| Loop Id: 350 | Module: exec | Source: pack_kernel.f90:156-160 | Coverage: 0.03% |
|---|
| Loop Id: 350 | Module: exec | Source: pack_kernel.f90:156-160 | Coverage: 0.03% |
|---|
0x445fc0 MOV %R9D,%R8D |
0x445fc3 LEA 0x1(%RDI),%EAX |
0x445fc6 INC %EDX |
0x445fc8 MOV %R8D,%R9D |
0x445fcb CMP -0x38(%RBP),%EDI |
0x445fce MOV %EAX,%EDI |
0x445fd0 JE 445f0c |
0x445fd6 TEST %R9D,%R9D |
0x445fd9 JLE 445fc0 |
0x445fdb MOV -0x50(%RBP),%RAX |
0x445fdf ADD %EDI,%EAX |
0x445fe1 MOV -0x60(%RBP),%RCX |
0x445fe5 MOVSXD (%RCX),%R14 |
0x445fe8 MOV -0x48(%RBP),%RCX |
0x445fec MOV (%RCX),%R8D |
0x445fef MOV (%R12),%R11 |
0x445ff3 MOV 0x38(%R12),%R10 |
0x445ff8 MOV -0x58(%RBP),%RCX |
0x445ffc MOV (%RCX),%ESI |
0x445ffe MOV 0x50(%R12),%RCX |
0x446003 MOV (%RBX),%R15 |
0x446006 VPBROADCASTQ %R10,%ZMM7 |
0x44600c MOV 0x38(%RBX),%R10 |
0x446010 MOV %R9D,%R13D |
0x446013 VPBROADCASTQ %R10,%ZMM5 |
0x446019 MOV %R13,%R9 |
0x44601c VPBROADCASTQ %R13,%ZMM9 |
0x446022 VPBROADCASTQ %R11,%ZMM10 |
0x446028 CLTQ |
0x44602a VPBROADCASTD %ESI,%YMM8 |
0x446030 VPBROADCASTQ %R15,%ZMM6 |
0x446036 MOV $-0x8,%R10D |
0x44603c AND %R10,%R9 |
0x44603f JE 446100 |
0x446045 LEA 0x1(%RAX),%R10 |
0x446049 IMUL %R10,%RCX |
0x44604d VPBROADCASTQ %RCX,%ZMM11 |
0x446053 LEA -0x1(%RAX,%R8,1),%EAX |
0x446058 IMUL %R8D,%EAX |
0x44605c MOVSXD %EAX,%R10 |
0x44605f ADD %R14,%R10 |
0x446062 LEA (%R8,%RDX,1),%EAX |
0x446066 IMUL %R8D,%EAX |
0x44606a CLTQ |
0x44606c ADD %R14,%RAX |
0x44606f ADD %RCX,%R11 |
0x446072 XOR %ECX,%ECX |
0x446074 NOPW %CS:(%RAX,%RAX,1) |
(351) 0x446080 VPBROADCASTD %ESI,%YMM12 |
(351) 0x446086 VPADDD %YMM1,%YMM12,%YMM12 |
(351) 0x44608a VPMOVSXDQ %YMM12,%ZMM12 |
(351) 0x446090 VPSUBQ %ZMM2,%ZMM12,%ZMM12 |
(351) 0x446096 VPMULLQ %ZMM12,%ZMM7,%ZMM12 |
(351) 0x44609c VXORPD %XMM13,%XMM13,%XMM13 |
(351) 0x4460a1 KXNORW %K0,%K0,%K1 |
(351) 0x4460a5 VGATHERQPD (%R11,%ZMM12,1),%ZMM13{%K1} |
(351) 0x4460ac LEA (%RAX,%RCX,1),%R14 |
(351) 0x4460b0 VPBROADCASTQ %R14,%ZMM12 |
(351) 0x4460b6 VPADDQ %ZMM3,%ZMM12,%ZMM12 |
(351) 0x4460bc VPMULLQ %ZMM12,%ZMM5,%ZMM12 |
(351) 0x4460c2 KXNORW %K0,%K0,%K1 |
(351) 0x4460c6 VSCATTERQPD %ZMM13,(%R15,%ZMM12,1){%K1} |
(351) 0x4460cd ADD $0x8,%RCX |
(351) 0x4460d1 ADD $-0x8,%ESI |
(351) 0x4460d4 CMP %R9,%RCX |
(351) 0x4460d7 JB 446080 |
0x4460d9 CMP %R13,%R9 |
0x4460dc JNE 446120 |
0x4460de JMP 445fc3 |
0x446100 LEA 0x1(%RAX),%RSI |
0x446104 IMUL %RSI,%RCX |
0x446108 VPBROADCASTQ %RCX,%ZMM11 |
0x44610e LEA -0x1(%RAX,%R8,1),%EAX |
0x446113 IMUL %R8D,%EAX |
0x446117 MOVSXD %EAX,%R10 |
0x44611a ADD %R14,%R10 |
0x44611d XOR %R9D,%R9D |
0x446120 VPADDQ %ZMM11,%ZMM10,%ZMM10 |
0x446126 VPBROADCASTQ %R9,%ZMM11 |
0x44612c VPSUBQ %ZMM11,%ZMM9,%ZMM9 |
0x446132 VPCMPNLEUQ %ZMM0,%ZMM9,%K1 |
0x446139 VPBROADCASTD %R9D,%YMM9 |
0x44613f VPSUBD %YMM9,%YMM8,%YMM8 |
0x446144 VPADDD %YMM1,%YMM8,%YMM8 |
0x446148 VPMOVSXDQ %YMM8,%ZMM8 |
0x44614e VPSUBQ %ZMM2,%ZMM8,%ZMM8 |
0x446154 VPMULLQ %ZMM8,%ZMM7,%ZMM7 |
0x44615a VPADDQ %ZMM7,%ZMM10,%ZMM7 |
0x446160 VPXOR %XMM8,%XMM8,%XMM8 |
0x446165 KMOVQ %K1,%K2 |
0x44616a VGATHERQPD (,%ZMM7,1),%ZMM8{%K2} |
0x446175 VMOVAPD %ZMM8,%ZMM4{%K1} |
0x44617b ADD %R9,%R10 |
0x44617e VPBROADCASTQ %R10,%ZMM7 |
0x446184 VPADDQ %ZMM0,%ZMM7,%ZMM7 |
0x44618a VPMULLQ %ZMM7,%ZMM5,%ZMM5 |
0x446190 VPADDQ %ZMM5,%ZMM6,%ZMM5 |
0x446196 VSCATTERQPD %ZMM4,(,%ZMM5,1){%K1} |
0x4461a1 JMP 445fc3 |
/scratch_na/users/xoserete/qaas_runs/171-415-7919/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/pack_kernel.f90: 156 - 160 |
-------------------------------------------------------------------------------- |
156: DO k=y_min-depth,y_max+y_inc+depth |
157: !$OMP SIMD |
158: DO j=1,depth |
159: index= buffer_offset + j+(k+depth-1)*depth |
160: right_snd_buffer(index)=field(x_max+1-j,k) |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.14 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.71 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.11 |
| Bottlenecks | |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:156-160 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 10.50 |
| CQA cycles if no scalar integer | 9.21 |
| CQA cycles if FP arith vectorized | 10.50 |
| CQA cycles if fully vectorized | 6.14 |
| Front-end cycles | 10.50 |
| DIV/SQRT cycles | 8.90 |
| P0 cycles | 6.13 |
| P1 cycles | 4.67 |
| P2 cycles | 4.67 |
| P3 cycles | 2.00 |
| P4 cycles | 9.25 |
| P5 cycles | 5.55 |
| P6 cycles | 2.00 |
| P7 cycles | 2.00 |
| P8 cycles | 2.00 |
| P9 cycles | 5.60 |
| P10 cycles | 4.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 11.00 - 17.29 |
| Stall cycles (UFS) | 1.18 - 7.34 |
| Nb insns | 48.25 |
| Nb uops | 63.00 |
| Nb loads | 10.50 |
| Nb stores | 0.50 |
| Nb stack references | 4.00 |
| 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 | 10.08 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 99.00 |
| Bytes stored | 32.00 |
| Stride 0 | 2.50 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 1.25 |
| Stride indirect | 1.50 |
| Vectorization ratio all | 22.24 |
| Vectorization ratio load | 8.33 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | 100.00 |
| Vectorization ratio add_sub | 44.44 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 12.53 |
| Vector-efficiency ratio all | 26.33 |
| Vector-efficiency ratio load | 16.74 |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | 100.00 |
| Vector-efficiency ratio add_sub | 44.10 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 17.51 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 16.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.33 |
| Bottlenecks | micro-operation queue, |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:156-160 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 1.33 |
| CQA cycles if no scalar integer | 1.33 |
| CQA cycles if FP arith vectorized | 1.33 |
| CQA cycles if fully vectorized | 0.08 |
| Front-end cycles | 1.33 |
| DIV/SQRT cycles | 1.00 |
| P0 cycles | 1.00 |
| P1 cycles | 0.33 |
| P2 cycles | 0.33 |
| P3 cycles | 0.00 |
| P4 cycles | 1.00 |
| P5 cycles | 1.00 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 1.00 |
| P10 cycles | 0.33 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 1.43 - 2.05 |
| Stall cycles (UFS) | 0.00 - 0.09 |
| Nb insns | 9.00 |
| Nb uops | 8.00 |
| Nb loads | 1.00 |
| Nb stores | 0.00 |
| 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 | 3.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 4.00 |
| Bytes stored | 0.00 |
| Stride 0 | 1.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 6.25 |
| Vector-efficiency ratio load | 6.25 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 6.25 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 6.25 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.11 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.37 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.07 |
| Bottlenecks | micro-operation queue, |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:156-160 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 15.50 |
| CQA cycles if no scalar integer | 14.00 |
| CQA cycles if FP arith vectorized | 15.50 |
| CQA cycles if fully vectorized | 11.29 |
| Front-end cycles | 15.50 |
| DIV/SQRT cycles | 14.50 |
| P0 cycles | 6.80 |
| P1 cycles | 7.00 |
| P2 cycles | 7.00 |
| P3 cycles | 4.00 |
| P4 cycles | 14.50 |
| P5 cycles | 6.60 |
| P6 cycles | 4.00 |
| P7 cycles | 4.00 |
| P8 cycles | 4.00 |
| P9 cycles | 6.60 |
| P10 cycles | 7.00 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 16.98 - 28.37 |
| Stall cycles (UFS) | 2.96 - 14.35 |
| Nb insns | 63.00 |
| Nb uops | 93.00 |
| Nb loads | 14.00 |
| Nb stores | 1.00 |
| Nb stack references | 5.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 13.94 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 152.00 |
| Bytes stored | 64.00 |
| Stride 0 | 3.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 1.00 |
| Stride indirect | 2.00 |
| Vectorization ratio all | 45.71 |
| Vectorization ratio load | 16.67 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | 100.00 |
| Vectorization ratio add_sub | 88.89 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 26.32 |
| Vector-efficiency ratio all | 44.82 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | 100.00 |
| Vector-efficiency ratio add_sub | 78.47 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 27.30 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.19 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 10.26 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.08 |
| Bottlenecks | micro-operation queue, |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:156-160 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 8.33 |
| CQA cycles if no scalar integer | 7.00 |
| CQA cycles if FP arith vectorized | 8.33 |
| CQA cycles if fully vectorized | 0.81 |
| Front-end cycles | 8.33 |
| DIV/SQRT cycles | 5.60 |
| P0 cycles | 7.73 |
| P1 cycles | 4.33 |
| P2 cycles | 4.33 |
| P3 cycles | 0.00 |
| P4 cycles | 7.00 |
| P5 cycles | 5.60 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 5.80 |
| P10 cycles | 4.33 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 8.48 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 50.00 |
| Nb uops | 50.00 |
| Nb loads | 13.00 |
| Nb stores | 0.00 |
| Nb stack references | 5.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 10.56 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 88.00 |
| Bytes stored | 0.00 |
| Stride 0 | 3.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 2.00 |
| Stride indirect | 1.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 11.01 |
| Vector-efficiency ratio load | 10.71 |
| Vector-efficiency ratio store | NA |
| 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 | 10.58 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.16 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.36 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.16 |
| Bottlenecks | micro-operation queue, |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:156-160 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 16.83 |
| CQA cycles if no scalar integer | 14.50 |
| CQA cycles if FP arith vectorized | 16.83 |
| CQA cycles if fully vectorized | 12.37 |
| Front-end cycles | 16.83 |
| DIV/SQRT cycles | 14.50 |
| P0 cycles | 9.00 |
| P1 cycles | 7.00 |
| P2 cycles | 7.00 |
| P3 cycles | 4.00 |
| P4 cycles | 14.50 |
| P5 cycles | 9.00 |
| P6 cycles | 4.00 |
| P7 cycles | 4.00 |
| P8 cycles | 4.00 |
| P9 cycles | 9.00 |
| P10 cycles | 7.00 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 17.11 - 30.27 |
| Stall cycles (UFS) | 1.76 - 14.92 |
| Nb insns | 71.00 |
| Nb uops | 101.00 |
| Nb loads | 14.00 |
| Nb stores | 1.00 |
| Nb stack references | 5.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 12.83 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 152.00 |
| Bytes stored | 64.00 |
| Stride 0 | 3.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 2.00 |
| Stride indirect | 3.00 |
| Vectorization ratio all | 43.24 |
| Vectorization ratio load | 16.67 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | 100.00 |
| Vectorization ratio add_sub | 88.89 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 23.81 |
| Vector-efficiency ratio all | 43.24 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | 100.00 |
| Vector-efficiency ratio add_sub | 79.17 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 25.89 |
| Path / |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:156-160 |
| Module | exec |
| nb instructions | 48.25 |
| nb uops | 63 |
| loop length | 212.50 |
| used x86 registers | 12.75 |
| used mmx registers | 0 |
| used xmm registers | 0.50 |
| used ymm registers | 1.75 |
| used zmm registers | 6.50 |
| nb stack references | 4 |
| micro-operation queue | 10.50 cycles |
| front end | 10.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 8.90 | 5.70 | 4.67 | 4.67 | 2.00 | 9.25 | 5.55 | 2.00 | 2.00 | 2.00 | 5.60 | 4.67 |
| cycles | 8.90 | 6.13 | 4.67 | 4.67 | 2.00 | 9.25 | 5.55 | 2.00 | 2.00 | 2.00 | 5.60 | 4.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 11.00-17.29 |
| Stall cycles | 1.18-7.34 |
| ROB full (events) | 1.45-7.75 |
| RS full (events) | 0.01-0.06 |
| Front-end | 10.50 |
| Dispatch | 9.43 |
| Data deps. | 1.00 |
| Overall L1 | 10.50 |
| all | 19% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 100% |
| add-sub | 44% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 8% |
| all | 100% |
| load | 100% |
| store | 100% |
| 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 | 22% |
| load | 8% |
| store | 100% |
| mul | 100% |
| add-sub | 44% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 12% |
| all | 23% |
| load | 9% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 100% |
| add-sub | 44% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 13% |
| all | 100% |
| load | 100% |
| store | 100% |
| 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 | 26% |
| load | 16% |
| store | 100% |
| mul | 100% |
| add-sub | 44% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 17% |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:156-160 |
| Module | exec |
| nb instructions | 9 |
| nb uops | 8 |
| loop length | 27 |
| used x86 registers | 6 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 1 |
| micro-operation queue | 1.33 cycles |
| front end | 1.33 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 1.00 | 0.33 | 0.33 | 0.00 | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.33 |
| cycles | 1.00 | 1.00 | 0.33 | 0.33 | 0.00 | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 1.43-2.05 |
| Stall cycles | 0.00-0.09 |
| Front-end | 1.33 |
| Dispatch | 1.00 |
| Data deps. | 1.00 |
| Overall L1 | 1.33 |
| 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) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 6% |
| load | 6% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 6% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 6% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MOV %R9D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| LEA 0x1(%RDI),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
| INC %EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV %R8D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP -0x38(%RBP),%EDI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
| MOV %EAX,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| JE 445f0c <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x8c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| TEST %R9D,%R9D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
| JLE 445fc0 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x140> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:156-160 |
| Module | exec |
| nb instructions | 63 |
| nb uops | 93 |
| loop length | 296 |
| used x86 registers | 15 |
| used mmx registers | 0 |
| used xmm registers | 1 |
| used ymm registers | 3 |
| used zmm registers | 10 |
| nb stack references | 5 |
| micro-operation queue | 15.50 cycles |
| front end | 15.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 14.50 | 6.80 | 7.00 | 7.00 | 4.00 | 14.50 | 6.60 | 4.00 | 4.00 | 4.00 | 6.60 | 7.00 |
| cycles | 14.50 | 6.80 | 7.00 | 7.00 | 4.00 | 14.50 | 6.60 | 4.00 | 4.00 | 4.00 | 6.60 | 7.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 16.98-28.37 |
| Stall cycles | 2.96-14.35 |
| ROB full (events) | 3.58-15.02 |
| RS full (events) | 0.03-0.00 |
| Front-end | 15.50 |
| Dispatch | 14.50 |
| Data deps. | 1.00 |
| Overall L1 | 15.50 |
| all | 40% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 100% |
| add-sub | 88% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 17% |
| all | 100% |
| load | 100% |
| store | 100% |
| 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 | 45% |
| load | 16% |
| store | 100% |
| mul | 100% |
| add-sub | 88% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 26% |
| all | 39% |
| load | 10% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 100% |
| add-sub | 78% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 18% |
| all | 100% |
| load | 100% |
| store | 100% |
| 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 | 44% |
| load | 25% |
| store | 100% |
| mul | 100% |
| add-sub | 78% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 27% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LEA 0x1(%RDI),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
| INC %EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV %R8D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP -0x38(%RBP),%EDI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
| MOV %EAX,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| JE 445f0c <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x8c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| TEST %R9D,%R9D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
| JLE 445fc0 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x140> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| ADD %EDI,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOVSXD (%RCX),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x48(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV (%RCX),%R8D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV (%R12),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV 0x38(%R12),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV (%RCX),%ESI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV 0x50(%R12),%RCX | 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 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VPBROADCASTQ %R10,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOV 0x38(%RBX),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %R9D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VPBROADCASTQ %R10,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOV %R13,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VPBROADCASTQ %R13,%ZMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPBROADCASTQ %R11,%ZMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| CLTQ | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VPBROADCASTD %ESI,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPBROADCASTQ %R15,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOV $-0x8,%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| AND %R10,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
| JE 446100 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x280> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| LEA 0x1(%RAX),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| IMUL %RSI,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPBROADCASTQ %RCX,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| LEA -0x1(%RAX,%R8,1),%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| IMUL %R8D,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOVSXD %EAX,%R10 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
| ADD %R14,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VPADDQ %ZMM11,%ZMM10,%ZMM10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VPBROADCASTQ %R9,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPSUBQ %ZMM11,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 |
| VPCMPNLEUQ %ZMM0,%ZMM9,%K1 | |||||||||||||||
| VPBROADCASTD %R9D,%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPSUBD %YMM9,%YMM8,%YMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
| VPADDD %YMM1,%YMM8,%YMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VPMOVSXDQ %YMM8,%ZMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPSUBQ %ZMM2,%ZMM8,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 |
| VPMULLQ %ZMM8,%ZMM7,%ZMM7 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
| VPADDQ %ZMM7,%ZMM10,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VPXOR %XMM8,%XMM8,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
| VGATHERQPD (,%ZMM7,1),%ZMM8{%K2} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| VMOVAPD %ZMM8,%ZMM4{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
| ADD %R9,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| VPBROADCASTQ %R10,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPADDQ %ZMM0,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VPMULLQ %ZMM7,%ZMM5,%ZMM5 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
| VPADDQ %ZMM5,%ZMM6,%ZMM5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VSCATTERQPD %ZMM4,(,%ZMM5,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 |
| JMP 445fc3 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x143> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:156-160 |
| Module | exec |
| nb instructions | 50 |
| nb uops | 50 |
| loop length | 199 |
| used x86 registers | 15 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 1 |
| used zmm registers | 6 |
| nb stack references | 5 |
| micro-operation queue | 8.33 cycles |
| front end | 8.33 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 5.60 | 6.00 | 4.33 | 4.33 | 0.00 | 7.00 | 5.60 | 0.00 | 0.00 | 0.00 | 5.80 | 4.33 |
| cycles | 5.60 | 7.73 | 4.33 | 4.33 | 0.00 | 7.00 | 5.60 | 0.00 | 0.00 | 0.00 | 5.80 | 4.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 8.48 |
| Stall cycles | 0.00 |
| Front-end | 8.33 |
| Dispatch | 7.73 |
| Data deps. | 1.00 |
| Overall L1 | 8.33 |
| 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) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 11% |
| load | 10% |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | 10% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LEA 0x1(%RDI),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
| INC %EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV %R8D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP -0x38(%RBP),%EDI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
| MOV %EAX,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| JE 445f0c <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x8c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| TEST %R9D,%R9D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
| JLE 445fc0 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x140> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| ADD %EDI,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOVSXD (%RCX),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x48(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV (%RCX),%R8D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV (%R12),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV 0x38(%R12),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV (%RCX),%ESI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV 0x50(%R12),%RCX | 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 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VPBROADCASTQ %R10,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOV 0x38(%RBX),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %R9D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VPBROADCASTQ %R10,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOV %R13,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VPBROADCASTQ %R13,%ZMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPBROADCASTQ %R11,%ZMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| CLTQ | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VPBROADCASTD %ESI,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPBROADCASTQ %R15,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOV $-0x8,%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| AND %R10,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
| JE 446100 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x280> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| LEA 0x1(%RAX),%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| IMUL %R10,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPBROADCASTQ %RCX,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| LEA -0x1(%RAX,%R8,1),%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| IMUL %R8D,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOVSXD %EAX,%R10 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
| ADD %R14,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| LEA (%R8,%RDX,1),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
| IMUL %R8D,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| CLTQ | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| ADD %R14,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| ADD %RCX,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| XOR %ECX,%ECX | 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 |
| CMP %R13,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JNE 446120 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| JMP 445fc3 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x143> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
| Function | clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:156-160 |
| Module | exec |
| nb instructions | 71 |
| nb uops | 101 |
| loop length | 328 |
| used x86 registers | 15 |
| used mmx registers | 0 |
| used xmm registers | 1 |
| used ymm registers | 3 |
| used zmm registers | 10 |
| nb stack references | 5 |
| micro-operation queue | 16.83 cycles |
| front end | 16.83 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 14.50 | 9.00 | 7.00 | 7.00 | 4.00 | 14.50 | 9.00 | 4.00 | 4.00 | 4.00 | 9.00 | 7.00 |
| cycles | 14.50 | 9.00 | 7.00 | 7.00 | 4.00 | 14.50 | 9.00 | 4.00 | 4.00 | 4.00 | 9.00 | 7.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 17.11-30.27 |
| Stall cycles | 1.77-14.92 |
| ROB full (events) | 2.21-15.99 |
| Front-end | 16.83 |
| Dispatch | 14.50 |
| Data deps. | 1.00 |
| Overall L1 | 16.83 |
| all | 38% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 100% |
| add-sub | 88% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 15% |
| all | 100% |
| load | 100% |
| store | 100% |
| 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 | 43% |
| load | 16% |
| store | 100% |
| mul | 100% |
| add-sub | 88% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 23% |
| all | 38% |
| load | 10% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 100% |
| add-sub | 79% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 18% |
| all | 100% |
| load | 100% |
| store | 100% |
| 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 | 43% |
| load | 25% |
| store | 100% |
| mul | 100% |
| add-sub | 79% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LEA 0x1(%RDI),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
| INC %EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV %R8D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP -0x38(%RBP),%EDI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
| MOV %EAX,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| JE 445f0c <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x8c> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| TEST %R9D,%R9D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
| JLE 445fc0 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x140> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| ADD %EDI,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOVSXD (%RCX),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x48(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV (%RCX),%R8D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV (%R12),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV 0x38(%R12),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV (%RCX),%ESI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV 0x50(%R12),%RCX | 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 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VPBROADCASTQ %R10,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOV 0x38(%RBX),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %R9D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VPBROADCASTQ %R10,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOV %R13,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| VPBROADCASTQ %R13,%ZMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPBROADCASTQ %R11,%ZMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| CLTQ | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VPBROADCASTD %ESI,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPBROADCASTQ %R15,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOV $-0x8,%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| AND %R10,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
| JE 446100 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x280> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| LEA 0x1(%RAX),%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| IMUL %R10,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPBROADCASTQ %RCX,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| LEA -0x1(%RAX,%R8,1),%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| IMUL %R8D,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| MOVSXD %EAX,%R10 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
| ADD %R14,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| LEA (%R8,%RDX,1),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
| IMUL %R8D,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| CLTQ | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| ADD %R14,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| ADD %RCX,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| XOR %ECX,%ECX | 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 |
| CMP %R13,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JNE 446120 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| VPADDQ %ZMM11,%ZMM10,%ZMM10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VPBROADCASTQ %R9,%ZMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPSUBQ %ZMM11,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 |
| VPCMPNLEUQ %ZMM0,%ZMM9,%K1 | |||||||||||||||
| VPBROADCASTD %R9D,%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPSUBD %YMM9,%YMM8,%YMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
| VPADDD %YMM1,%YMM8,%YMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VPMOVSXDQ %YMM8,%ZMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPSUBQ %ZMM2,%ZMM8,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 |
| VPMULLQ %ZMM8,%ZMM7,%ZMM7 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
| VPADDQ %ZMM7,%ZMM10,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VPXOR %XMM8,%XMM8,%XMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
| VGATHERQPD (,%ZMM7,1),%ZMM8{%K2} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| VMOVAPD %ZMM8,%ZMM4{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.17 |
| ADD %R9,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| VPBROADCASTQ %R10,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPADDQ %ZMM0,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VPMULLQ %ZMM7,%ZMM5,%ZMM5 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 |
| VPADDQ %ZMM5,%ZMM6,%ZMM5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VSCATTERQPD %ZMM4,(,%ZMM5,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 |
| JMP 445fc3 <pack_kernel_module_mp_clover_pack_message_right_.DIR.OMP.PARALLEL.LOOP.2.split101+0x143> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
