| Loop Id: 519 | Module: exec | Source: flux_calc_kernel.f90-pp.f90:54-62 | Coverage: 0.01% |
|---|
| Loop Id: 519 | Module: exec | Source: flux_calc_kernel.f90-pp.f90:54-62 | Coverage: 0.01% |
|---|
0x42310c ADD X8, X8, #1 |
0x423110 SUBS W9, W9, #1 |
0x423114 ADD X13, X13, #1 |
0x423118 B.LE 423338 |
0x42311c CMP W19, #1 |
0x423120 B.LT 42310c |
0x423124 LDR X10, [X20, #56] |
0x423128 LDP X17, X16, [X20, #112] |
0x42312c LDR X0, [X20, #32] |
0x423130 ORR X22, XZR, X1 |
0x423134 ORR W23, WZR, W19 |
0x423138 CMP X25, X14 |
0x42313c LDP X28, X30, [X20, #208] |
0x423140 LDR X18, [X10] |
0x423144 LDP X10, X11, [X20, #96] |
0x423148 LDP X2, X5, [X20, #152] |
0x42314c LDR X3, [X10] |
0x423150 LDR X10, [X20, #176] |
0x423154 LDR D1, [X11] |
0x423158 LDR X7, [X10] |
0x42315c LDP X10, X6, [X20, #192] |
0x423160 FMUL D1, D1, D0 |
0x423164 LDR X21, [X10] |
0x423168 B.CC 423270 |
0x42316c UDIV X10, X25, X14 |
0x423170 MADD X11, X18, X13, X1 |
0x423174 MADD X12, X18, X8, X1 |
0x423178 ORR X4, XZR, X0 |
0x42317c ORR X0, XZR, X17 |
0x423180 STP X30, X28, [SP, #48] |
0x423184 ORR X24, XZR, XZR |
0x423188 DUP Z2.D, Z1.D[0] |
0x42318c SUB X11, X11, X3 |
0x423190 SUB X12, X12, X3 |
0x423194 STP X4, X0, [SP, #64] |
0x423198 UBFM X11, X11, #61, #60 |
0x42319c UBFM X17, X12, #61, #60 |
0x4231a0 ADD X26, X16, X11 |
0x4231a4 ADD X27, X2, X11 |
0x4231a8 MADD X11, X7, X8, X1 |
0x4231ac ADD X28, X28, X17 |
0x4231b0 ADD X30, X30, X17 |
0x4231b4 ADD X12, X0, X17 |
0x4231b8 SUB X11, X11, X21 |
0x4231bc MADD X29, X10, X14, XZR |
0x4231c0 SUB X10, X25, X29 |
0x4231c4 SUB W23, W19, W29 |
0x4231c8 ADD X19, X4, X17 |
0x4231cc ADD X25, X16, X17 |
0x4231d0 ADD X22, X29, X1 |
0x4231d4 STR X10, [SP, #40] |
0x4231d8 ADD X10, X2, X17 |
0x4231dc UBFM X17, X11, #61, #60 |
0x4231e0 ADD X11, X5, X17 |
0x4231e4 ADD X17, X6, X17 |
(521) 0x4231e8 LD1D {Z3.D}, P0/Z, [X27, X24,LSL #3] |
(521) 0x4231ec LD1D {Z4.D}, P0/Z, [X10, X24,LSL #3] |
(521) 0x4231f0 UBFM X0, X24, #61, #60 |
(521) 0x4231f4 ADD X1, X30, X0 |
(521) 0x4231f8 LD1D {Z5.D}, P0/Z, [X25, X24,LSL #3] |
(521) 0x4231fc ADD X0, X28, X0 |
(521) 0x423200 FADD Z3.D, Z3.D, Z4.D |
(521) 0x423204 LD1D {Z4.D}, P0/Z, [X26, X24,LSL #3] |
(521) 0x423208 FADD Z4.D, Z4.D, Z5.D |
(521) 0x42320c FADD Z3.D, Z3.D, Z4.D |
(521) 0x423210 LD1D {Z4.D}, P0/Z, [X12, X24,LSL #3] |
(521) 0x423214 FMUL Z4.D, Z4.D, Z2.D |
(521) 0x423218 FMUL Z3.D, Z3.D, Z4.D |
(521) 0x42321c ST1D {Z3.D}, P0, [X19, X24,LSL #3] |
(521) 0x423220 LD1D {Z3.D}, P0/Z, [X1, X15,LSL #3] |
(521) 0x423224 LD1D {Z4.D}, P0/Z, [X1, MUL VL] |
(521) 0x423228 FADD Z3.D, Z3.D, Z4.D |
(521) 0x42322c LD1D {Z4.D}, P0/Z, [X0, X15,LSL #3] |
(521) 0x423230 LD1D {Z5.D}, P0/Z, [X0, MUL VL] |
(521) 0x423234 FADD Z4.D, Z4.D, Z5.D |
(521) 0x423238 FADD Z3.D, Z3.D, Z4.D |
(521) 0x42323c LD1D {Z4.D}, P0/Z, [X17, X24,LSL #3] |
(521) 0x423240 FMUL Z4.D, Z2.D, Z4.D |
(521) 0x423244 FMUL Z3.D, Z3.D, Z4.D |
(521) 0x423248 ST1D {Z3.D}, P0, [X11, X24,LSL #3] |
(521) 0x42324c ADD X24, X24, X14 |
(521) 0x423250 CMP X29, X24 |
(521) 0x423254 B.NE 4231e8 |
0x423258 LDP X1, X10, [SP, #32] |
0x42325c LDR W19, [SP, #28] |
0x423260 LDR X25, [SP, #16] |
0x423264 LDP X0, X17, [SP, #64] |
0x423268 LDP X30, X28, [SP, #48] |
0x42326c CBZ X10, 42310c |
0x423270 MADD X10, X18, X13, X22 |
0x423274 MADD X11, X7, X8, X22 |
0x423278 ADD W23, W23, #1 |
0x42327c ORR X24, XZR, XZR |
0x423280 SUB X10, X10, X3 |
0x423284 SUB X11, X11, X21 |
0x423288 UBFM X10, X10, #61, #60 |
0x42328c UBFM X11, X11, #61, #60 |
0x423290 ADD X7, X16, X10 |
0x423294 ADD X21, X2, X10 |
0x423298 MADD X10, X18, X8, X22 |
0x42329c ADD X6, X6, X11 |
0x4232a0 SUB X10, X10, X3 |
0x4232a4 UBFM X10, X10, #61, #60 |
0x4232a8 ADD X12, X30, X10 |
0x4232ac ADD X0, X0, X10 |
0x4232b0 ADD X16, X16, X10 |
0x4232b4 ADD X18, X12, #8 |
0x4232b8 ADD X12, X28, X10 |
0x4232bc ADD X3, X12, #8 |
0x4232c0 ADD X12, X17, X10 |
0x4232c4 ADD X10, X2, X10 |
0x4232c8 ADD X17, X5, X11 |
(520) 0x4232cc LDR D2, [X21, X24] |
(520) 0x4232d0 LDR D3, [X10, X24] |
(520) 0x4232d4 LDR D4, [X16, X24] |
(520) 0x4232d8 ADD X11, X18, X24 |
(520) 0x4232dc SUB W23, W23, #1 |
(520) 0x4232e0 CMP W23, #1 |
(520) 0x4232e4 FADD D2, D2, D3 |
(520) 0x4232e8 LDR D3, [X7, X24] |
(520) 0x4232ec FADD D3, D3, D4 |
(520) 0x4232f0 FADD D2, D2, D3 |
(520) 0x4232f4 LDR D3, [X12, X24] |
(520) 0x4232f8 FMUL D3, D3, D1 |
(520) 0x4232fc FMUL D2, D2, D3 |
(520) 0x423300 STR D2, [X0, X24] |
(520) 0x423304 LDP D3, D2, [X11, #1016] |
(520) 0x423308 ADD X11, X3, X24 |
(520) 0x42330c FADD D2, D2, D3 |
(520) 0x423310 LDP D4, D3, [X11, #1016] |
(520) 0x423314 FADD D3, D3, D4 |
(520) 0x423318 FADD D2, D2, D3 |
(520) 0x42331c LDR D3, [X6, X24] |
(520) 0x423320 FMUL D3, D1, D3 |
(520) 0x423324 FMUL D2, D2, D3 |
(520) 0x423328 STR D2, [X17, X24] |
(520) 0x42332c ADD X24, X24, #8 |
(520) 0x423330 B.HI 4232cc |
0x423334 B 42310c |
/home/hbollore/qaas-runs/170-308-3604/intel/CloverLeafFC/build/armclang_1/CMakeFiles/clover_leaf.dir/CloverLeaf_ref/kernels/flux_calc_kernel.f90-pp.f90: 54 - 62 |
-------------------------------------------------------------------------------- |
54: !$OMP DO |
55: DO k=y_min,y_max+1 |
56: !$OMP SIMD |
57: DO j=x_min,x_max+1 |
58: vol_flux_x(j,k)=0.25_8*dt*xarea(j,k) & |
59: *(xvel0(j,k)+xvel0(j,k+1)+xvel1(j,k)+xvel1(j,k+1)) |
60: vol_flux_y(j,k)=0.25_8*dt*yarea(j,k) & |
61: *(yvel0(j,k)+yvel0(j+1,k)+yvel1(j,k)+yvel1(j+1,k)) |
62: ENDDO |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 4.64 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 2.02 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.18 |
| Bottlenecks | |
| Function | __nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_ |
| Source | flux_calc_kernel.f90-pp.f90:54-56,flux_calc_kernel.f90-pp.f90:59-62 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.67 |
| CQA cycles if no scalar integer | 1.22 |
| CQA cycles if FP arith vectorized | 5.67 |
| CQA cycles if fully vectorized | 2.81 |
| Front-end cycles | 4.79 |
| DIV/SQRT cycles | 1.67 |
| P0 cycles | 1.67 |
| P1 cycles | 5.67 |
| P2 cycles | 5.67 |
| P3 cycles | 5.67 |
| P4 cycles | 5.67 |
| P5 cycles | 0.25 |
| P6 cycles | 0.25 |
| P7 cycles | 0.25 |
| P8 cycles | 0.25 |
| P9 cycles | 3.83 |
| P10 cycles | 3.72 |
| P11 cycles | 3.78 |
| P12 cycles | 0.50 |
| P13 cycles | 0.50 |
| P14 cycles | 0.33 - 0.17 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 38.33 |
| Nb uops | 38.33 |
| Nb loads | NA |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.12 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.67 |
| 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 | 15.97 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 116.00 |
| Bytes stored | 13.33 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 1.39 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 6.25 |
| Vector-efficiency ratio all | 23.13 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 22.37 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 25.63 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 5.33 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.33 |
| Bottlenecks | P0, P1, P2, P3, P4, P5, |
| Function | __nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_ |
| Source | flux_calc_kernel.f90-pp.f90:54-56,flux_calc_kernel.f90-pp.f90:59-62 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 1.00 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 1.00 |
| CQA cycles if fully vectorized | 0.19 |
| Front-end cycles | 0.75 |
| DIV/SQRT cycles | 1.00 |
| P0 cycles | 1.00 |
| P1 cycles | 1.00 |
| P2 cycles | 1.00 |
| P3 cycles | 1.00 |
| P4 cycles | 1.00 |
| P5 cycles | 0.00 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.00 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 6.00 |
| Nb uops | 6.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| 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 | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | NA |
| 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 | NA |
| Vector-efficiency ratio all | 20.83 |
| Vector-efficiency ratio load | NA |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 20.83 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 6.38 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.24 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.11 |
| Bottlenecks | P2, P3, P4, P5, |
| Function | __nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_ |
| Source | flux_calc_kernel.f90-pp.f90:54-56,flux_calc_kernel.f90-pp.f90:59-62 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 8.50 |
| CQA cycles if no scalar integer | 1.33 |
| CQA cycles if FP arith vectorized | 8.50 |
| CQA cycles if fully vectorized | 6.83 |
| Front-end cycles | 7.63 |
| DIV/SQRT cycles | 2.00 |
| P0 cycles | 2.00 |
| P1 cycles | 8.50 |
| P2 cycles | 8.50 |
| P3 cycles | 8.50 |
| P4 cycles | 8.50 |
| P5 cycles | 0.50 |
| P6 cycles | 0.50 |
| P7 cycles | 0.50 |
| P8 cycles | 0.50 |
| P9 cycles | 7.17 |
| P10 cycles | 6.83 |
| P11 cycles | 7.00 |
| P12 cycles | 1.50 |
| P13 cycles | 1.50 |
| P14 cycles | 1.00 - 0.50 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 61.00 |
| Nb uops | 61.00 |
| Nb loads | NA |
| Nb stores | 3.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.12 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 1.00 |
| 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 | 28.71 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 204.00 |
| Bytes stored | 40.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 4.17 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 12.50 |
| Vector-efficiency ratio all | 26.04 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 23.08 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 31.25 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 5.63 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 5.33 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.25 |
| Bottlenecks | P2, P3, P4, P5, |
| Function | __nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_ |
| Source | flux_calc_kernel.f90-pp.f90:54-56,flux_calc_kernel.f90-pp.f90:59-62 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 7.50 |
| CQA cycles if no scalar integer | 1.33 |
| CQA cycles if FP arith vectorized | 7.50 |
| CQA cycles if fully vectorized | 1.41 |
| Front-end cycles | 6.00 |
| DIV/SQRT cycles | 2.00 |
| P0 cycles | 2.00 |
| P1 cycles | 7.50 |
| P2 cycles | 7.50 |
| P3 cycles | 7.50 |
| P4 cycles | 7.50 |
| P5 cycles | 0.25 |
| P6 cycles | 0.25 |
| P7 cycles | 0.25 |
| P8 cycles | 0.25 |
| P9 cycles | 4.33 |
| P10 cycles | 4.33 |
| P11 cycles | 4.33 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 48.00 |
| Nb uops | 48.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.13 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 1.00 |
| 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 | 19.20 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 144.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 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 | 22.50 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 23.21 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 20.00 |
| Path / |
| Function | __nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_ |
| Source file and lines | flux_calc_kernel.f90-pp.f90:54-62 |
| Module | exec |
 |
| nb instructions | 38.33 |
| loop length | 153.33 |
| nb stack references | 0 |
| front end | 4.79 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.67 | 1.67 | 5.67 | 5.67 | 5.67 | 5.67 | 0.25 | 0.25 | 0.25 | 0.25 | 3.83 | 3.72 | 3.78 | 0.50 | 0.50 |
| cycles | 1.67 | 1.67 | 5.67 | 5.67 | 5.67 | 5.67 | 0.25 | 0.25 | 0.25 | 0.25 | 3.83 | 3.72 | 3.78 | 0.50 | 0.50 |
| Cycles executing div or sqrt instructions | 0.33-0.17 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 4.79 |
| Data deps. | 1.00 |
| Overall L1 | 5.67 |
| all | 1% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 6% |
| Function | __nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_ |
| Source file and lines | flux_calc_kernel.f90-pp.f90:54-62 |
| Module | exec |
|
| nb instructions | 6 |
| loop length | 24 |
| nb stack references | 0 |
| front end | 0.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| cycles | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 0.75 |
| Data deps. | 1.00 |
| Overall L1 | 1.00 |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| 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 | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD X8, X8, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SUBS W9, W9, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| ADD X13, X13, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| B.LE 423338 <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0x2f8> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| CMP W19, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| B.LT 42310c <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0xcc> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| Function | __nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_ |
| Source file and lines | flux_calc_kernel.f90-pp.f90:54-62 |
| Module | exec |
|
| nb instructions | 61 |
| loop length | 244 |
| nb stack references | 0 |
| front end | 7.63 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 2.00 | 2.00 | 8.50 | 8.50 | 8.50 | 8.50 | 0.50 | 0.50 | 0.50 | 0.50 | 7.17 | 6.83 | 7.00 | 1.50 | 1.50 |
| cycles | 2.00 | 2.00 | 8.50 | 8.50 | 8.50 | 8.50 | 0.50 | 0.50 | 0.50 | 0.50 | 7.17 | 6.83 | 7.00 | 1.50 | 1.50 |
| Cycles executing div or sqrt instructions | 1.00-0.50 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 7.63 |
| Data deps. | 1.00 |
| Overall L1 | 8.50 |
| all | 4% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 12% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD X8, X8, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SUBS W9, W9, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| ADD X13, X13, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| B.LE 423338 <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0x2f8> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| CMP W19, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| B.LT 42310c <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0xcc> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| LDR X10, [X20, #56] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDP X17, X16, [X20, #112] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDR X0, [X20, #32] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| ORR X22, XZR, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ORR W23, WZR, W19 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| CMP X25, X14 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| LDP X28, X30, [X20, #208] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDR X18, [X10] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDP X10, X11, [X20, #96] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDP X2, X5, [X20, #152] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDR X3, [X10] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDR X10, [X20, #176] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDR D1, [X11] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 |
| LDR X7, [X10] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDP X10, X6, [X20, #192] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| FMUL D1, D1, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 |
| LDR X21, [X10] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| B.CC 423270 <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0x230> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| UDIV X10, X25, X14 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5-20 | 1-0.50 |
| MADD X11, X18, X13, X1 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
| MADD X12, X18, X8, X1 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
| ORR X4, XZR, X0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ORR X0, XZR, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| STP X30, X28, [SP, #48] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 |
| ORR X24, XZR, XZR | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| DUP Z2.D, Z1.D[0] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 |
| SUB X11, X11, X3 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SUB X12, X12, X3 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| STP X4, X0, [SP, #64] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 |
| UBFM X11, X11, #61, #60 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| UBFM X17, X12, #61, #60 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X26, X16, X11 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X27, X2, X11 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| MADD X11, X7, X8, X1 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
| ADD X28, X28, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X30, X30, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X12, X0, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SUB X11, X11, X21 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| MADD X29, X10, X14, XZR | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
| SUB X10, X25, X29 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SUB W23, W19, W29 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X19, X4, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X25, X16, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X22, X29, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| STR X10, [SP, #40] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 |
| ADD X10, X2, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| UBFM X17, X11, #61, #60 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X11, X5, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X17, X6, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| LDP X1, X10, [SP, #32] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDR W19, [SP, #28] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDR X25, [SP, #16] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDP X0, X17, [SP, #64] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDP X30, X28, [SP, #48] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| CBZ X10, 42310c <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0xcc> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| Function | __nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_ |
| Source file and lines | flux_calc_kernel.f90-pp.f90:54-62 |
| Module | exec |
|
| nb instructions | 48 |
| loop length | 192 |
| nb stack references | 0 |
| front end | 6.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 2.00 | 2.00 | 7.50 | 7.50 | 7.50 | 7.50 | 0.25 | 0.25 | 0.25 | 0.25 | 4.33 | 4.33 | 4.33 | 0.00 | 0.00 |
| cycles | 2.00 | 2.00 | 7.50 | 7.50 | 7.50 | 7.50 | 0.25 | 0.25 | 0.25 | 0.25 | 4.33 | 4.33 | 4.33 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 6.00 |
| Data deps. | 1.00 |
| Overall L1 | 7.50 |
| 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% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD X8, X8, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SUBS W9, W9, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| ADD X13, X13, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| B.LE 423338 <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0x2f8> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| CMP W19, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| B.LT 42310c <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0xcc> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| LDR X10, [X20, #56] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDP X17, X16, [X20, #112] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDR X0, [X20, #32] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| ORR X22, XZR, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ORR W23, WZR, W19 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| CMP X25, X14 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| LDP X28, X30, [X20, #208] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDR X18, [X10] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDP X10, X11, [X20, #96] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDP X2, X5, [X20, #152] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| LDR X3, [X10] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDR X10, [X20, #176] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDR D1, [X11] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 |
| LDR X7, [X10] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| LDP X10, X6, [X20, #192] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
| FMUL D1, D1, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 |
| LDR X21, [X10] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 |
| B.CC 423270 <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0x230> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| MADD X10, X18, X13, X22 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
| MADD X11, X7, X8, X22 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
| ADD W23, W23, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ORR X24, XZR, XZR | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SUB X10, X10, X3 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SUB X11, X11, X21 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| UBFM X10, X10, #61, #60 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| UBFM X11, X11, #61, #60 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X7, X16, X10 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X21, X2, X10 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| MADD X10, X18, X8, X22 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
| ADD X6, X6, X11 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SUB X10, X10, X3 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| UBFM X10, X10, #61, #60 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X12, X30, X10 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X0, X0, X10 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X16, X16, X10 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X18, X12, #8 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X12, X28, X10 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X3, X12, #8 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X12, X17, X10 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X10, X2, X10 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X17, X5, X11 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| B 42310c <__nv_flux_calc_kernel_module_flux_calc_kernel__F1L49_1_+0xcc> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |