Loop Id: 133 | Module: libparcsr_mv.so | Source: par_csr_matop.c:865-989 [...] | Coverage: 0.06% |
---|
Loop Id: 133 | Module: libparcsr_mv.so | Source: par_csr_matop.c:865-989 [...] | Coverage: 0.06% |
---|
0x10a80 MOV %RCX,-0x30(%RBP) |
0x10a84 MOV %RAX,%R14 |
0x10a87 CMP -0x38(%RBP),%R8 |
0x10a8b JGE 10e80 |
0x10a91 MOV %R8,%RSI |
0x10a94 CMPQ $0,-0x98(%RBP) |
0x10a9c JE 10ab6 |
0x10a9e MOV %R14,(%RDI,%RSI,8) |
0x10aa2 MOVQ $0,(%R12,%R14,8) |
0x10aaa MOV -0x50(%RBP),%RAX |
0x10aae MOV %RSI,(%RAX,%R14,8) |
0x10ab2 LEA 0x1(%R14),%RAX |
0x10ab6 CMPQ $0,-0x90(%RBP) |
0x10abe JE 10cc0 |
0x10ac4 MOV -0x58(%RBP),%RCX |
0x10ac8 MOV (%RCX,%RSI,8),%R10 |
0x10acc LEA 0x1(%RSI),%R8 |
0x10ad0 CMP 0x8(%RCX,%RSI,8),%R10 |
0x10ad5 JGE 10cc4 |
0x10adb MOV %R8,-0x48(%RBP) |
0x10adf MOV -0x30(%RBP),%RCX |
0x10ae3 MOV %RSI,-0xb0(%RBP) |
0x10aea JMP 10b1c |
(137) 0x10b00 MOV %RBX,%R10 |
(137) 0x10b03 INC %R10 |
(137) 0x10b06 MOV -0x58(%RBP),%RDX |
(137) 0x10b0a MOV -0xb0(%RBP),%RSI |
(137) 0x10b11 CMP 0x8(%RDX,%RSI,8),%R10 |
(137) 0x10b16 JGE 10d00 |
(137) 0x10b1c MOV -0xa0(%RBP),%RDX |
(137) 0x10b23 MOV (%RDX,%R10,8),%R9 |
(137) 0x10b27 MOV -0xa8(%RBP),%RDX |
(137) 0x10b2e MOV %R10,%RBX |
(137) 0x10b31 VMOVSD (%RDX,%R10,8),%XMM0 |
(137) 0x10b37 MOV -0x78(%RBP),%RDX |
(137) 0x10b3b MOV (%RDX,%R9,8),%R10 |
(137) 0x10b3f MOV 0x8(%RDX,%R9,8),%R11 |
(137) 0x10b44 JMP 10b95 |
(139) 0x10b80 VADDSD (%R13,%R8,8),%XMM1,%XMM1 |
(139) 0x10b87 VMOVSD %XMM1,(%R13,%R8,8) |
(139) 0x10b8e MOV -0x40(%RBP),%R15 |
(139) 0x10b92 INC %R10 |
(139) 0x10b95 CMP %R11,%R10 |
(139) 0x10b98 JGE 10c00 |
(139) 0x10b9a MOV -0x100(%RBP),%RDX |
(139) 0x10ba1 MOV (%RDX,%R10,8),%RSI |
(139) 0x10ba5 LEA (%RSI,%R15,1),%RDX |
(139) 0x10ba9 MOV (%RDI,%RDX,8),%R8 |
(139) 0x10bad MOV -0xf8(%RBP),%R15 |
(139) 0x10bb4 VMULSD (%R15,%R10,8),%XMM0,%XMM1 |
(139) 0x10bba CMP -0x30(%RBP),%R8 |
(139) 0x10bbe JGE 10b80 |
(139) 0x10bc0 MOV %RCX,(%RDI,%RDX,8) |
(139) 0x10bc4 VMOVSD %XMM1,(%R13,%RCX,8) |
(139) 0x10bcb MOV -0x88(%RBP),%RDX |
(139) 0x10bd2 MOV %RSI,(%RDX,%RCX,8) |
(139) 0x10bd6 INC %RCX |
(139) 0x10bd9 MOV -0x78(%RBP),%RDX |
(139) 0x10bdd MOV 0x8(%RDX,%R9,8),%R11 |
(139) 0x10be2 JMP 10b8e |
(137) 0x10c00 MOV -0x70(%RBP),%RDX |
(137) 0x10c04 MOV (%RDX,%R9,8),%R10 |
(137) 0x10c08 MOV 0x8(%RDX,%R9,8),%R11 |
(137) 0x10c0d CMP %R11,%R10 |
(137) 0x10c10 JL 10c6a |
(137) 0x10c12 JMP 10b00 |
(138) 0x10c40 MOV %RAX,(%RDI,%RSI,8) |
(138) 0x10c44 VMOVSD %XMM1,(%R12,%RAX,8) |
(138) 0x10c4a MOV -0x50(%RBP),%RDX |
(138) 0x10c4e MOV %RSI,(%RDX,%RAX,8) |
(138) 0x10c52 INC %RAX |
(138) 0x10c55 MOV -0x70(%RBP),%RDX |
(138) 0x10c59 MOV 0x8(%RDX,%R9,8),%R11 |
(138) 0x10c5e INC %R10 |
(138) 0x10c61 CMP %R11,%R10 |
(138) 0x10c64 JGE 10b00 |
(138) 0x10c6a MOV -0xf0(%RBP),%RDX |
(138) 0x10c71 MOV (%RDX,%R10,8),%RSI |
(138) 0x10c75 MOV (%RDI,%RSI,8),%RDX |
(138) 0x10c79 MOV -0xe8(%RBP),%R8 |
(138) 0x10c80 VMULSD (%R8,%R10,8),%XMM0,%XMM1 |
(138) 0x10c86 CMP %R14,%RDX |
(138) 0x10c89 JL 10c40 |
(138) 0x10c8b VADDSD (%R12,%RDX,8),%XMM1,%XMM1 |
(138) 0x10c91 VMOVSD %XMM1,(%R12,%RDX,8) |
(138) 0x10c97 INC %R10 |
(138) 0x10c9a CMP %R11,%R10 |
(138) 0x10c9d JL 10c6a |
(137) 0x10c9f JMP 10b00 |
0x10cc0 LEA 0x1(%RSI),%R8 |
0x10cc4 MOV -0x30(%RBP),%RCX |
0x10cc8 MOV -0x60(%RBP),%RDX |
0x10ccc MOV (%RDX,%RSI,8),%RSI |
0x10cd0 CMP (%RDX,%R8,8),%RSI |
0x10cd4 JGE 10a80 |
0x10cda JMP 10d16 |
0x10d00 MOV -0x48(%RBP),%R8 |
0x10d04 MOV -0x60(%RBP),%RDX |
0x10d08 MOV (%RDX,%RSI,8),%RSI |
0x10d0c CMP (%RDX,%R8,8),%RSI |
0x10d10 JGE 10a80 |
0x10d16 MOV %R8,-0x48(%RBP) |
0x10d1a JMP 10d55 |
(134) 0x10d40 INC %RSI |
(134) 0x10d43 MOV -0x60(%RBP),%RDX |
(134) 0x10d47 MOV -0x48(%RBP),%R8 |
(134) 0x10d4b CMP (%RDX,%R8,8),%RSI |
(134) 0x10d4f JGE 10a80 |
(134) 0x10d55 MOV -0xc8(%RBP),%RDX |
(134) 0x10d5c MOV (%RDX,%RSI,8),%R8 |
(134) 0x10d60 MOV -0xc0(%RBP),%RDX |
(134) 0x10d67 VMOVSD (%RDX,%RSI,8),%XMM0 |
(134) 0x10d6c MOV -0x80(%RBP),%RDX |
(134) 0x10d70 MOV (%RDX,%R8,8),%R9 |
(134) 0x10d74 MOV 0x8(%RDX,%R8,8),%R10 |
(134) 0x10d79 CMP %R10,%R9 |
(134) 0x10d7c JL 10da6 |
(134) 0x10d7e JMP 10ddb |
(136) 0x10d80 MOV %RAX,(%RDI,%RDX,8) |
(136) 0x10d84 VMOVSD %XMM1,(%R12,%RAX,8) |
(136) 0x10d8a MOV -0x50(%RBP),%R10 |
(136) 0x10d8e MOV %RDX,(%R10,%RAX,8) |
(136) 0x10d92 INC %RAX |
(136) 0x10d95 MOV -0x80(%RBP),%RDX |
(136) 0x10d99 MOV 0x8(%RDX,%R8,8),%R10 |
(136) 0x10d9e INC %R9 |
(136) 0x10da1 CMP %R10,%R9 |
(136) 0x10da4 JGE 10ddb |
(136) 0x10da6 MOV -0x110(%RBP),%RDX |
(136) 0x10dad MOV (%RDX,%R9,8),%RDX |
(136) 0x10db1 MOV (%RDI,%RDX,8),%R11 |
(136) 0x10db5 MOV -0x108(%RBP),%RBX |
(136) 0x10dbc VMULSD (%RBX,%R9,8),%XMM0,%XMM1 |
(136) 0x10dc2 CMP %R14,%R11 |
(136) 0x10dc5 JL 10d80 |
(136) 0x10dc7 VADDSD (%R12,%R11,8),%XMM1,%XMM1 |
(136) 0x10dcd VMOVSD %XMM1,(%R12,%R11,8) |
(136) 0x10dd3 INC %R9 |
(136) 0x10dd6 CMP %R10,%R9 |
(136) 0x10dd9 JL 10da6 |
(134) 0x10ddb CMPQ $0,-0xb8(%RBP) |
(134) 0x10de3 JE 10d40 |
(134) 0x10de9 MOV -0x68(%RBP),%RDX |
(134) 0x10ded MOV (%RDX,%R8,8),%R9 |
(134) 0x10df1 MOV 0x8(%RDX,%R8,8),%R10 |
(134) 0x10df6 JMP 10e15 |
(135) 0x10e00 VADDSD (%R13,%R15,8),%XMM1,%XMM1 |
(135) 0x10e07 VMOVSD %XMM1,(%R13,%R15,8) |
(135) 0x10e0e MOV -0x40(%RBP),%R15 |
(135) 0x10e12 INC %R9 |
(135) 0x10e15 CMP %R10,%R9 |
(135) 0x10e18 JGE 10d40 |
(135) 0x10e1e MOV -0xd8(%RBP),%RDX |
(135) 0x10e25 MOV (%RDX,%R9,8),%RDX |
(135) 0x10e29 MOV -0xe0(%RBP),%R11 |
(135) 0x10e30 MOV (%R11,%RDX,8),%RDX |
(135) 0x10e34 LEA (%RDX,%R15,1),%R11 |
(135) 0x10e38 MOV (%RDI,%R11,8),%R15 |
(135) 0x10e3c MOV -0xd0(%RBP),%RBX |
(135) 0x10e43 VMULSD (%RBX,%R9,8),%XMM0,%XMM1 |
(135) 0x10e49 CMP -0x30(%RBP),%R15 |
(135) 0x10e4d JGE 10e00 |
(135) 0x10e4f MOV %RCX,(%RDI,%R11,8) |
(135) 0x10e53 VMOVSD %XMM1,(%R13,%RCX,8) |
(135) 0x10e5a MOV -0x88(%RBP),%R10 |
(135) 0x10e61 MOV %RDX,(%R10,%RCX,8) |
(135) 0x10e65 INC %RCX |
(135) 0x10e68 MOV -0x68(%RBP),%RDX |
(135) 0x10e6c MOV 0x8(%RDX,%R8,8),%R10 |
(135) 0x10e71 JMP 10e0e |
/home/eoseret/qaas_runs_CPU_9468/171-716-5699/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]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.08 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.25 |
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 | 6.67 |
CQA cycles if no scalar integer | 6.67 |
CQA cycles if FP arith vectorized | 6.67 |
CQA cycles if fully vectorized | 0.55 |
Front-end cycles | 6.67 |
DIV/SQRT cycles | 3.00 |
P0 cycles | 2.00 |
P1 cycles | 5.33 |
P2 cycles | 5.33 |
P3 cycles | 3.50 |
P4 cycles | 2.00 |
P5 cycles | 3.00 |
P6 cycles | 3.50 |
P7 cycles | 3.50 |
P8 cycles | 3.50 |
P9 cycles | 2.00 |
P10 cycles | 5.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.87 |
Stall cycles (UFS) | 0.00 |
Nb insns | 37.00 |
Nb uops | 37.00 |
Nb loads | 16.00 |
Nb stores | 7.00 |
Nb stack references | 9.00 |
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 | 27.60 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 56.00 |
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 | 12.02 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 11.61 |
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 | 12.08 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.25 |
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 | 6.67 |
CQA cycles if no scalar integer | 6.67 |
CQA cycles if FP arith vectorized | 6.67 |
CQA cycles if fully vectorized | 0.55 |
Front-end cycles | 6.67 |
DIV/SQRT cycles | 3.00 |
P0 cycles | 2.00 |
P1 cycles | 5.33 |
P2 cycles | 5.33 |
P3 cycles | 3.50 |
P4 cycles | 2.00 |
P5 cycles | 3.00 |
P6 cycles | 3.50 |
P7 cycles | 3.50 |
P8 cycles | 3.50 |
P9 cycles | 2.00 |
P10 cycles | 5.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.87 |
Stall cycles (UFS) | 0.00 |
Nb insns | 37.00 |
Nb uops | 37.00 |
Nb loads | 16.00 |
Nb stores | 7.00 |
Nb stack references | 9.00 |
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 | 27.60 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 56.00 |
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 | 12.02 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 11.61 |
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 | 37 |
nb uops | 37 |
loop length | 164 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 9 |
micro-operation queue | 6.67 cycles |
front end | 6.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.00 | 2.00 | 5.33 | 5.33 | 3.50 | 2.00 | 3.00 | 3.50 | 3.50 | 3.50 | 2.00 | 5.33 |
cycles | 3.00 | 2.00 | 5.33 | 5.33 | 3.50 | 2.00 | 3.00 | 3.50 | 3.50 | 3.50 | 2.00 | 5.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.87 |
Stall cycles | 0.00 |
Front-end | 6.67 |
Dispatch | 5.33 |
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 | 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,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x38(%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 10e80 <hypre_ParMatmul.extracted.12+0x680> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMPQ $0,-0x98(%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 10ab6 <hypre_ParMatmul.extracted.12+0x2b6> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R14,(%RDI,%RSI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVQ $0,(%R12,%R14,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RSI,(%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,-0x90(%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 10cc0 <hypre_ParMatmul.extracted.12+0x4c0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RCX,%RSI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA 0x1(%RSI),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP 0x8(%RCX,%RSI,8),%R10 | 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 10cc4 <hypre_ParMatmul.extracted.12+0x4c4> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RSI,-0xb0(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 10b1c <hypre_ParMatmul.extracted.12+0x31c> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RSI),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x60(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDX,%RSI,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RDX,%R8,8),%RSI | 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 10a80 <hypre_ParMatmul.extracted.12+0x280> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 10d16 <hypre_ParMatmul.extracted.12+0x516> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x60(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDX,%RSI,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RDX,%R8,8),%RSI | 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 10a80 <hypre_ParMatmul.extracted.12+0x280> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 10d55 <hypre_ParMatmul.extracted.12+0x555> | 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 | 37 |
nb uops | 37 |
loop length | 164 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 9 |
micro-operation queue | 6.67 cycles |
front end | 6.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.00 | 2.00 | 5.33 | 5.33 | 3.50 | 2.00 | 3.00 | 3.50 | 3.50 | 3.50 | 2.00 | 5.33 |
cycles | 3.00 | 2.00 | 5.33 | 5.33 | 3.50 | 2.00 | 3.00 | 3.50 | 3.50 | 3.50 | 2.00 | 5.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.87 |
Stall cycles | 0.00 |
Front-end | 6.67 |
Dispatch | 5.33 |
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 | 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,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x38(%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 10e80 <hypre_ParMatmul.extracted.12+0x680> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMPQ $0,-0x98(%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 10ab6 <hypre_ParMatmul.extracted.12+0x2b6> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R14,(%RDI,%RSI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVQ $0,(%R12,%R14,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RSI,(%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,-0x90(%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 10cc0 <hypre_ParMatmul.extracted.12+0x4c0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RCX,%RSI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA 0x1(%RSI),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP 0x8(%RCX,%RSI,8),%R10 | 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 10cc4 <hypre_ParMatmul.extracted.12+0x4c4> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RSI,-0xb0(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 10b1c <hypre_ParMatmul.extracted.12+0x31c> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RSI),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x60(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDX,%RSI,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RDX,%R8,8),%RSI | 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 10a80 <hypre_ParMatmul.extracted.12+0x280> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 10d16 <hypre_ParMatmul.extracted.12+0x516> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x60(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDX,%RSI,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RDX,%R8,8),%RSI | 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 10a80 <hypre_ParMatmul.extracted.12+0x280> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 10d55 <hypre_ParMatmul.extracted.12+0x555> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |