Loop Id: 3938 | Module: exec | Source: ams.c:3532-3534 | Coverage: 0.05% |
---|
Loop Id: 3938 | Module: exec | Source: ams.c:3532-3534 | Coverage: 0.05% |
---|
0x522d70 ADD $0x20,%RDI |
0x522d74 DEC %RSI |
0x522d77 JE 522c54 |
0x522d7d MOV -0xd8(%RBP),%R9 [3] |
0x522d84 MOV -0x10(%R9,%RDI,1),%R8 [7] |
0x522d89 UCOMISD (%R13,%R8,8),%XMM3 [1] |
0x522d90 JBE 522df0 |
0x522d92 MOV -0x88(%RBP),%R8 [3] |
0x522d99 MOVSD -0x10(%R8,%RDI,1),%XMM0 [5] |
0x522da0 XORPD %XMM4,%XMM0 |
0x522da4 MOVLPD %XMM0,-0x10(%R8,%RDI,1) [5] |
0x522dab MOV -0x8(%R9,%RDI,1),%R8 [7] |
0x522db0 UCOMISD (%R13,%R8,8),%XMM3 [4] |
0x522db7 JA 522dfe |
0x522db9 MOV (%R9,%RDI,1),%R8 [7] |
0x522dbd UCOMISD (%R13,%R8,8),%XMM3 [2] |
0x522dc4 JBE 522e24 |
0x522dc6 MOV -0x88(%RBP),%R8 [3] |
0x522dcd MOVSD (%R8,%RDI,1),%XMM0 [5] |
0x522dd3 XORPD %XMM4,%XMM0 |
0x522dd7 MOVLPD %XMM0,(%R8,%RDI,1) [5] |
0x522ddd MOV 0x8(%R9,%RDI,1),%R8 [7] |
0x522de2 UCOMISD (%R13,%R8,8),%XMM3 [6] |
0x522de9 JBE 522d70 |
0x522deb JMP 522e36 |
0x522df0 MOV -0x8(%R9,%RDI,1),%R8 [7] |
0x522df5 UCOMISD (%R13,%R8,8),%XMM3 [4] |
0x522dfc JBE 522db9 |
0x522dfe MOV -0x88(%RBP),%R8 [3] |
0x522e05 MOVSD -0x8(%R8,%RDI,1),%XMM0 [5] |
0x522e0c XORPD %XMM4,%XMM0 |
0x522e10 MOVLPD %XMM0,-0x8(%R8,%RDI,1) [5] |
0x522e17 MOV (%R9,%RDI,1),%R8 [7] |
0x522e1b UCOMISD (%R13,%R8,8),%XMM3 [2] |
0x522e22 JA 522dc6 |
0x522e24 MOV 0x8(%R9,%RDI,1),%R8 [7] |
0x522e29 UCOMISD (%R13,%R8,8),%XMM3 [6] |
0x522e30 JBE 522d70 |
0x522e36 MOV -0x88(%RBP),%R8 [3] |
0x522e3d MOVSD 0x8(%R8,%RDI,1),%XMM0 [5] |
0x522e44 XORPD %XMM4,%XMM0 |
0x522e48 MOVLPD %XMM0,0x8(%R8,%RDI,1) [5] |
0x522e4f JMP 522d70 |
/beegfs/hackathon/users/eoseret/qaas_runs/170-859-5251/intel/AMG/build/AMG/AMG/parcsr_ls/ams.c: 3532 - 3534 |
-------------------------------------------------------------------------------- |
3532: for (i = ns; i < ne; i++) |
3533: if (A_diag_data[A_diag_I[i]] < 0) |
3534: l1_norm[i] = -l1_norm[i]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.54 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 4.32 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.08 |
Bottlenecks | P5, P6, P7, |
Function | hypre_ParCSRComputeL1NormsThreads.extracted |
Source | ams.c:3532-3534 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | high |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 9.00 |
CQA cycles if no scalar integer | 5.83 |
CQA cycles if FP arith vectorized | 9.00 |
CQA cycles if fully vectorized | 2.08 |
Front-end cycles | 8.33 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 0.75 |
P1 cycles | 0.75 |
P2 cycles | 0.50 |
P3 cycles | 5.00 |
P4 cycles | 9.00 |
P5 cycles | 9.00 |
P6 cycles | 9.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 3.50 |
P10 cycles | 3.50 |
P11 cycles | 5.50 |
P12 cycles | 5.50 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 43.00 |
Nb uops | 50.00 |
Nb loads | 23.00 |
Nb stores | 4.00 |
Nb stack references | 2.00 |
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 | 24.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 184.00 |
Bytes stored | 32.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 21.05 |
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 | 36.36 |
Vector-efficiency ratio all | 15.13 |
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 | 17.05 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.54 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 4.32 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.08 |
Bottlenecks | P5, P6, P7, |
Function | hypre_ParCSRComputeL1NormsThreads.extracted |
Source | ams.c:3532-3534 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | high |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 9.00 |
CQA cycles if no scalar integer | 5.83 |
CQA cycles if FP arith vectorized | 9.00 |
CQA cycles if fully vectorized | 2.08 |
Front-end cycles | 8.33 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 0.75 |
P1 cycles | 0.75 |
P2 cycles | 0.50 |
P3 cycles | 5.00 |
P4 cycles | 9.00 |
P5 cycles | 9.00 |
P6 cycles | 9.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 3.50 |
P10 cycles | 3.50 |
P11 cycles | 5.50 |
P12 cycles | 5.50 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 43.00 |
Nb uops | 50.00 |
Nb loads | 23.00 |
Nb stores | 4.00 |
Nb stack references | 2.00 |
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 | 24.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 184.00 |
Bytes stored | 32.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 21.05 |
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 | 36.36 |
Vector-efficiency ratio all | 15.13 |
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 | 17.05 |
Path / |
Function | hypre_ParCSRComputeL1NormsThreads.extracted |
Source file and lines | ams.c:3532-3534 |
Module | exec |
nb instructions | 43 |
nb uops | 50 |
loop length | 225 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 8.33 cycles |
front end | 8.33 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 0.75 | 0.75 | 0.50 | 5.00 | 9.00 | 9.00 | 9.00 | 2.00 | 2.00 | 3.50 | 3.50 | 5.50 | 5.50 |
cycles | 5.00 | 0.75 | 0.75 | 0.50 | 5.00 | 9.00 | 9.00 | 9.00 | 2.00 | 2.00 | 3.50 | 3.50 | 5.50 | 5.50 |
Cycles executing div or sqrt instructions | NA |
Front-end | 8.33 |
Dispatch | 9.00 |
Overall L1 | 9.00 |
all | 21% |
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 | 36% |
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 | 17% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
ADD $0x20,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
DEC %RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
JE 522c54 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1bb4> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0xd8(%RBP),%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV -0x10(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522df0 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d50> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x88(%RBP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOVSD -0x10(%R8,%RDI,1),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
XORPD %XMM4,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
MOVLPD %XMM0,-0x10(%R8,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
MOV -0x8(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JA 522dfe <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d5e> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV (%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522e24 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d84> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x88(%RBP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOVSD (%R8,%RDI,1),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
XORPD %XMM4,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
MOVLPD %XMM0,(%R8,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
MOV 0x8(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522d70 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1cd0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
JMP 522e36 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d96> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
MOV -0x8(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522db9 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d19> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x88(%RBP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOVSD -0x8(%R8,%RDI,1),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
XORPD %XMM4,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
MOVLPD %XMM0,-0x8(%R8,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
MOV (%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JA 522dc6 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d26> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV 0x8(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522d70 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1cd0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x88(%RBP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOVSD 0x8(%R8,%RDI,1),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
XORPD %XMM4,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
MOVLPD %XMM0,0x8(%R8,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
JMP 522d70 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1cd0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
Function | hypre_ParCSRComputeL1NormsThreads.extracted |
Source file and lines | ams.c:3532-3534 |
Module | exec |
nb instructions | 43 |
nb uops | 50 |
loop length | 225 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 8.33 cycles |
front end | 8.33 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 0.75 | 0.75 | 0.50 | 5.00 | 9.00 | 9.00 | 9.00 | 2.00 | 2.00 | 3.50 | 3.50 | 5.50 | 5.50 |
cycles | 5.00 | 0.75 | 0.75 | 0.50 | 5.00 | 9.00 | 9.00 | 9.00 | 2.00 | 2.00 | 3.50 | 3.50 | 5.50 | 5.50 |
Cycles executing div or sqrt instructions | NA |
Front-end | 8.33 |
Dispatch | 9.00 |
Overall L1 | 9.00 |
all | 21% |
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 | 36% |
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 | 17% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
ADD $0x20,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
DEC %RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
JE 522c54 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1bb4> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0xd8(%RBP),%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOV -0x10(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522df0 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d50> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x88(%RBP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOVSD -0x10(%R8,%RDI,1),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
XORPD %XMM4,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
MOVLPD %XMM0,-0x10(%R8,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
MOV -0x8(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JA 522dfe <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d5e> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV (%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522e24 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d84> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x88(%RBP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOVSD (%R8,%RDI,1),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
XORPD %XMM4,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
MOVLPD %XMM0,(%R8,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
MOV 0x8(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522d70 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1cd0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
JMP 522e36 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d96> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
MOV -0x8(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522db9 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d19> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x88(%RBP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOVSD -0x8(%R8,%RDI,1),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
XORPD %XMM4,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
MOVLPD %XMM0,-0x8(%R8,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
MOV (%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JA 522dc6 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1d26> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV 0x8(%R9,%RDI,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
UCOMISD (%R13,%R8,8),%XMM3 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 7 | 1 |
JBE 522d70 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1cd0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV -0x88(%RBP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
MOVSD 0x8(%R8,%RDI,1),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
XORPD %XMM4,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
MOVLPD %XMM0,0x8(%R8,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
JMP 522d70 <hypre_ParCSRComputeL1NormsThreads.extracted+0x1cd0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |