Loop Id: 106 | Module: libparcsr_mv.so | Source: par_csr_matop.c:865-989 [...] | Coverage: 0.03% |
---|
Loop Id: 106 | Module: libparcsr_mv.so | Source: par_csr_matop.c:865-989 [...] | Coverage: 0.03% |
---|
0xb4a0 MOV %RCX,%R12 |
0xb4a3 MOV %RAX,%R14 |
0xb4a6 CMP -0x48(%RBP),%R8 |
0xb4aa JGE b7f6 |
0xb4b0 MOV %R8,%RDX |
0xb4b3 CMPQ $0,-0xc0(%RBP) |
0xb4bb JE b4d5 |
0xb4bd MOV %R14,(%RDI,%RDX,8) |
0xb4c1 MOVQ $0,(%R15,%R14,8) |
0xb4c9 MOV -0x58(%RBP),%RAX |
0xb4cd MOV %RDX,(%RAX,%R14,8) |
0xb4d1 LEA 0x1(%R14),%RAX |
0xb4d5 CMPQ $0,-0xb8(%RBP) |
0xb4dd JE b650 |
0xb4e3 MOV -0x60(%RBP),%RCX |
0xb4e7 MOV (%RCX,%RDX,8),%R9 |
0xb4eb LEA 0x1(%RDX),%R8 |
0xb4ef CMP 0x8(%RCX,%RDX,8),%R9 |
0xb4f4 JGE b654 |
0xb4fa MOV %R8,-0x30(%RBP) |
0xb4fe MOV %R12,%RCX |
0xb501 MOV %RDX,-0xe0(%RBP) |
0xb508 JMP b52d |
(110) 0xb510 MOV -0x38(%RBP),%R9 |
(110) 0xb514 INC %R9 |
(110) 0xb517 MOV -0x60(%RBP),%RDX |
(110) 0xb51b MOV -0xe0(%RBP),%RSI |
(110) 0xb522 CMP 0x8(%RDX,%RSI,8),%R9 |
(110) 0xb527 JGE b660 |
(110) 0xb52d MOV -0xd0(%RBP),%RDX |
(110) 0xb534 MOV (%RDX,%R9,8),%R8 |
(110) 0xb538 MOV -0xd8(%RBP),%RDX |
(110) 0xb53f MOV %R9,-0x38(%RBP) |
(110) 0xb543 VMOVSD (%RDX,%R9,8),%XMM0 |
(110) 0xb549 MOV -0x80(%RBP),%RDX |
(110) 0xb54d MOV (%RDX,%R8,8),%R9 |
(110) 0xb551 MOV 0x8(%RDX,%R8,8),%R10 |
(110) 0xb556 CMP %R10,%R9 |
(110) 0xb559 JL b595 |
(110) 0xb55b JMP b5cb |
(112) 0xb560 MOV %RCX,(%RDI,%RSI,8) |
(112) 0xb564 MOV -0xa8(%RBP),%RDX |
(112) 0xb56b VMULSD (%RDX,%R9,8),%XMM0,%XMM1 |
(112) 0xb571 VMOVSD %XMM1,(%RBX,%RCX,8) |
(112) 0xb576 MOV -0x98(%RBP),%RDX |
(112) 0xb57d MOV %R11,(%RDX,%RCX,8) |
(112) 0xb581 INC %RCX |
(112) 0xb584 MOV -0x80(%RBP),%RDX |
(112) 0xb588 MOV 0x8(%RDX,%R8,8),%R10 |
(112) 0xb58d INC %R9 |
(112) 0xb590 CMP %R10,%R9 |
(112) 0xb593 JGE b5cb |
(112) 0xb595 MOV (%R13,%R9,8),%R11 |
(112) 0xb59a MOV -0x40(%RBP),%RDX |
(112) 0xb59e LEA (%R11,%RDX,1),%RSI |
(112) 0xb5a2 MOV (%RDI,%RSI,8),%RDX |
(112) 0xb5a6 CMP %R12,%RDX |
(112) 0xb5a9 JL b560 |
(112) 0xb5ab MOV -0xa8(%RBP),%RSI |
(112) 0xb5b2 VMOVSD (%RSI,%R9,8),%XMM1 |
(112) 0xb5b8 VFMADD213SD (%RBX,%RDX,8),%XMM0,%XMM1 |
(112) 0xb5be VMOVSD %XMM1,(%RBX,%RDX,8) |
(112) 0xb5c3 INC %R9 |
(112) 0xb5c6 CMP %R10,%R9 |
(112) 0xb5c9 JL b595 |
(110) 0xb5cb MOV -0x78(%RBP),%RDX |
(110) 0xb5cf MOV (%RDX,%R8,8),%R9 |
(110) 0xb5d3 MOV 0x8(%RDX,%R8,8),%R10 |
(110) 0xb5d8 CMP %R10,%R9 |
(110) 0xb5db JGE b510 |
(110) 0xb5e1 MOV -0xc8(%RBP),%RSI |
(110) 0xb5e8 JMP b615 |
(111) 0xb5f0 MOV -0xa0(%RBP),%R11 |
(111) 0xb5f7 VMOVSD (%R11,%R9,8),%XMM1 |
(111) 0xb5fd VFMADD213SD (%R15,%RDX,8),%XMM0,%XMM1 |
(111) 0xb603 VMOVSD %XMM1,(%R15,%RDX,8) |
(111) 0xb609 INC %R9 |
(111) 0xb60c CMP %R10,%R9 |
(111) 0xb60f JGE b510 |
(111) 0xb615 MOV (%RSI,%R9,8),%R11 |
(111) 0xb619 MOV (%RDI,%R11,8),%RDX |
(111) 0xb61d CMP %R14,%RDX |
(111) 0xb620 JGE b5f0 |
(111) 0xb622 MOV %RAX,(%RDI,%R11,8) |
(111) 0xb626 MOV -0xa0(%RBP),%RDX |
(111) 0xb62d VMULSD (%RDX,%R9,8),%XMM0,%XMM1 |
(111) 0xb633 VMOVSD %XMM1,(%R15,%RAX,8) |
(111) 0xb639 MOV -0x58(%RBP),%RDX |
(111) 0xb63d MOV %R11,(%RDX,%RAX,8) |
(111) 0xb641 INC %RAX |
(111) 0xb644 MOV -0x78(%RBP),%RDX |
(111) 0xb648 MOV 0x8(%RDX,%R8,8),%R10 |
(111) 0xb64d JMP b609 |
0xb650 LEA 0x1(%RDX),%R8 |
0xb654 MOV %R12,%RCX |
0xb657 JMP b667 |
0xb660 MOV %RSI,%RDX |
0xb663 MOV -0x30(%RBP),%R8 |
0xb667 MOV -0x68(%RBP),%RSI |
0xb66b MOV (%RSI,%RDX,8),%RDX |
0xb66f CMP (%RSI,%R8,8),%RDX |
0xb673 JGE b4a0 |
0xb679 MOV %R8,-0x30(%RBP) |
0xb67d JMP b699 |
(107) 0xb680 INC %RDX |
(107) 0xb683 MOV -0x68(%RBP),%RSI |
(107) 0xb687 MOV -0x30(%RBP),%R8 |
(107) 0xb68b CMP (%RSI,%R8,8),%RDX |
(107) 0xb68f MOV -0x50(%RBP),%R13 |
(107) 0xb693 JGE b4a0 |
(107) 0xb699 MOV -0xf8(%RBP),%RSI |
(107) 0xb6a0 MOV (%RSI,%RDX,8),%RSI |
(107) 0xb6a4 MOV -0xf0(%RBP),%R8 |
(107) 0xb6ab VMOVSD (%R8,%RDX,8),%XMM0 |
(107) 0xb6b1 MOV -0x88(%RBP),%R9 |
(107) 0xb6b8 MOV (%R9,%RSI,8),%R8 |
(107) 0xb6bc MOV 0x8(%R9,%RSI,8),%R9 |
(107) 0xb6c1 CMP %R9,%R8 |
(107) 0xb6c4 JGE b740 |
(107) 0xb6c6 MOV -0x58(%RBP),%R13 |
(107) 0xb6ca JMP b6f1 |
(109) 0xb6d0 MOV -0xb0(%RBP),%R10 |
(109) 0xb6d7 VMOVSD (%R10,%R8,8),%XMM1 |
(109) 0xb6dd VFMADD213SD (%R15,%R11,8),%XMM0,%XMM1 |
(109) 0xb6e3 VMOVSD %XMM1,(%R15,%R11,8) |
(109) 0xb6e9 INC %R8 |
(109) 0xb6ec CMP %R9,%R8 |
(109) 0xb6ef JGE b740 |
(109) 0xb6f1 MOV -0x110(%RBP),%R10 |
(109) 0xb6f8 MOV (%R10,%R8,8),%R10 |
(109) 0xb6fc MOV (%RDI,%R10,8),%R11 |
(109) 0xb700 CMP %R14,%R11 |
(109) 0xb703 JGE b6d0 |
(109) 0xb705 MOV %RAX,(%RDI,%R10,8) |
(109) 0xb709 MOV -0xb0(%RBP),%R9 |
(109) 0xb710 VMULSD (%R9,%R8,8),%XMM0,%XMM1 |
(109) 0xb716 VMOVSD %XMM1,(%R15,%RAX,8) |
(109) 0xb71c MOV %R10,(%R13,%RAX,8) |
(109) 0xb721 INC %RAX |
(109) 0xb724 MOV -0x88(%RBP),%R9 |
(109) 0xb72b MOV 0x8(%R9,%RSI,8),%R9 |
(109) 0xb730 JMP b6e9 |
(107) 0xb740 CMPQ $0,-0xe8(%RBP) |
(107) 0xb748 JE b680 |
(107) 0xb74e MOV -0x70(%RBP),%R9 |
(107) 0xb752 MOV (%R9,%RSI,8),%R8 |
(107) 0xb756 MOV 0x8(%R9,%RSI,8),%R9 |
(107) 0xb75b CMP %R9,%R8 |
(107) 0xb75e JL b7a9 |
(107) 0xb760 JMP b680 |
(108) 0xb770 MOV %RCX,(%RDI,%R13,8) |
(108) 0xb774 MOV -0x90(%RBP),%R9 |
(108) 0xb77b VMULSD (%R9,%R8,8),%XMM0,%XMM1 |
(108) 0xb781 VMOVSD %XMM1,(%RBX,%RCX,8) |
(108) 0xb786 MOV -0x98(%RBP),%R9 |
(108) 0xb78d MOV %R10,(%R9,%RCX,8) |
(108) 0xb791 INC %RCX |
(108) 0xb794 MOV -0x70(%RBP),%R9 |
(108) 0xb798 MOV 0x8(%R9,%RSI,8),%R9 |
(108) 0xb79d INC %R8 |
(108) 0xb7a0 CMP %R9,%R8 |
(108) 0xb7a3 JGE b680 |
(108) 0xb7a9 MOV -0x100(%RBP),%R10 |
(108) 0xb7b0 MOV (%R10,%R8,8),%R10 |
(108) 0xb7b4 MOV -0x108(%RBP),%R11 |
(108) 0xb7bb MOV (%R11,%R10,8),%R10 |
(108) 0xb7bf MOV -0x40(%RBP),%R11 |
(108) 0xb7c3 LEA (%R10,%R11,1),%R13 |
(108) 0xb7c7 MOV (%RDI,%R13,8),%R11 |
(108) 0xb7cb CMP %R12,%R11 |
(108) 0xb7ce JL b770 |
(108) 0xb7d0 MOV -0x90(%RBP),%R10 |
(108) 0xb7d7 VMOVSD (%R10,%R8,8),%XMM1 |
(108) 0xb7dd VFMADD213SD (%RBX,%R11,8),%XMM0,%XMM1 |
(108) 0xb7e3 VMOVSD %XMM1,(%RBX,%R11,8) |
(108) 0xb7e9 INC %R8 |
(108) 0xb7ec CMP %R9,%R8 |
(108) 0xb7ef JL b7a9 |
(107) 0xb7f1 JMP b680 |
/scratch_na/users/xoserete/qaas_runs/171-587-0005/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 865 - 989 |
-------------------------------------------------------------------------------- |
865: for (i1 = ns; i1 < ne; i1++) |
[...] |
874: if ( allsquare ) |
875: { |
876: B_marker[i1] = jj_count_diag; |
877: C_diag_data[jj_count_diag] = zero; |
878: C_diag_j[jj_count_diag] = i1; |
879: jj_count_diag++; |
[...] |
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 |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.36 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.64 |
Bottlenecks | micro-operation queue, |
Function | hypre_ParMatmul.extracted.12 |
Source | par_csr_matop.c:865-865,par_csr_matop.c:874-879,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 | 6.00 |
CQA cycles if no scalar integer | 6.00 |
CQA cycles if FP arith vectorized | 6.00 |
CQA cycles if fully vectorized | 0.49 |
Front-end cycles | 6.00 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 1.80 |
P1 cycles | 3.67 |
P2 cycles | 3.67 |
P3 cycles | 3.00 |
P4 cycles | 1.60 |
P5 cycles | 2.50 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 1.60 |
P10 cycles | 3.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.16 |
Stall cycles (UFS) | 0.00 |
Nb insns | 34.00 |
Nb uops | 34.00 |
Nb loads | 11.00 |
Nb stores | 6.00 |
Nb stack references | 8.00 |
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 | 22.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 88.00 |
Bytes stored | 48.00 |
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 | 11.98 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 11.46 |
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 | 12.36 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.64 |
Bottlenecks | micro-operation queue, |
Function | hypre_ParMatmul.extracted.12 |
Source | par_csr_matop.c:865-865,par_csr_matop.c:874-879,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 | 6.00 |
CQA cycles if no scalar integer | 6.00 |
CQA cycles if FP arith vectorized | 6.00 |
CQA cycles if fully vectorized | 0.49 |
Front-end cycles | 6.00 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 1.80 |
P1 cycles | 3.67 |
P2 cycles | 3.67 |
P3 cycles | 3.00 |
P4 cycles | 1.60 |
P5 cycles | 2.50 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 1.60 |
P10 cycles | 3.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.16 |
Stall cycles (UFS) | 0.00 |
Nb insns | 34.00 |
Nb uops | 34.00 |
Nb loads | 11.00 |
Nb stores | 6.00 |
Nb stack references | 8.00 |
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 | 22.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 88.00 |
Bytes stored | 48.00 |
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 | 11.98 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 11.46 |
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:865-989 |
Module | libparcsr_mv.so |
nb instructions | 34 |
nb uops | 34 |
loop length | 146 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 6.00 cycles |
front end | 6.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 1.80 | 3.67 | 3.67 | 3.00 | 1.60 | 2.50 | 3.00 | 3.00 | 3.00 | 1.60 | 3.67 |
cycles | 2.50 | 1.80 | 3.67 | 3.67 | 3.00 | 1.60 | 2.50 | 3.00 | 3.00 | 3.00 | 1.60 | 3.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.16 |
Stall cycles | 0.00 |
Front-end | 6.00 |
Dispatch | 3.67 |
Overall L1 | 6.00 |
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 | 11% |
load | 12% |
store | 11% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV %RCX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RAX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x48(%RBP),%R8 | 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 b7f6 <hypre_ParMatmul.extracted.12+0x586> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMPQ $0,-0xc0(%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 b4d5 <hypre_ParMatmul.extracted.12+0x265> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R14,(%RDI,%RDX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVQ $0,(%R15,%R14,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RDX,(%RAX,%R14,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%R14),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMPQ $0,-0xb8(%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 b650 <hypre_ParMatmul.extracted.12+0x3e0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RCX,%RDX,8),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA 0x1(%RDX),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP 0x8(%RCX,%RDX,8),%R9 | 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 b654 <hypre_ParMatmul.extracted.12+0x3e4> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R12,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RDX,-0xe0(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP b52d <hypre_ParMatmul.extracted.12+0x2bd> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RDX),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R12,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JMP b667 <hypre_ParMatmul.extracted.12+0x3f7> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
MOV %RSI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x30(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x68(%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),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RSI,%R8,8),%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 b4a0 <hypre_ParMatmul.extracted.12+0x230> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP b699 <hypre_ParMatmul.extracted.12+0x429> | 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:865-989 |
Module | libparcsr_mv.so |
nb instructions | 34 |
nb uops | 34 |
loop length | 146 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 6.00 cycles |
front end | 6.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 1.80 | 3.67 | 3.67 | 3.00 | 1.60 | 2.50 | 3.00 | 3.00 | 3.00 | 1.60 | 3.67 |
cycles | 2.50 | 1.80 | 3.67 | 3.67 | 3.00 | 1.60 | 2.50 | 3.00 | 3.00 | 3.00 | 1.60 | 3.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.16 |
Stall cycles | 0.00 |
Front-end | 6.00 |
Dispatch | 3.67 |
Overall L1 | 6.00 |
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 | 11% |
load | 12% |
store | 11% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV %RCX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RAX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x48(%RBP),%R8 | 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 b7f6 <hypre_ParMatmul.extracted.12+0x586> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMPQ $0,-0xc0(%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 b4d5 <hypre_ParMatmul.extracted.12+0x265> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R14,(%RDI,%RDX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVQ $0,(%R15,%R14,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RDX,(%RAX,%R14,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%R14),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMPQ $0,-0xb8(%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 b650 <hypre_ParMatmul.extracted.12+0x3e0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RCX,%RDX,8),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA 0x1(%RDX),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP 0x8(%RCX,%RDX,8),%R9 | 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 b654 <hypre_ParMatmul.extracted.12+0x3e4> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R12,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RDX,-0xe0(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP b52d <hypre_ParMatmul.extracted.12+0x2bd> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RDX),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R12,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JMP b667 <hypre_ParMatmul.extracted.12+0x3f7> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
MOV %RSI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x30(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x68(%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),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RSI,%R8,8),%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 b4a0 <hypre_ParMatmul.extracted.12+0x230> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP b699 <hypre_ParMatmul.extracted.12+0x429> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |