i1++) |
[...] |
874: if ( allsquare ) |
[...] |
886: if (num_cols_offd_A) |
887: { |
888: for (jj2 = A_offd_i[i1]; jj2 < A_offd_i[i1+1]; jj2++) |
889: { |
890: i2 = A_offd_j[jj2]; |
891: a_entry = A_offd_data[jj2]; |
[...] |
897: for (jj3 = B_ext_offd_i[i2]; jj3 < B_ext_offd_i[i2+1]; jj3++) |
898: { |
899: i3 = num_cols_diag_B+B_ext_offd_j[jj3]; |
[...] |
907: if (B_marker[i3] < jj_row_begin_offd) |
908: { |
909: B_marker[i3] = jj_count_offd; |
910: C_offd_data[jj_count_offd] = a_entry*B_ext_offd_data[jj3]; |
911: C_offd_j[jj_count_offd] = i3-num_cols_diag_B; |
912: jj_count_offd++; |
913: } |
914: else |
915: C_offd_data[B_marker[i3]] += a_entry*B_ext_offd_data[jj3]; |
916: } |
917: for (jj3 = B_ext_diag_i[i2]; jj3 < B_ext_diag_i[i2+1]; jj3++) |
918: { |
919: i3 = B_ext_diag_j[jj3]; |
920: if (B_marker[i3] < jj_row_begin_diag) |
921: { |
922: B_marker[i3] = jj_count_diag; |
923: C_diag_data[jj_count_diag] = a_entry*B_ext_diag_data[jj3]; |
924: C_diag_j[jj_count_diag] = i3; |
925: jj_count_diag++; |
926: } |
927: else |
928: C_diag_data[B_marker[i3]] += a_entry*B_ext_diag_data[jj3]; |
[...] |
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]; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
○99.07 | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
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 | 1.03 |
Bottlenecks | P2, P3, P11, |
Function | hypre_ParMatmul._omp_fn.3 |
Source | par_csr_matop.c:865-865,par_csr_matop.c:874-874,par_csr_matop.c:886-888,par_csr_matop.c:937-937 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 6.67 |
CQA cycles if no scalar integer | 6.67 |
CQA cycles if FP arith vectorized | 6.67 |
CQA cycles if fully vectorized | 0.83 |
Front-end cycles | 6.50 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.00 |
P1 cycles | 6.67 |
P2 cycles | 6.67 |
P3 cycles | 2.50 |
P4 cycles | 2.00 |
P5 cycles | 2.50 |
P6 cycles | 2.50 |
P7 cycles | 2.50 |
P8 cycles | 2.50 |
P9 cycles | 2.00 |
P10 cycles | 6.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.82 |
Stall cycles (UFS) | 0.16 |
Nb insns | 35.00 |
Nb uops | 37.00 |
Nb loads | 20.00 |
Nb stores | 5.00 |
Nb stack references | 13.00 |
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 | 30.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 160.00 |
Bytes stored | 40.00 |
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 | 0.00 |
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 | 12.50 |
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 | 1.00 |
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 | 1.03 |
Bottlenecks | P2, P3, P11, |
Function | hypre_ParMatmul._omp_fn.3 |
Source | par_csr_matop.c:865-865,par_csr_matop.c:874-874,par_csr_matop.c:886-888,par_csr_matop.c:937-937 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 6.67 |
CQA cycles if no scalar integer | 6.67 |
CQA cycles if FP arith vectorized | 6.67 |
CQA cycles if fully vectorized | 0.83 |
Front-end cycles | 6.50 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.00 |
P1 cycles | 6.67 |
P2 cycles | 6.67 |
P3 cycles | 2.50 |
P4 cycles | 2.00 |
P5 cycles | 2.50 |
P6 cycles | 2.50 |
P7 cycles | 2.50 |
P8 cycles | 2.50 |
P9 cycles | 2.00 |
P10 cycles | 6.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.82 |
Stall cycles (UFS) | 0.16 |
Nb insns | 35.00 |
Nb uops | 37.00 |
Nb loads | 20.00 |
Nb stores | 5.00 |
Nb stack references | 13.00 |
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 | 30.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 160.00 |
Bytes stored | 40.00 |
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 | 0.00 |
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 | 12.50 |
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._omp_fn.3 |
Source file and lines | par_csr_matop.c:865-989 |
Module | libparcsr_mv.so |
nb instructions | 35 |
nb uops | 37 |
loop length | 198 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 13 |
micro-operation queue | 6.50 cycles |
front end | 6.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.00 | 6.67 | 6.67 | 2.50 | 2.00 | 2.50 | 2.50 | 2.50 | 2.50 | 2.00 | 6.67 |
cycles | 2.50 | 2.00 | 6.67 | 6.67 | 2.50 | 2.00 | 2.50 | 2.50 | 2.50 | 2.50 | 2.00 | 6.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.82 |
Stall cycles | 0.16 |
LM full (events) | 0.98 |
Front-end | 6.50 |
Dispatch | 6.67 |
Overall L1 | 6.67 |
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) |
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) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
CMPQ $0,-0x118(%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 |
MOV -0x40(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 76f5 <hypre_ParMatmul._omp_fn.3+0x365> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0xb0(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0xa0(%RBP),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R11,%R14,8),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%R11,%R14,8),%RDI | 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 7695 <hypre_ParMatmul._omp_fn.3+0x305> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x128(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x130(%RBP),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RSI,-0xa8(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDI,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV -0xa8(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INCQ -0xa0(%RBP) | 3 | 0.20 | 0.20 | 0.33 | 0.33 | 0.50 | 0.20 | 0.20 | 0.50 | 0.50 | 0.50 | 0.20 | 0.33 | 1 | 0.50 |
MOV -0xa0(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %R12,-0x120(%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 797f <hypre_ParMatmul._omp_fn.3+0x5ef> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPQ $0,-0x110(%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 |
MOV %RSI,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 759d <hypre_ParMatmul._omp_fn.3+0x20d> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0xe0(%RBP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0xa0(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R15,%RAX,8),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%R15,%RAX,8),%R14 | 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 75b2 <hypre_ParMatmul._omp_fn.3+0x222> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R12,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x50(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x58(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV -0x48(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 75b2 <hypre_ParMatmul._omp_fn.3+0x222> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | hypre_ParMatmul._omp_fn.3 |
Source file and lines | par_csr_matop.c:865-989 |
Module | libparcsr_mv.so |
nb instructions | 35 |
nb uops | 37 |
loop length | 198 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 13 |
micro-operation queue | 6.50 cycles |
front end | 6.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.00 | 6.67 | 6.67 | 2.50 | 2.00 | 2.50 | 2.50 | 2.50 | 2.50 | 2.00 | 6.67 |
cycles | 2.50 | 2.00 | 6.67 | 6.67 | 2.50 | 2.00 | 2.50 | 2.50 | 2.50 | 2.50 | 2.00 | 6.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.82 |
Stall cycles | 0.16 |
LM full (events) | 0.98 |
Front-end | 6.50 |
Dispatch | 6.67 |
Overall L1 | 6.67 |
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) |
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) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
CMPQ $0,-0x118(%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 |
MOV -0x40(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 76f5 <hypre_ParMatmul._omp_fn.3+0x365> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0xb0(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0xa0(%RBP),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R11,%R14,8),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%R11,%R14,8),%RDI | 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 7695 <hypre_ParMatmul._omp_fn.3+0x305> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x128(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x130(%RBP),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RSI,-0xa8(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDI,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV -0xa8(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INCQ -0xa0(%RBP) | 3 | 0.20 | 0.20 | 0.33 | 0.33 | 0.50 | 0.20 | 0.20 | 0.50 | 0.50 | 0.50 | 0.20 | 0.33 | 1 | 0.50 |
MOV -0xa0(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %R12,-0x120(%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 797f <hypre_ParMatmul._omp_fn.3+0x5ef> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPQ $0,-0x110(%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 |
MOV %RSI,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 759d <hypre_ParMatmul._omp_fn.3+0x20d> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0xe0(%RBP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0xa0(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R15,%RAX,8),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%R15,%RAX,8),%R14 | 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 75b2 <hypre_ParMatmul._omp_fn.3+0x222> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R12,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x50(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x58(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV -0x48(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 75b2 <hypre_ParMatmul._omp_fn.3+0x222> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |