Loop Id: 4312 | Module: exec | Source: csr_matvec.c:248-263 [...] | Coverage: 0.72% |
---|
Loop Id: 4312 | Module: exec | Source: csr_matvec.c:248-263 [...] | Coverage: 0.72% |
---|
0x4de260 MOV 0x30(%RBP),%RAX |
0x4de264 VMOVSD %XMM0,(%RAX,%RDI,8) |
0x4de269 LEA 0x1(%RSI),%RAX |
0x4de26d CMP %R15,%RSI |
0x4de270 MOV %RAX,%RSI |
0x4de273 JE 4dee9c |
0x4de279 LEA (%R12,%RSI,1),%RDI |
0x4de27d MOV (%RBX,%RDI,8),%R10 |
0x4de281 MOV 0x8(%RBX,%RDI,8),%R8 |
0x4de286 VXORPD %XMM0,%XMM0,%XMM0 |
0x4de28a MOV %R8,%R11 |
0x4de28d SUB %R10,%R11 |
0x4de290 JLE 4de260 |
0x4de292 MOV %R11,%R9 |
0x4de295 AND $-0x4,%R9 |
0x4de299 JE 4de30e |
0x4de29b MOV %R15,%RBX |
0x4de29e LEA -0x1(%R9),%R15 |
0x4de2a2 LEA (%R14,%R10,8),%R13 |
0x4de2a6 LEA (%RDX,%R10,8),%RAX |
0x4de2aa VXORPD %XMM0,%XMM0,%XMM0 |
0x4de2ae XOR %R12D,%R12D |
0x4de2b1 NOPW %CS:(%RAX,%RAX,1) |
(4314) 0x4de2c0 VMOVUPD (%RAX,%R12,8),%YMM1 |
(4314) 0x4de2c6 KXNORW %K0,%K0,%K1 |
(4314) 0x4de2ca VXORPD %XMM2,%XMM2,%XMM2 |
(4314) 0x4de2ce VGATHERQPD (%RCX,%YMM1,8),%YMM2{%K1} |
(4314) 0x4de2d5 VFMADD231PD (%R13,%R12,8),%YMM2,%YMM0 |
(4314) 0x4de2dc ADD $0x4,%R12 |
(4314) 0x4de2e0 CMP %R15,%R12 |
(4314) 0x4de2e3 JBE 4de2c0 |
0x4de2e5 VEXTRACTF128 $0x1,%YMM0,%XMM1 |
0x4de2eb VADDPD %XMM1,%XMM0,%XMM0 |
0x4de2ef VSHUFPD $0x1,%XMM0,%XMM0,%XMM1 |
0x4de2f4 VADDSD %XMM1,%XMM0,%XMM0 |
0x4de2f8 CMP %R9,%R11 |
0x4de2fb MOV -0x38(%RBP),%R12 |
0x4de2ff MOV %RBX,%R15 |
0x4de302 MOV -0x30(%RBP),%RBX |
0x4de306 JE 4de260 |
0x4de30c JMP 4de311 |
0x4de30e XOR %R9D,%R9D |
0x4de311 ADD %R10,%R9 |
0x4de314 NOPW %CS:(%RAX,%RAX,1) |
(4313) 0x4de320 MOV (%RDX,%R9,8),%RAX |
(4313) 0x4de324 VMOVSD (%RCX,%RAX,8),%XMM1 |
(4313) 0x4de329 VFMADD231SD (%R14,%R9,8),%XMM1,%XMM0 |
(4313) 0x4de32f INC %R9 |
(4313) 0x4de332 CMP %R9,%R8 |
(4313) 0x4de335 JNE 4de320 |
0x4de337 JMP 4de260 |
/home/eoseret/qaas_runs_CPU_9468/171-716-5699/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c: 248 - 263 |
-------------------------------------------------------------------------------- |
248: hypre_assert(iBegin <= iEnd); |
[...] |
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; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.85 |
CQA speedup if FP arith vectorized | 1.95 |
CQA speedup if fully vectorized | 7.55 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.22 |
Bottlenecks | |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source | csr_matvec.c:248-248,csr_matvec.c:256-256,csr_matvec.c:259-263 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.17 |
CQA cycles if no scalar integer | 2.25 |
CQA cycles if FP arith vectorized | 2.14 |
CQA cycles if fully vectorized | 0.55 |
Front-end cycles | 4.17 |
DIV/SQRT cycles | 1.88 |
P0 cycles | 1.70 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.50 |
P4 cycles | 1.70 |
P5 cycles | 1.88 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 1.60 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 6.43 |
Stall cycles (UFS) | 1.79 |
Nb insns | 25.25 |
Nb uops | 25.00 |
Nb loads | 4.00 |
Nb stores | 1.00 |
Nb stack references | 2.00 |
FLOP/cycle | 0.36 |
Nb FLOP add-sub | 1.50 |
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 | 10.65 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
Bytes stored | 8.00 |
Stride 0 | 1.50 |
Stride 1 | 1.00 |
Stride n | 1.75 |
Stride unknown | 1.75 |
Stride indirect | 0.00 |
Vectorization ratio all | 32.53 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 27.78 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 50.00 |
Vector-efficiency ratio all | 16.57 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 15.97 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 18.75 |
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 | 2.00 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source | csr_matvec.c:248-248,csr_matvec.c:256-256,csr_matvec.c:259-263 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.00 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 0.25 |
Front-end cycles | 2.00 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.40 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 0.50 |
P4 cycles | 0.40 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.20 |
P10 cycles | 1.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 2.12 |
Stall cycles (UFS) | 0.00 |
Nb insns | 13.00 |
Nb uops | 12.00 |
Nb loads | 3.00 |
Nb stores | 1.00 |
Nb stack references | 1.00 |
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 | 16.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 24.00 |
Bytes stored | 8.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 25.00 |
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 | 50.00 |
Vector-efficiency ratio all | 15.63 |
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 | 18.75 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.67 |
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 | 2.22 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source | csr_matvec.c:248-248,csr_matvec.c:256-256,csr_matvec.c:259-263 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.33 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 3.33 |
CQA cycles if fully vectorized | 0.42 |
Front-end cycles | 3.33 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.40 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 0.50 |
P4 cycles | 1.40 |
P5 cycles | 1.50 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 1.20 |
P10 cycles | 1.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 3.45 |
Stall cycles (UFS) | 0.00 |
Nb insns | 20.00 |
Nb uops | 20.00 |
Nb loads | 3.00 |
Nb stores | 1.00 |
Nb stack references | 1.00 |
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 | 9.60 |
Bytes prefetched | 0.00 |
Bytes loaded | 24.00 |
Bytes stored | 8.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 3.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 16.67 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 33.33 |
Vector-efficiency ratio all | 14.58 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 16.67 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.40 |
CQA speedup if FP arith vectorized | 3.35 |
CQA speedup if fully vectorized | 7.38 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.31 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source | csr_matvec.c:248-248,csr_matvec.c:256-256,csr_matvec.c:259-263 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 6.00 |
CQA cycles if no scalar integer | 2.50 |
CQA cycles if FP arith vectorized | 1.79 |
CQA cycles if fully vectorized | 0.81 |
Front-end cycles | 6.00 |
DIV/SQRT cycles | 2.60 |
P0 cycles | 2.60 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 0.50 |
P4 cycles | 2.60 |
P5 cycles | 2.60 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 2.60 |
P10 cycles | 1.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 10.09 |
Stall cycles (UFS) | 3.24 |
Nb insns | 36.00 |
Nb uops | 36.00 |
Nb loads | 5.00 |
Nb stores | 1.00 |
Nb stack references | 3.00 |
FLOP/cycle | 0.50 |
Nb FLOP add-sub | 3.00 |
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 | 8.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 40.00 |
Bytes stored | 8.00 |
Stride 0 | 2.00 |
Stride 1 | 2.00 |
Stride n | 2.00 |
Stride unknown | 3.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 38.46 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 33.33 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 50.00 |
Vector-efficiency ratio all | 17.31 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 16.67 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 18.75 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.13 |
CQA speedup if FP arith vectorized | 3.76 |
CQA speedup if fully vectorized | 7.31 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.22 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source | csr_matvec.c:248-248,csr_matvec.c:256-256,csr_matvec.c:259-263 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.33 |
CQA cycles if no scalar integer | 2.50 |
CQA cycles if FP arith vectorized | 1.42 |
CQA cycles if fully vectorized | 0.73 |
Front-end cycles | 5.33 |
DIV/SQRT cycles | 2.40 |
P0 cycles | 2.40 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 0.50 |
P4 cycles | 2.40 |
P5 cycles | 2.40 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 2.40 |
P10 cycles | 1.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 10.08 |
Stall cycles (UFS) | 3.90 |
Nb insns | 32.00 |
Nb uops | 32.00 |
Nb loads | 5.00 |
Nb stores | 1.00 |
Nb stack references | 3.00 |
FLOP/cycle | 0.56 |
Nb FLOP add-sub | 3.00 |
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 | 9.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 40.00 |
Bytes stored | 8.00 |
Stride 0 | 2.00 |
Stride 1 | 2.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 50.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 50.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 66.67 |
Vector-efficiency ratio all | 18.75 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 18.75 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 20.83 |
Path / |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source file and lines | csr_matvec.c:248-263 |
Module | exec |
nb instructions | 25.25 |
nb uops | 25 |
loop length | 106 |
used x86 registers | 12.25 |
used mmx registers | 0 |
used xmm registers | 1.50 |
used ymm registers | 0.50 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 4.17 cycles |
front end | 4.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.88 | 1.70 | 1.33 | 1.33 | 0.50 | 1.70 | 1.88 | 0.50 | 0.50 | 0.50 | 1.60 | 1.33 |
cycles | 1.88 | 1.70 | 1.33 | 1.33 | 0.50 | 1.70 | 1.88 | 0.50 | 0.50 | 0.50 | 1.60 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 6.44 |
Stall cycles | 1.79 |
ROB full (events) | 2.06 |
Front-end | 4.17 |
Dispatch | 1.88 |
Data deps. | 2.00 |
Overall L1 | 4.17 |
all | 0% |
load | 0% |
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 | 60% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 32% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 27% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
all | 12% |
load | 12% |
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 | 20% |
load | NA (no load vectorizable/vectorized instructions) |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 16% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 15% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 18% |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source file and lines | csr_matvec.c:248-263 |
Module | exec |
nb instructions | 13 |
nb uops | 12 |
loop length | 50 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 2.00 cycles |
front end | 2.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.40 | 1.00 | 1.00 | 0.50 | 0.40 | 1.00 | 0.50 | 0.50 | 0.50 | 0.20 | 1.00 |
cycles | 1.00 | 0.40 | 1.00 | 1.00 | 0.50 | 0.40 | 1.00 | 0.50 | 0.50 | 0.50 | 0.20 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 2.12 |
Stall cycles | 0.00 |
Front-end | 2.00 |
Dispatch | 1.00 |
Data deps. | 2.00 |
Overall L1 | 2.00 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 50% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 100% |
all | 25% |
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 | 50% |
all | 12% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 18% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 25% |
all | 15% |
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 | 18% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x30(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM0,(%RAX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%RSI),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %R15,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 4dee9c <hypre_CSRMatrixMatvecOutOfPlace.extracted+0xd6c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA (%R12,%RSI,1),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV (%RBX,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RBX,%RDI,8),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R8,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB %R10,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 4de260 <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x130> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source file and lines | csr_matvec.c:248-263 |
Module | exec |
nb instructions | 20 |
nb uops | 20 |
loop length | 82 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 3.33 cycles |
front end | 3.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.40 | 1.00 | 1.00 | 0.50 | 1.40 | 1.50 | 0.50 | 0.50 | 0.50 | 1.20 | 1.00 |
cycles | 1.50 | 1.40 | 1.00 | 1.00 | 0.50 | 1.40 | 1.50 | 0.50 | 0.50 | 0.50 | 1.20 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 3.45 |
Stall cycles | 0.00 |
Front-end | 3.33 |
Dispatch | 1.50 |
Data deps. | 2.00 |
Overall L1 | 3.33 |
all | 0% |
load | 0% |
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 | 50% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 100% |
all | 16% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 33% |
all | 12% |
load | 12% |
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 | 18% |
load | NA (no load vectorizable/vectorized instructions) |
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 | 25% |
all | 14% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 16% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x30(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM0,(%RAX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%RSI),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %R15,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 4dee9c <hypre_CSRMatrixMatvecOutOfPlace.extracted+0xd6c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA (%R12,%RSI,1),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV (%RBX,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RBX,%RDI,8),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R8,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB %R10,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 4de260 <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x130> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R11,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
AND $-0x4,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
JE 4de30e <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x1de> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
ADD %R10,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 4de260 <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x130> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source file and lines | csr_matvec.c:248-263 |
Module | exec |
nb instructions | 36 |
nb uops | 36 |
loop length | 157 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 6.00 cycles |
front end | 6.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.60 | 2.60 | 1.67 | 1.67 | 0.50 | 2.60 | 2.60 | 0.50 | 0.50 | 0.50 | 2.60 | 1.67 |
cycles | 2.60 | 2.60 | 1.67 | 1.67 | 0.50 | 2.60 | 2.60 | 0.50 | 0.50 | 0.50 | 2.60 | 1.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 10.09 |
Stall cycles | 3.24 |
ROB full (events) | 4.06 |
Front-end | 6.00 |
Dispatch | 2.60 |
Data deps. | 2.00 |
Overall L1 | 6.00 |
all | 0% |
load | 0% |
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 | 71% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 38% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
all | 12% |
load | 12% |
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 | 21% |
load | NA (no load vectorizable/vectorized instructions) |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 17% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 16% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 18% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x30(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM0,(%RAX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%RSI),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %R15,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 4dee9c <hypre_CSRMatrixMatvecOutOfPlace.extracted+0xd6c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA (%R12,%RSI,1),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV (%RBX,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RBX,%RDI,8),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R8,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB %R10,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 4de260 <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x130> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R11,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
AND $-0x4,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
JE 4de30e <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x1de> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R15,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
LEA -0x1(%R9),%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
LEA (%R14,%R10,8),%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
LEA (%RDX,%R10,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VEXTRACTF128 $0x1,%YMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPD %XMM1,%XMM0,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDSD %XMM1,%XMM0,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
CMP %R9,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x38(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RBX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x30(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JE 4de260 <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x130> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 4de311 <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x1e1> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
ADD %R10,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 4de260 <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x130> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | hypre_CSRMatrixMatvecOutOfPlace.extracted |
Source file and lines | csr_matvec.c:248-263 |
Module | exec |
nb instructions | 32 |
nb uops | 32 |
loop length | 135 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 5.33 cycles |
front end | 5.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.40 | 2.40 | 1.67 | 1.67 | 0.50 | 2.40 | 2.40 | 0.50 | 0.50 | 0.50 | 2.40 | 1.67 |
cycles | 2.40 | 2.40 | 1.67 | 1.67 | 0.50 | 2.40 | 2.40 | 0.50 | 0.50 | 0.50 | 2.40 | 1.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 10.08 |
Stall cycles | 3.90 |
ROB full (events) | 4.19 |
Front-end | 5.33 |
Dispatch | 2.40 |
Data deps. | 2.00 |
Overall L1 | 5.33 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 71% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 50% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 66% |
all | 12% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 21% |
load | NA (no load vectorizable/vectorized instructions) |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 18% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 20% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x30(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM0,(%RAX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%RSI),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %R15,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 4dee9c <hypre_CSRMatrixMatvecOutOfPlace.extracted+0xd6c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
LEA (%R12,%RSI,1),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV (%RBX,%RDI,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RBX,%RDI,8),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R8,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SUB %R10,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 4de260 <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x130> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R11,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
AND $-0x4,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
JE 4de30e <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x1de> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R15,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
LEA -0x1(%R9),%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
LEA (%R14,%R10,8),%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
LEA (%RDX,%R10,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VEXTRACTF128 $0x1,%YMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VADDPD %XMM1,%XMM0,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDSD %XMM1,%XMM0,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
CMP %R9,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x38(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RBX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x30(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JE 4de260 <hypre_CSRMatrixMatvecOutOfPlace.extracted+0x130> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |