Loop Id: 71 | Module: libparcsr_mv.so | Source: par_csr_matop.c:127-242 [...] | Coverage: 0.04% |
---|
Loop Id: 71 | Module: libparcsr_mv.so | Source: par_csr_matop.c:127-242 [...] | Coverage: 0.04% |
---|
0x9b90 MOV -0x78(%RBP),%RSI |
0x9b94 MOV -0x50(%RBP),%RDI |
0x9b98 MOV %RBX,(%RSI,%RDI,8) |
0x9b9c MOV -0x70(%RBP),%RSI |
0x9ba0 MOV %R8,(%RSI,%RDI,8) |
0x9ba4 MOV %RDX,%RDI |
0x9ba7 MOV %R13,%R8 |
0x9baa MOV %RAX,%RBX |
0x9bad CMP -0x38(%RBP),%RDX |
0x9bb1 JGE 9d7c |
0x9bb7 MOV 0x78(%RBP),%RSI |
0x9bbb TEST %RSI,%RSI |
0x9bbe JE 9bc8 |
0x9bc0 MOV %RBX,(%R14,%RDI,8) |
0x9bc4 LEA 0x1(%RBX),%RAX |
0x9bc8 CMPQ $0,0x70(%RBP) |
0x9bcd MOV %RDI,-0x50(%RBP) |
0x9bd1 JE 9ca0 |
0x9bd7 MOV 0x10(%RBP),%RSI |
0x9bdb MOV (%RSI,%RDI,8),%R10 |
0x9bdf LEA 0x1(%RDI),%RDX |
0x9be3 CMP 0x8(%RSI,%RDI,8),%R10 |
0x9be8 JGE 9ca4 |
0x9bee MOV %R8,%R13 |
0x9bf1 JMP 9c16 |
(75) 0x9c00 INC %R10 |
(75) 0x9c03 MOV 0x10(%RBP),%RSI |
(75) 0x9c07 MOV -0x50(%RBP),%RDI |
(75) 0x9c0b CMP 0x8(%RSI,%RDI,8),%R10 |
(75) 0x9c10 JGE 9ca7 |
(75) 0x9c16 MOV 0x18(%RBP),%RSI |
(75) 0x9c1a MOV (%RSI,%R10,8),%R12 |
(75) 0x9c1e MOV 0x50(%RBP),%RDI |
(75) 0x9c22 MOV (%RDI,%R12,8),%RSI |
(75) 0x9c26 MOV 0x8(%RDI,%R12,8),%RDI |
(75) 0x9c2b JMP 9c33 |
(77) 0x9c30 INC %RSI |
(77) 0x9c33 CMP %RDI,%RSI |
(77) 0x9c36 JGE 9c60 |
(77) 0x9c38 MOV 0x58(%RBP),%R9 |
(77) 0x9c3c MOV (%R9,%RSI,8),%R9 |
(77) 0x9c40 ADD %R15,%R9 |
(77) 0x9c43 CMP %R8,(%R14,%R9,8) |
(77) 0x9c47 JGE 9c30 |
(77) 0x9c49 MOV %R13,(%R14,%R9,8) |
(77) 0x9c4d INC %R13 |
(77) 0x9c50 MOV 0x50(%RBP),%RDI |
(77) 0x9c54 MOV 0x8(%RDI,%R12,8),%RDI |
(77) 0x9c59 JMP 9c30 |
(75) 0x9c60 MOV 0x40(%RBP),%RDI |
(75) 0x9c64 MOV (%RDI,%R12,8),%RSI |
(75) 0x9c68 MOV 0x8(%RDI,%R12,8),%RDI |
(75) 0x9c6d JMP 9c73 |
(76) 0x9c70 INC %RSI |
(76) 0x9c73 CMP %RDI,%RSI |
(76) 0x9c76 JGE 9c00 |
(76) 0x9c78 MOV 0x48(%RBP),%R9 |
(76) 0x9c7c MOV (%R9,%RSI,8),%R9 |
(76) 0x9c80 CMP %RBX,(%R14,%R9,8) |
(76) 0x9c84 JGE 9c70 |
(76) 0x9c86 MOV %RAX,(%R14,%R9,8) |
(76) 0x9c8a INC %RAX |
(76) 0x9c8d MOV 0x40(%RBP),%RDI |
(76) 0x9c91 MOV 0x8(%RDI,%R12,8),%RDI |
(76) 0x9c96 JMP 9c70 |
0x9ca0 LEA 0x1(%RDI),%RDX |
0x9ca4 MOV %R8,%R13 |
0x9ca7 MOV -0x58(%RBP),%RSI |
0x9cab MOV (%RSI,%RDI,8),%R10 |
0x9caf JMP 9cc7 |
(72) 0x9cc0 INC %R10 |
(72) 0x9cc3 MOV -0x58(%RBP),%RSI |
(72) 0x9cc7 CMP (%RSI,%RDX,8),%R10 |
(72) 0x9ccb JGE 9b90 |
(72) 0x9cd1 MOV -0x80(%RBP),%RSI |
(72) 0x9cd5 MOV (%RSI,%R10,8),%R12 |
(72) 0x9cd9 MOV 0x20(%RBP),%RDI |
(72) 0x9cdd MOV (%RDI,%R12,8),%RSI |
(72) 0x9ce1 MOV 0x8(%RDI,%R12,8),%RDI |
(72) 0x9ce6 JMP 9cf3 |
(74) 0x9cf0 INC %RSI |
(74) 0x9cf3 CMP %RDI,%RSI |
(74) 0x9cf6 JGE 9d20 |
(74) 0x9cf8 MOV (%RCX,%RSI,8),%R9 |
(74) 0x9cfc CMP %RBX,(%R14,%R9,8) |
(74) 0x9d00 JGE 9cf0 |
(74) 0x9d02 MOV %RAX,(%R14,%R9,8) |
(74) 0x9d06 INC %RAX |
(74) 0x9d09 MOV 0x20(%RBP),%RDI |
(74) 0x9d0d MOV 0x8(%RDI,%R12,8),%RDI |
(74) 0x9d12 JMP 9cf0 |
(72) 0x9d20 CMPQ $0,0x88(%RBP) |
(72) 0x9d28 JE 9cc0 |
(72) 0x9d2a MOV 0x30(%RBP),%RDI |
(72) 0x9d2e MOV (%RDI,%R12,8),%RSI |
(72) 0x9d32 MOV 0x8(%RDI,%R12,8),%RDI |
(72) 0x9d37 JMP 9d43 |
(73) 0x9d40 INC %RSI |
(73) 0x9d43 CMP %RDI,%RSI |
(73) 0x9d46 JGE 9cc0 |
(73) 0x9d4c MOV 0x38(%RBP),%R9 |
(73) 0x9d50 MOV (%R9,%RSI,8),%R9 |
(73) 0x9d54 MOV 0x60(%RBP),%R11 |
(73) 0x9d58 MOV (%R11,%R9,8),%R9 |
(73) 0x9d5c ADD %R15,%R9 |
(73) 0x9d5f CMP %R8,(%R14,%R9,8) |
(73) 0x9d63 JGE 9d40 |
(73) 0x9d65 MOV %R13,(%R14,%R9,8) |
(73) 0x9d69 INC %R13 |
(73) 0x9d6c MOV 0x30(%RBP),%RDI |
(73) 0x9d70 MOV 0x8(%RDI,%R12,8),%RDI |
(73) 0x9d75 JMP 9d40 |
/home/eoseret/qaas_runs_CPU_9468/171-147-2675/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 127 - 242 |
-------------------------------------------------------------------------------- |
127: for (i1 = ns; i1 < ne; i1++) |
[...] |
135: if ( allsquare ) { |
136: B_marker[i1] = jj_count_diag; |
137: jj_count_diag++; |
[...] |
144: if (num_cols_offd_A) |
145: { |
146: for (jj2 = A_offd_i[i1]; jj2 < A_offd_i[i1+1]; jj2++) |
147: { |
148: i2 = A_offd_j[jj2]; |
[...] |
154: for (jj3 = B_ext_offd_i[i2]; jj3 < B_ext_offd_i[i2+1]; jj3++) |
155: { |
156: i3 = num_cols_diag_B+B_ext_offd_j[jj3]; |
[...] |
164: if (B_marker[i3] < jj_row_begin_offd) |
165: { |
166: B_marker[i3] = jj_count_offd; |
167: jj_count_offd++; |
168: } |
169: } |
170: for (jj3 = B_ext_diag_i[i2]; jj3 < B_ext_diag_i[i2+1]; jj3++) |
171: { |
172: i3 = B_ext_diag_j[jj3]; |
173: |
174: if (B_marker[i3] < jj_row_begin_diag) |
175: { |
176: B_marker[i3] = jj_count_diag; |
177: jj_count_diag++; |
[...] |
187: for (jj2 = A_diag_i[i1]; jj2 < A_diag_i[i1+1]; jj2++) |
188: { |
189: i2 = A_diag_j[jj2]; |
[...] |
195: for (jj3 = B_diag_i[i2]; jj3 < B_diag_i[i2+1]; jj3++) |
196: { |
197: i3 = B_diag_j[jj3]; |
[...] |
205: if (B_marker[i3] < jj_row_begin_diag) |
206: { |
207: B_marker[i3] = jj_count_diag; |
208: jj_count_diag++; |
[...] |
216: if (num_cols_offd_B) |
217: { |
218: for (jj3 = B_offd_i[i2]; jj3 < B_offd_i[i2+1]; jj3++) |
219: { |
220: i3 = num_cols_diag_B+map_B_to_C[B_offd_j[jj3]]; |
[...] |
228: if (B_marker[i3] < jj_row_begin_offd) |
229: { |
230: B_marker[i3] = jj_count_offd; |
231: jj_count_offd++; |
[...] |
241: (*C_diag_i)[i1] = jj_row_begin_diag; |
242: (*C_offd_i)[i1] = jj_row_begin_offd; |
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 | 1.41 |
Bottlenecks | micro-operation queue, |
Function | hypre_ParMatmul_RowSizes.extracted |
Source | par_csr_matop.c:127-127,par_csr_matop.c:135-137,par_csr_matop.c:144-146,par_csr_matop.c:187-187,par_csr_matop.c:241-242 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.17 |
CQA cycles if no scalar integer | 5.17 |
CQA cycles if FP arith vectorized | 5.17 |
CQA cycles if fully vectorized | 0.65 |
Front-end cycles | 5.17 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 1.40 |
P1 cycles | 3.67 |
P2 cycles | 3.67 |
P3 cycles | 2.00 |
P4 cycles | 1.40 |
P5 cycles | 2.00 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 1.20 |
P10 cycles | 3.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 5.31 |
Stall cycles (UFS) | 0.00 |
Nb insns | 30.00 |
Nb uops | 30.00 |
Nb loads | 11.00 |
Nb stores | 4.00 |
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 | 23.23 |
Bytes prefetched | 0.00 |
Bytes loaded | 88.00 |
Bytes stored | 32.00 |
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 | 1.41 |
Bottlenecks | micro-operation queue, |
Function | hypre_ParMatmul_RowSizes.extracted |
Source | par_csr_matop.c:127-127,par_csr_matop.c:135-137,par_csr_matop.c:144-146,par_csr_matop.c:187-187,par_csr_matop.c:241-242 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.17 |
CQA cycles if no scalar integer | 5.17 |
CQA cycles if FP arith vectorized | 5.17 |
CQA cycles if fully vectorized | 0.65 |
Front-end cycles | 5.17 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 1.40 |
P1 cycles | 3.67 |
P2 cycles | 3.67 |
P3 cycles | 2.00 |
P4 cycles | 1.40 |
P5 cycles | 2.00 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 1.20 |
P10 cycles | 3.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 5.31 |
Stall cycles (UFS) | 0.00 |
Nb insns | 30.00 |
Nb uops | 30.00 |
Nb loads | 11.00 |
Nb stores | 4.00 |
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 | 23.23 |
Bytes prefetched | 0.00 |
Bytes loaded | 88.00 |
Bytes stored | 32.00 |
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_RowSizes.extracted |
Source file and lines | par_csr_matop.c:127-242 |
Module | libparcsr_mv.so |
nb instructions | 30 |
nb uops | 30 |
loop length | 116 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 5.17 cycles |
front end | 5.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 1.40 | 3.67 | 3.67 | 2.00 | 1.40 | 2.00 | 2.00 | 2.00 | 2.00 | 1.20 | 3.67 |
cycles | 2.00 | 1.40 | 3.67 | 3.67 | 2.00 | 1.40 | 2.00 | 2.00 | 2.00 | 2.00 | 1.20 | 3.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 5.31 |
Stall cycles | 0.00 |
Front-end | 5.17 |
Dispatch | 3.67 |
Overall L1 | 5.17 |
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) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x78(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x50(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RBX,(%RSI,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x70(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R8,(%RSI,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RAX,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x38(%RBP),%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 9d7c <hypre_ParMatmul_RowSizes.extracted+0x2dc> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x78(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %RSI,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 9bc8 <hypre_ParMatmul_RowSizes.extracted+0x128> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %RBX,(%R14,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%RBX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMPQ $0,0x70(%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 %RDI,-0x50(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JE 9ca0 <hypre_ParMatmul_RowSizes.extracted+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x10(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA 0x1(%RDI),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP 0x8(%RSI,%RDI,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 9ca4 <hypre_ParMatmul_RowSizes.extracted+0x204> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JMP 9c16 <hypre_ParMatmul_RowSizes.extracted+0x176> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RDI),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R8,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x58(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 9cc7 <hypre_ParMatmul_RowSizes.extracted+0x227> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
Function | hypre_ParMatmul_RowSizes.extracted |
Source file and lines | par_csr_matop.c:127-242 |
Module | libparcsr_mv.so |
nb instructions | 30 |
nb uops | 30 |
loop length | 116 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 5.17 cycles |
front end | 5.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 1.40 | 3.67 | 3.67 | 2.00 | 1.40 | 2.00 | 2.00 | 2.00 | 2.00 | 1.20 | 3.67 |
cycles | 2.00 | 1.40 | 3.67 | 3.67 | 2.00 | 1.40 | 2.00 | 2.00 | 2.00 | 2.00 | 1.20 | 3.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 5.31 |
Stall cycles | 0.00 |
Front-end | 5.17 |
Dispatch | 3.67 |
Overall L1 | 5.17 |
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) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x78(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x50(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RBX,(%RSI,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x70(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R8,(%RSI,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RAX,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x38(%RBP),%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 9d7c <hypre_ParMatmul_RowSizes.extracted+0x2dc> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x78(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %RSI,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JE 9bc8 <hypre_ParMatmul_RowSizes.extracted+0x128> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %RBX,(%R14,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%RBX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMPQ $0,0x70(%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 %RDI,-0x50(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JE 9ca0 <hypre_ParMatmul_RowSizes.extracted+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x10(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA 0x1(%RDI),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP 0x8(%RSI,%RDI,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 9ca4 <hypre_ParMatmul_RowSizes.extracted+0x204> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JMP 9c16 <hypre_ParMatmul_RowSizes.extracted+0x176> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
LEA 0x1(%RDI),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R8,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x58(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 9cc7 <hypre_ParMatmul_RowSizes.extracted+0x227> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |