Loop Id: 2991 | Module: exec | Source: csr_matop.c:272-298 | Coverage: 0.01% |
---|
Loop Id: 2991 | Module: exec | Source: csr_matop.c:272-298 | Coverage: 0.01% |
---|
0x5975d0 MOV 0x40(%RSP),%R15 |
0x5975d5 MOV 0x78(%RSP),%R11 |
0x5975da CMPQ $0,0x48(%RSP) |
0x5975e0 MOV (%R15,%R11,8),%R9 |
0x5975e4 JE 5975f9 |
0x5975e6 MOV %RDI,(%RBX,%R11,8) |
0x5975ea MOVQ $0,(%R10,%RDI,8) |
0x5975f2 MOV %R11,(%R14,%RDI,8) |
0x5975f6 INC %RDI |
0x5975f9 MOV 0x68(%RSP),%R8 |
0x5975fe MOV 0x78(%RSP),%RAX |
0x597603 MOV (%R8,%RAX,8),%RCX |
0x597607 MOV 0x8(%R8,%RAX,8),%RDX |
0x59760c CMP %RDX,%RCX |
0x59760f JGE 59768a |
0x597611 NOPL (%RAX) |
(2992) 0x597618 MOV 0x58(%RSP),%R15 |
(2992) 0x59761d MOV 0x70(%RSP),%R8 |
(2992) 0x597622 MOV 0x60(%RSP),%RSI |
(2992) 0x597627 MOV (%R15,%RCX,8),%R11 |
(2992) 0x59762b VMOVSD (%RSI,%RCX,8),%XMM7 |
(2992) 0x597630 LEA 0x8(%R8,%R11,8),%R15 |
(2992) 0x597635 MOV (%R8,%R11,8),%RAX |
(2992) 0x597639 MOV (%R15),%R11 |
(2992) 0x59763c CMP %R11,%RAX |
(2992) 0x59763f JGE 597682 |
(2992) 0x597641 NOPL (%RAX) |
(2993) 0x597648 MOV (%R12,%RAX,8),%RSI |
(2993) 0x59764c VMULSD (%R13,%RAX,8),%XMM7,%XMM8 |
(2993) 0x597653 LEA (%RBX,%RSI,8),%RDX |
(2993) 0x597657 MOV (%RDX),%R8 |
(2993) 0x59765a CMP %R8,%R9 |
(2993) 0x59765d JG 5976d0 |
(2993) 0x59765f LEA (%R10,%R8,8),%RSI |
(2993) 0x597663 INC %RAX |
(2993) 0x597666 VADDSD (%RSI),%XMM8,%XMM9 |
(2993) 0x59766a VMOVSD %XMM9,(%RSI) |
(2993) 0x59766e CMP %RAX,%R11 |
(2993) 0x597671 JG 597648 |
(2992) 0x597673 MOV 0x68(%RSP),%RAX |
(2992) 0x597678 MOV 0x78(%RSP),%R15 |
(2992) 0x59767d MOV 0x8(%RAX,%R15,8),%RDX |
(2992) 0x597682 INC %RCX |
(2992) 0x597685 CMP %RDX,%RCX |
(2992) 0x597688 JL 597618 |
0x59768a INCQ 0x78(%RSP) |
0x59768f MOV 0x78(%RSP),%R9 |
0x597694 CMP %R9,0x50(%RSP) |
0x597699 JNE 5975d0 |
(2993) 0x5976d0 MOV %RDI,(%RDX) |
(2993) 0x5976d3 INC %RAX |
(2993) 0x5976d6 MOV %RSI,(%R14,%RDI,8) |
(2993) 0x5976da INC %RDI |
(2993) 0x5976dd MOV (%RDX),%R11 |
(2993) 0x5976e0 VMOVSD %XMM8,(%R10,%R11,8) |
(2993) 0x5976e6 MOV (%R15),%R11 |
(2993) 0x5976e9 CMP %R11,%RAX |
(2993) 0x5976ec JL 597648 |
(2992) 0x5976f2 JMP 597673 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c: 272 - 298 |
-------------------------------------------------------------------------------- |
272: for (ic = ns; ic < ne; ic++) |
273: { |
274: row_start = C_i[ic]; |
275: if (allsquare) |
276: { |
277: B_marker[ic] = counter; |
278: C_data[counter] = 0; |
279: C_j[counter] = ic; |
280: counter++; |
281: } |
282: for (ia = A_i[ic]; ia < A_i[ic+1]; ia++) |
283: { |
284: ja = A_j[ia]; |
285: a_entry = A_data[ia]; |
286: for (ib = B_i[ja]; ib < B_i[ja+1]; ib++) |
287: { |
288: jb = B_j[ib]; |
289: b_entry = B_data[ib]; |
290: if (B_marker[jb] < row_start) |
291: { |
292: B_marker[jb] = counter; |
293: C_j[B_marker[jb]] = jb; |
294: C_data[B_marker[jb]] = a_entry*b_entry; |
295: counter++; |
296: } |
297: else |
298: C_data[B_marker[jb]] += a_entry*b_entry; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
○100.00 | GOMP_parallel | libgomp.h:985 | 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 | 11.73 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.05 |
Bottlenecks | P2, P3, |
Function | hypre_CSRMatrixMultiply._omp_fn.0 |
Source | csr_matop.c:272-298 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.50 |
CQA cycles if no scalar integer | 5.50 |
CQA cycles if FP arith vectorized | 5.50 |
CQA cycles if fully vectorized | 0.47 |
Front-end cycles | 5.25 |
DIV/SQRT cycles | 1.75 |
P0 cycles | 1.75 |
P1 cycles | 5.50 |
P2 cycles | 5.50 |
P3 cycles | 4.00 |
P4 cycles | 1.75 |
P5 cycles | 1.75 |
P6 cycles | 4.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 5.65 |
Stall cycles (UFS) | 0.45 |
Nb insns | 20.00 |
Nb uops | 21.00 |
Nb loads | 11.00 |
Nb stores | 4.00 |
Nb stack references | 5.00 |
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 | 21.82 |
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 | 11.72 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 10.94 |
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 | 11.73 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.05 |
Bottlenecks | P2, P3, |
Function | hypre_CSRMatrixMultiply._omp_fn.0 |
Source | csr_matop.c:272-298 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.50 |
CQA cycles if no scalar integer | 5.50 |
CQA cycles if FP arith vectorized | 5.50 |
CQA cycles if fully vectorized | 0.47 |
Front-end cycles | 5.25 |
DIV/SQRT cycles | 1.75 |
P0 cycles | 1.75 |
P1 cycles | 5.50 |
P2 cycles | 5.50 |
P3 cycles | 4.00 |
P4 cycles | 1.75 |
P5 cycles | 1.75 |
P6 cycles | 4.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 5.65 |
Stall cycles (UFS) | 0.45 |
Nb insns | 20.00 |
Nb uops | 21.00 |
Nb loads | 11.00 |
Nb stores | 4.00 |
Nb stack references | 5.00 |
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 | 21.82 |
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 | 11.72 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 10.94 |
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_CSRMatrixMultiply._omp_fn.0 |
Source file and lines | csr_matop.c:272-298 |
Module | exec |
nb instructions | 20 |
nb uops | 21 |
loop length | 93 |
used x86 registers | 12 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 5.25 cycles |
front end | 5.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 1.75 | 1.75 | 5.50 | 5.50 | 4.00 | 1.75 | 1.75 | 4.00 |
cycles | 1.75 | 1.75 | 5.50 | 5.50 | 4.00 | 1.75 | 1.75 | 4.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 5.65 |
Stall cycles | 0.45 |
LM full (events) | 1.35 |
Front-end | 5.25 |
Dispatch | 5.50 |
Overall L1 | 5.50 |
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 | 10% |
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 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x40(%RSP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x78(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0,0x48(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV (%R15,%R11,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 5975f9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDI,(%RBX,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVQ $0,(%R10,%RDI,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV %R11,(%R14,%RDI,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x68(%RSP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x78(%RSP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R8,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%R8,%RAX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 59768a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INCQ 0x78(%RSP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
MOV 0x78(%RSP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R9,0x50(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 5975d0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | hypre_CSRMatrixMultiply._omp_fn.0 |
Source file and lines | csr_matop.c:272-298 |
Module | exec |
nb instructions | 20 |
nb uops | 21 |
loop length | 93 |
used x86 registers | 12 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 5.25 cycles |
front end | 5.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 1.75 | 1.75 | 5.50 | 5.50 | 4.00 | 1.75 | 1.75 | 4.00 |
cycles | 1.75 | 1.75 | 5.50 | 5.50 | 4.00 | 1.75 | 1.75 | 4.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 5.65 |
Stall cycles | 0.45 |
LM full (events) | 1.35 |
Front-end | 5.25 |
Dispatch | 5.50 |
Overall L1 | 5.50 |
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 | 10% |
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 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x40(%RSP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x78(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0,0x48(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV (%R15,%R11,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 5975f9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDI,(%RBX,%R11,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVQ $0,(%R10,%RDI,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV %R11,(%R14,%RDI,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x68(%RSP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x78(%RSP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R8,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%R8,%RAX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 59768a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INCQ 0x78(%RSP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
MOV 0x78(%RSP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R9,0x50(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 5975d0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |