Loop Id: 130 | Module: libseq_mv.so | Source: csr_matvec.c:256-263 | Coverage: 10.83% |
---|
Loop Id: 130 | Module: libseq_mv.so | Source: csr_matvec.c:256-263 | Coverage: 10.83% |
---|
0xcc10 SUB %RDX,%RCX |
0xcc13 MOV %RDX,%R15 |
0xcc16 LEA -0x1(%RCX),%RSI |
0xcc1a CMP $0x2,%RSI |
0xcc1e JBE dea4 |
0xcc24 MOV %RCX,%R11 |
0xcc27 LEA (,%RDX,8),%RSI |
0xcc2f VXORPD %XMM1,%XMM1,%XMM1 |
0xcc33 XOR %EAX,%EAX |
0xcc35 SHR $0x2,%R11 |
0xcc39 LEA (%R14,%RSI,1),%R10 |
0xcc3d ADD %R13,%RSI |
0xcc40 SAL $0x5,%R11 |
0xcc44 LEA -0x20(%R11),%RDI |
0xcc48 SHR $0x5,%RDI |
0xcc4c INC %RDI |
0xcc4f AND $0x7,%EDI |
0xcc52 JE cd40 |
0xcc58 CMP $0x1,%RDI |
0xcc5c JE cd1e |
0xcc62 CMP $0x2,%RDI |
0xcc66 JE cd04 |
0xcc6c CMP $0x3,%RDI |
0xcc70 JE ccea |
0xcc72 CMP $0x4,%RDI |
0xcc76 JE ccd0 |
0xcc78 CMP $0x5,%RDI |
0xcc7c JE ccb7 |
0xcc7e CMP $0x6,%RDI |
0xcc82 JE cc9d |
0xcc84 VMOVDQU (%RSI),%YMM9 |
0xcc88 VMOVAPD %YMM15,%YMM10 |
0xcc8d MOV $0x20,%EAX |
0xcc92 VGATHERQPD %YMM10,(%RBX,%YMM9,8),%YMM8 |
0xcc98 VFMADD231PD (%R10),%YMM8,%YMM1 |
0xcc9d VMOVDQU (%RSI,%RAX,1),%YMM14 |
0xcca2 VMOVAPD %YMM15,%YMM13 |
0xcca7 VGATHERQPD %YMM13,(%RBX,%YMM14,8),%YMM0 |
0xccad VFMADD231PD (%R10,%RAX,1),%YMM0,%YMM1 |
0xccb3 ADD $0x20,%RAX |
0xccb7 VMOVDQU (%RSI,%RAX,1),%YMM5 |
0xccbc VMOVAPD %YMM15,%YMM7 |
0xccc0 VGATHERQPD %YMM7,(%RBX,%YMM5,8),%YMM3 |
0xccc6 VFMADD231PD (%R10,%RAX,1),%YMM3,%YMM1 |
0xcccc ADD $0x20,%RAX |
0xccd0 VMOVDQU (%RSI,%RAX,1),%YMM4 |
0xccd5 VMOVAPD %YMM15,%YMM11 |
0xccda VGATHERQPD %YMM11,(%RBX,%YMM4,8),%YMM6 |
0xcce0 VFMADD231PD (%R10,%RAX,1),%YMM6,%YMM1 |
0xcce6 ADD $0x20,%RAX |
0xccea VMOVDQU (%RSI,%RAX,1),%YMM9 |
0xccef VMOVAPD %YMM15,%YMM10 |
0xccf4 VGATHERQPD %YMM10,(%RBX,%YMM9,8),%YMM8 |
0xccfa VFMADD231PD (%R10,%RAX,1),%YMM8,%YMM1 |
0xcd00 ADD $0x20,%RAX |
0xcd04 VMOVDQU (%RSI,%RAX,1),%YMM14 |
0xcd09 VMOVAPD %YMM15,%YMM13 |
0xcd0e VGATHERQPD %YMM13,(%RBX,%YMM14,8),%YMM0 |
0xcd14 VFMADD231PD (%R10,%RAX,1),%YMM0,%YMM1 |
0xcd1a ADD $0x20,%RAX |
0xcd1e VMOVDQU (%RSI,%RAX,1),%YMM7 |
0xcd23 VMOVAPD %YMM15,%YMM5 |
0xcd27 VGATHERQPD %YMM5,(%RBX,%YMM7,8),%YMM3 |
0xcd2d VFMADD231PD (%R10,%RAX,1),%YMM3,%YMM1 |
0xcd33 ADD $0x20,%RAX |
0xcd37 CMP %RAX,%R11 |
0xcd3a JE ce21 |
(131) 0xcd40 VMOVDQU (%RSI,%RAX,1),%YMM4 |
(131) 0xcd45 VMOVDQU 0x20(%RSI,%RAX,1),%YMM9 |
(131) 0xcd4b VMOVAPD %YMM15,%YMM11 |
(131) 0xcd50 VMOVAPD %YMM15,%YMM10 |
(131) 0xcd55 VMOVDQU 0x40(%RSI,%RAX,1),%YMM14 |
(131) 0xcd5b VMOVAPD %YMM15,%YMM13 |
(131) 0xcd60 VMOVAPD %YMM15,%YMM7 |
(131) 0xcd64 VMOVAPD %YMM15,%YMM3 |
(131) 0xcd68 VGATHERQPD %YMM11,(%RBX,%YMM4,8),%YMM6 |
(131) 0xcd6e VFMADD231PD (%R10,%RAX,1),%YMM6,%YMM1 |
(131) 0xcd74 VMOVDQU 0x60(%RSI,%RAX,1),%YMM5 |
(131) 0xcd7a VGATHERQPD %YMM10,(%RBX,%YMM9,8),%YMM8 |
(131) 0xcd80 VFMADD231PD 0x20(%R10,%RAX,1),%YMM8,%YMM1 |
(131) 0xcd87 VMOVAPD %YMM15,%YMM4 |
(131) 0xcd8b VGATHERQPD %YMM13,(%RBX,%YMM14,8),%YMM0 |
(131) 0xcd91 VMOVDQU 0x80(%RSI,%RAX,1),%YMM11 |
(131) 0xcd9a VFMADD132PD 0x40(%R10,%RAX,1),%YMM1,%YMM0 |
(131) 0xcda1 VMOVAPD %YMM15,%YMM8 |
(131) 0xcda6 VMOVDQU 0xa0(%RSI,%RAX,1),%YMM10 |
(131) 0xcdaf VGATHERQPD %YMM7,(%RBX,%YMM5,8),%YMM1 |
(131) 0xcdb5 VMOVDQU 0xc0(%RSI,%RAX,1),%YMM13 |
(131) 0xcdbe VFMADD132PD 0x60(%R10,%RAX,1),%YMM0,%YMM1 |
(131) 0xcdc5 VGATHERQPD %YMM3,(%RBX,%YMM11,8),%YMM6 |
(131) 0xcdcb VMOVAPD %YMM15,%YMM0 |
(131) 0xcdcf VFMADD132PD 0x80(%R10,%RAX,1),%YMM1,%YMM6 |
(131) 0xcdd9 VMOVDQU 0xe0(%RSI,%RAX,1),%YMM7 |
(131) 0xcde2 VGATHERQPD %YMM4,(%RBX,%YMM10,8),%YMM9 |
(131) 0xcde8 VFMADD132PD 0xa0(%R10,%RAX,1),%YMM6,%YMM9 |
(131) 0xcdf2 VGATHERQPD %YMM8,(%RBX,%YMM13,8),%YMM14 |
(131) 0xcdf8 VFMADD132PD 0xc0(%R10,%RAX,1),%YMM9,%YMM14 |
(131) 0xce02 VGATHERQPD %YMM0,(%RBX,%YMM7,8),%YMM1 |
(131) 0xce08 VFMADD132PD 0xe0(%R10,%RAX,1),%YMM14,%YMM1 |
(131) 0xce12 ADD $0x100,%RAX |
(131) 0xce18 CMP %RAX,%R11 |
(131) 0xce1b JNE cd40 |
0xce21 VEXTRACTF128 $0x1,%YMM1,%XMM3 |
0xce27 VADDPD %XMM1,%XMM3,%XMM5 |
0xce2b VUNPCKHPD %XMM5,%XMM5,%XMM11 |
0xce2f VADDPD %XMM5,%XMM11,%XMM8 |
0xce33 TEST $0x3,%CL |
0xce36 JE ce8f |
0xce38 MOV %RCX,%R10 |
0xce3b VADDPD %XMM1,%XMM3,%XMM6 |
0xce3f AND $-0x4,%R10 |
0xce43 ADD %R10,%RDX |
0xce46 SUB %R10,%RCX |
0xce49 CMP $0x1,%RCX |
0xce4d JE ce7f |
0xce4f ADD %R15,%R10 |
0xce52 VMOVAPD %XMM12,%XMM4 |
0xce56 VMOVDQU (%R13,%R10,8),%XMM10 |
0xce5d VGATHERQPD %XMM4,(%RBX,%XMM10,8),%XMM9 |
0xce63 VFMADD132PD (%R14,%R10,8),%XMM6,%XMM9 |
0xce69 VUNPCKHPD %XMM9,%XMM9,%XMM6 |
0xce6e VADDPD %XMM9,%XMM6,%XMM8 |
0xce73 TEST $0x1,%CL |
0xce76 JE ce8f |
0xce78 AND $-0x2,%RCX |
0xce7c ADD %RCX,%RDX |
0xce7f MOV (%R13,%RDX,8),%RCX |
0xce84 VMOVSD (%RBX,%RCX,8),%XMM13 |
0xce89 VFMADD231SD (%R14,%RDX,8),%XMM13,%XMM8 |
0xce8f MOV 0x38(%RSP),%RDX |
0xce94 VMOVSD %XMM8,(%RDX,%R12,8) |
0xce9a INC %R12 |
0xce9d CMP %R12,%R9 |
0xcea0 JE cbc8 |
0xcea6 MOV (%R8,%R12,8),%RDX |
0xceaa MOV 0x8(%R8,%R12,8),%RCX |
0xceaf CMP %RDX,%RCX |
0xceb2 JG cc10 |
0xdea4 VMOVSD %XMM2,%XMM2,%XMM8 |
0xdea8 VXORPD %XMM6,%XMM6,%XMM6 |
0xdeac XOR %R10D,%R10D |
0xdeaf JMP ce46 |
/home/eoseret/qaas_runs_CPU_9468/172-019-1763/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c: 256 - 263 |
-------------------------------------------------------------------------------- |
256: for (i = iBegin; i < iEnd; i++) |
257: { |
258: tempx = 0.0; |
259: for (jj = A_i[i]; jj < A_i[i+1]; jj++) |
260: { |
261: tempx += A_data[jj] * x_data[A_j[jj]]; |
262: } |
263: y_data[i] = tempx; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
○95.76 | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
○4.24 | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.15 |
CQA speedup if FP arith vectorized | 2.19 |
CQA speedup if fully vectorized | 4.27 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.44 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6 |
Source | csr_matvec.c:256-263 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 47.50 |
CQA cycles if no scalar integer | 41.17 |
CQA cycles if FP arith vectorized | 21.72 |
CQA cycles if fully vectorized | 11.13 |
Front-end cycles | 47.50 |
DIV/SQRT cycles | 11.50 |
P0 cycles | 11.50 |
P1 cycles | 11.25 |
P2 cycles | 11.25 |
P3 cycles | 7.50 |
P4 cycles | 7.67 |
P5 cycles | 7.67 |
P6 cycles | 7.67 |
P7 cycles | 19.50 |
P8 cycles | 19.50 |
P9 cycles | 19.00 |
P10 cycles | 19.00 |
P11 cycles | 19.50 |
P12 cycles | 19.50 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 107.00 |
Nb uops | 285.00 |
Nb loads | 30.00 |
Nb stores | 1.00 |
Nb stack references | 1.00 |
FLOP/cycle | 1.47 |
Nb FLOP add-sub | 8.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 31.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 16.34 |
Bytes prefetched | 0.00 |
Bytes loaded | 768.00 |
Bytes stored | 8.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 66.10 |
Vectorization ratio load | 92.31 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 80.00 |
Vectorization ratio fma | 88.89 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 54.29 |
Vector-efficiency ratio all | 32.52 |
Vector-efficiency ratio load | 44.23 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 22.50 |
Vector-efficiency ratio fma | 43.06 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 29.11 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.15 |
CQA speedup if FP arith vectorized | 2.19 |
CQA speedup if fully vectorized | 4.27 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.44 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6 |
Source | csr_matvec.c:256-263 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 47.50 |
CQA cycles if no scalar integer | 41.17 |
CQA cycles if FP arith vectorized | 21.72 |
CQA cycles if fully vectorized | 11.13 |
Front-end cycles | 47.50 |
DIV/SQRT cycles | 11.50 |
P0 cycles | 11.50 |
P1 cycles | 11.25 |
P2 cycles | 11.25 |
P3 cycles | 7.50 |
P4 cycles | 7.67 |
P5 cycles | 7.67 |
P6 cycles | 7.67 |
P7 cycles | 19.50 |
P8 cycles | 19.50 |
P9 cycles | 19.00 |
P10 cycles | 19.00 |
P11 cycles | 19.50 |
P12 cycles | 19.50 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 107.00 |
Nb uops | 285.00 |
Nb loads | 30.00 |
Nb stores | 1.00 |
Nb stack references | 1.00 |
FLOP/cycle | 1.47 |
Nb FLOP add-sub | 8.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 31.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 16.34 |
Bytes prefetched | 0.00 |
Bytes loaded | 768.00 |
Bytes stored | 8.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 66.10 |
Vectorization ratio load | 92.31 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 80.00 |
Vectorization ratio fma | 88.89 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 54.29 |
Vector-efficiency ratio all | 32.52 |
Vector-efficiency ratio load | 44.23 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 22.50 |
Vector-efficiency ratio fma | 43.06 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 29.11 |
Path / |
Function | hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6 |
Source file and lines | csr_matvec.c:256-263 |
Module | libseq_mv.so |
nb instructions | 107 |
nb uops | 285 |
loop length | 471 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 12 |
used ymm registers | 14 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 47.50 cycles |
front end | 47.50 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 11.50 | 11.50 | 11.25 | 11.25 | 7.50 | 7.67 | 7.67 | 7.67 | 19.50 | 19.50 | 19.00 | 19.00 | 19.50 | 19.50 |
cycles | 11.50 | 11.50 | 11.25 | 11.25 | 7.50 | 7.67 | 7.67 | 7.67 | 19.50 | 19.50 | 19.00 | 19.00 | 19.50 | 19.50 |
Cycles executing div or sqrt instructions | NA |
Front-end | 47.50 |
Dispatch | 19.50 |
Overall L1 | 47.50 |
all | 36% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 83% |
load | 88% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 88% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 86% |
all | 66% |
load | 92% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 80% |
fma | 88% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 54% |
all | 24% |
load | 46% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 37% |
load | 43% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | 43% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 39% |
all | 32% |
load | 44% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 22% |
fma | 43% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 29% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SUB %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %RDX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | scal (12.5%) |
LEA -0x1(%RCX),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP $0x2,%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JBE dea4 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x16a4> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV %RCX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
LEA (,%RDX,8),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | N/A |
SHR $0x2,%R11 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
LEA (%R14,%RSI,1),%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
ADD %R13,%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
SAL $0x5,%R11 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
LEA -0x20(%R11),%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
SHR $0x5,%RDI | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
INC %RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
AND $0x7,%EDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (6.3%) |
JE cd40 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x540> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x1,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE cd1e <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x51e> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x2,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE cd04 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x504> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x3,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ccea <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x4ea> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x4,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ccd0 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x4d0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x5,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ccb7 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x4b7> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x6,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE cc9d <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x49d> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
VMOVDQU (%RSI),%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
MOV $0x20,%EAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VGATHERQPD %YMM10,(%RBX,%YMM9,8),%YMM8 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10),%YMM8,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
VMOVDQU (%RSI,%RAX,1),%YMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM13,(%RBX,%YMM14,8),%YMM0 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM0,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM7,(%RBX,%YMM5,8),%YMM3 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM3,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM11,(%RBX,%YMM4,8),%YMM6 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM6,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM10,(%RBX,%YMM9,8),%YMM8 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM8,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM13,(%RBX,%YMM14,8),%YMM0 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM0,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM5,(%RBX,%YMM7,8),%YMM3 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM3,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP %RAX,%R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ce21 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x621> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
VEXTRACTF128 $0x1,%YMM1,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 | vect (25.0%) |
VADDPD %XMM1,%XMM3,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
VUNPCKHPD %XMM5,%XMM5,%XMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | scal (12.5%) |
VADDPD %XMM5,%XMM11,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
TEST $0x3,%CL | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JE ce8f <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x68f> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV %RCX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
VADDPD %XMM1,%XMM3,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
AND $-0x4,%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
ADD %R10,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
SUB %R10,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP $0x1,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ce7f <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x67f> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
ADD %R15,%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVAPD %XMM12,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
VMOVDQU (%R13,%R10,8),%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
VGATHERQPD %XMM4,(%RBX,%XMM10,8),%XMM9 | 18 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.25 | 1.58 | 0.58 | 0.58 | 1.50 | 1.50 | 0-16 | 3 | vect (25.0%) |
VFMADD132PD (%R14,%R10,8),%XMM6,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (25.0%) |
VUNPCKHPD %XMM9,%XMM9,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | scal (12.5%) |
VADDPD %XMM9,%XMM6,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
TEST $0x1,%CL | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JE ce8f <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x68f> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
AND $-0x2,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
ADD %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV (%R13,%RDX,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VMOVSD (%RBX,%RCX,8),%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
VFMADD231SD (%R14,%RDX,8),%XMM13,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
MOV 0x38(%RSP),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VMOVSD %XMM8,(%RDX,%R12,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 | scal (12.5%) |
INC %R12 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP %R12,%R9 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE cbc8 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x3c8> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV (%R8,%R12,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV 0x8(%R8,%R12,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JG cc10 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x410> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
VMOVSD %XMM2,%XMM2,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
VXORPD %XMM6,%XMM6,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | N/A |
JMP ce46 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x646> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | N/A |
Function | hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6 |
Source file and lines | csr_matvec.c:256-263 |
Module | libseq_mv.so |
nb instructions | 107 |
nb uops | 285 |
loop length | 471 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 12 |
used ymm registers | 14 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 47.50 cycles |
front end | 47.50 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 11.50 | 11.50 | 11.25 | 11.25 | 7.50 | 7.67 | 7.67 | 7.67 | 19.50 | 19.50 | 19.00 | 19.00 | 19.50 | 19.50 |
cycles | 11.50 | 11.50 | 11.25 | 11.25 | 7.50 | 7.67 | 7.67 | 7.67 | 19.50 | 19.50 | 19.00 | 19.00 | 19.50 | 19.50 |
Cycles executing div or sqrt instructions | NA |
Front-end | 47.50 |
Dispatch | 19.50 |
Overall L1 | 47.50 |
all | 36% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 83% |
load | 88% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 88% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 86% |
all | 66% |
load | 92% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 80% |
fma | 88% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 54% |
all | 24% |
load | 46% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 37% |
load | 43% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | 43% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 39% |
all | 32% |
load | 44% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 22% |
fma | 43% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 29% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SUB %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %RDX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | scal (12.5%) |
LEA -0x1(%RCX),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP $0x2,%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JBE dea4 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x16a4> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV %RCX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
LEA (,%RDX,8),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | N/A |
SHR $0x2,%R11 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
LEA (%R14,%RSI,1),%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
ADD %R13,%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
SAL $0x5,%R11 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
LEA -0x20(%R11),%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
SHR $0x5,%RDI | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
INC %RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
AND $0x7,%EDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (6.3%) |
JE cd40 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x540> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x1,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE cd1e <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x51e> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x2,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE cd04 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x504> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x3,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ccea <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x4ea> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x4,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ccd0 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x4d0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x5,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ccb7 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x4b7> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
CMP $0x6,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE cc9d <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x49d> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
VMOVDQU (%RSI),%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
MOV $0x20,%EAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VGATHERQPD %YMM10,(%RBX,%YMM9,8),%YMM8 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10),%YMM8,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
VMOVDQU (%RSI,%RAX,1),%YMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM13,(%RBX,%YMM14,8),%YMM0 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM0,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM7,(%RBX,%YMM5,8),%YMM3 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM3,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM11,(%RBX,%YMM4,8),%YMM6 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM6,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM10,(%RBX,%YMM9,8),%YMM8 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM8,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM13,(%RBX,%YMM14,8),%YMM0 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM0,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVDQU (%RSI,%RAX,1),%YMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (50.0%) |
VMOVAPD %YMM15,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (50.0%) |
VGATHERQPD %YMM5,(%RBX,%YMM7,8),%YMM3 | 24 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 3 | 1.50 | 1.50 | 2.50 | 2.50 | 0-16 | 4 | vect (50.0%) |
VFMADD231PD (%R10,%RAX,1),%YMM3,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (50.0%) |
ADD $0x20,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP %RAX,%R11 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ce21 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x621> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
VEXTRACTF128 $0x1,%YMM1,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 | vect (25.0%) |
VADDPD %XMM1,%XMM3,%XMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
VUNPCKHPD %XMM5,%XMM5,%XMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | scal (12.5%) |
VADDPD %XMM5,%XMM11,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
TEST $0x3,%CL | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JE ce8f <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x68f> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV %RCX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
VADDPD %XMM1,%XMM3,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
AND $-0x4,%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
ADD %R10,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
SUB %R10,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP $0x1,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE ce7f <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x67f> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
ADD %R15,%R10 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
VMOVAPD %XMM12,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
VMOVDQU (%R13,%R10,8),%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
VGATHERQPD %XMM4,(%RBX,%XMM10,8),%XMM9 | 18 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.25 | 1.58 | 0.58 | 0.58 | 1.50 | 1.50 | 0-16 | 3 | vect (25.0%) |
VFMADD132PD (%R14,%R10,8),%XMM6,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | vect (25.0%) |
VUNPCKHPD %XMM9,%XMM9,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | scal (12.5%) |
VADDPD %XMM9,%XMM6,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | vect (25.0%) |
TEST $0x1,%CL | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JE ce8f <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x68f> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
AND $-0x2,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
ADD %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV (%R13,%RDX,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VMOVSD (%RBX,%RCX,8),%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
VFMADD231SD (%R14,%RDX,8),%XMM13,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
MOV 0x38(%RSP),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VMOVSD %XMM8,(%RDX,%R12,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 | scal (12.5%) |
INC %R12 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP %R12,%R9 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE cbc8 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x3c8> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV (%R8,%R12,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV 0x8(%R8,%R12,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JG cc10 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x410> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
VMOVSD %XMM2,%XMM2,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
VXORPD %XMM6,%XMM6,%XMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | N/A |
JMP ce46 <hypre_CSRMatrixMatvecOutOfPlace._omp_fn.6+0x646> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | N/A |