OV - exec - Function build_field(global_variables&) [clone .omp

	Function: build_field(global_variables&) [clone .omp_outlined.4]	Module: exec	Source: build_field.cpp:133-138 [...]	Coverage (incl. loops): 0.02% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: 69 - 69

--------------------------------------------------------------------------------

69:   T &operator()(size_t i, size_t j) const { return data[i + j * sizeX]; }

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp: 133 - 138

--------------------------------------------------------------------------------

133: #pragma omp parallel for simd collapse(2)

134:     for (int j = (0); j < (yrange); j++) {

135:       for (int i = (0); i < (xrange); i++) {

136:         field.vol_flux_x(i, j) = 0.0;

137:         field.mass_flux_x(i, j) = 0.0;

138:         field.xarea(i, j) = 0.0;

0x2391d0 PUSH	%RBP

0x2391d1 MOV	%RSP,%RBP

0x2391d4 PUSH	%R15

0x2391d6 PUSH	%R14

0x2391d8 PUSH	%R13

0x2391da PUSH	%R12

0x2391dc PUSH	%RBX

0x2391dd SUB	$0x58,%RSP

0x2391e1 MOV	(%RDX),%R15D

0x2391e4 TEST	%R15D,%R15D

0x2391e7 JLE	2393df

0x2391ed MOV	(%RCX),%EAX

0x2391ef TEST	%EAX,%EAX

0x2391f1 JLE	2393df

0x2391f7 MOV	%R8,%R14

0x2391fa MOV	%EAX,-0x2c(%RBP)

0x2391fd MOVSXD	%EAX,%R13

0x239200 IMUL	%R13,%R15

0x239204 DEC	%R15

0x239207 MOVQ	$0,-0x58(%RBP)

0x23920f MOV	%R15,-0x38(%RBP)

0x239213 MOVQ	$0x1,-0x80(%RBP)

0x23921b MOVL	$0,-0x40(%RBP)

0x239222 MOV	(%RDI),%ESI

0x239224 SUB	$0x8,%RSP

0x239228 LEA	-0x80(%RBP),%RAX

0x23922c LEA	0x25375(%RIP),%RDI

0x239233 LEA	-0x40(%RBP),%RCX

0x239237 LEA	-0x58(%RBP),%R8

0x23923b LEA	-0x38(%RBP),%R9

0x23923f MOV	%ESI,-0x3c(%RBP)

0x239242 MOV	$0x22,%EDX

0x239247 PUSH	$0x1

0x239249 PUSH	$0x1

0x23924b PUSH	%RAX

0x23924c CALL	25ccf0 <@plt_start@+0x530>

0x239251 ADD	$0x20,%RSP

0x239255 MOV	-0x38(%RBP),%RAX

0x239259 CMP	%R15,%RAX

0x23925c CMOVL	%RAX,%R15

0x239260 MOV	%R15,-0x38(%RBP)

0x239264 MOV	-0x58(%RBP),%RSI

0x239268 CMP	%R15,%RSI

0x23926b JG	2393d0

0x239271 MOV	0x108(%R14),%RDI

0x239278 MOV	0x118(%R14),%R8

0x23927f MOV	0x130(%R14),%R10

0x239286 MOV	0x120(%R14),%RBX

0x23928d MOV	0x2b8(%R14),%R12

0x239294 MOV	0x2a8(%R14),%R14

0x23929b MOV	%R15,%RAX

0x23929e SUB	%RSI,%RAX

0x2392a1 INC	%RAX

0x2392a4 CMP	$0x2,%RAX

0x2392a8 JAE	2392b2

0x2392aa MOV	%RSI,%RCX

0x2392ad JMP	23943c

0x2392b2 MOV	%R8,-0x48(%RBP)

0x2392b6 MOV	%RDI,-0x50(%RBP)

0x2392ba MOV	%R15,-0x70(%RBP)

0x2392be MOV	%RAX,-0x68(%RBP)

0x2392c2 MOV	%RAX,%R15

0x2392c5 AND	$-0x2,%R15

0x2392c9 LEA	(%RSI,%R15,1),%RCX

0x2392cd MOV	%R15,-0x60(%RBP)

0x2392d1 MOV	%R10,-0x78(%RBP)

0x2392d5 MOV	-0x48(%RBP),%R11

0x2392d9 JMP	239368

0x2392de XCHG	%AX,%AX

(189) 0x2392e0 CQTO

(189) 0x2392e2 IDIV	%R13

(189) 0x2392e5 MOVSXD	%R8D,%R8

(189) 0x2392e8 MOVSXD	%EDX,%RDX

(189) 0x2392eb MOVSXD	%EDI,%R9

(189) 0x2392ee CLTQ

(189) 0x2392f0 MOV	%R9,%RDI

(189) 0x2392f3 MOV	-0x50(%RBP),%R10

(189) 0x2392f7 IMUL	%R10,%RDI

(189) 0x2392fb ADD	%R8,%RDI

(189) 0x2392fe MOVQ	$0,(%R11,%RDI,8)

(189) 0x239306 MOV	%RAX,%RDI

(189) 0x239309 IMUL	%R10,%RDI

(189) 0x23930d ADD	%RDX,%RDI

(189) 0x239310 MOVQ	$0,(%R11,%RDI,8)

(189) 0x239318 MOV	%R9,%RDI

(189) 0x23931b IMUL	%RBX,%RDI

(189) 0x23931f ADD	%R8,%RDI

(189) 0x239322 MOV	-0x78(%RBP),%R10

(189) 0x239326 MOVQ	$0,(%R10,%RDI,8)

(189) 0x23932e MOV	%RAX,%RDI

(189) 0x239331 IMUL	%RBX,%RDI

(189) 0x239335 ADD	%RDX,%RDI

(189) 0x239338 MOVQ	$0,(%R10,%RDI,8)

(189) 0x239340 IMUL	%R14,%R9

(189) 0x239344 ADD	%R8,%R9

(189) 0x239347 IMUL	%R14,%RAX

(189) 0x23934b ADD	%RDX,%RAX

(189) 0x23934e MOVQ	$0,(%R12,%R9,8)

(189) 0x239356 MOVQ	$0,(%R12,%RAX,8)

(189) 0x23935e ADD	$0x2,%RSI

(189) 0x239362 ADD	$-0x2,%R15

(189) 0x239366 JE	2393ba

(189) 0x239368 MOV	%RSI,%RAX

(189) 0x23936b OR	%R13,%RAX

(189) 0x23936e SHR	$0x20,%RAX

(189) 0x239372 JE	239390

(189) 0x239374 MOV	%RSI,%RAX

(189) 0x239377 CQTO

(189) 0x239379 IDIV	%R13

(189) 0x23937c MOV	%RDX,%R8

(189) 0x23937f MOV	%RAX,%RDI

(189) 0x239382 JMP	23939c

0x239384 NOPW	%CS:(%RAX,%RAX,1)

(189) 0x239390 MOV	%ESI,%EAX

(189) 0x239392 XOR	%EDX,%EDX

(189) 0x239394 DIVL	-0x2c(%RBP)

(189) 0x239397 MOV	%EDX,%R8D

(189) 0x23939a MOV	%EAX,%EDI

(189) 0x23939c LEA	0x1(%RSI),%RAX

(189) 0x2393a0 MOV	%RAX,%RDX

(189) 0x2393a3 OR	%R13,%RDX

(189) 0x2393a6 SHR	$0x20,%RDX

(189) 0x2393aa JNE	2392e0

(189) 0x2393b0 XOR	%EDX,%EDX

(189) 0x2393b2 DIVL	-0x2c(%RBP)

(189) 0x2393b5 JMP	2392e5

0x2393ba MOV	-0x60(%RBP),%RAX

0x2393be CMP	%RAX,-0x68(%RBP)

0x2393c2 MOV	-0x70(%RBP),%R15

0x2393c6 MOV	-0x50(%RBP),%RDI

0x2393ca MOV	-0x48(%RBP),%R8

0x2393ce JNE	23943c

0x2393d0 LEA	0x251e9(%RIP),%RDI

0x2393d7 MOV	-0x3c(%RBP),%ESI

0x2393da CALL	25cd00 <@plt_start@+0x540>

0x2393df ADD	$0x58,%RSP

0x2393e3 POP	%RBX

0x2393e4 POP	%R12

0x2393e6 POP	%R13

0x2393e8 POP	%R14

0x2393ea POP	%R15

0x2393ec POP	%RBP

0x2393ed RET

0x2393ee XCHG	%AX,%AX

(188) 0x2393f0 MOV	%RCX,%RAX

(188) 0x2393f3 CQTO

(188) 0x2393f5 IDIV	%R13

(188) 0x2393f8 MOVSXD	%EDX,%RDX

(188) 0x2393fb CLTQ

(188) 0x2393fd MOV	%RAX,%RSI

(188) 0x239400 IMUL	%RDI,%RSI

(188) 0x239404 ADD	%RDX,%RSI

(188) 0x239407 MOVQ	$0,(%R8,%RSI,8)

(188) 0x23940f MOV	%RAX,%RSI

(188) 0x239412 IMUL	%RBX,%RSI

(188) 0x239416 ADD	%RDX,%RSI

(188) 0x239419 MOVQ	$0,(%R10,%RSI,8)

(188) 0x239421 IMUL	%R14,%RAX

(188) 0x239425 ADD	%RDX,%RAX

(188) 0x239428 MOVQ	$0,(%R12,%RAX,8)

(188) 0x239430 LEA	0x1(%RCX),%RAX

(188) 0x239434 CMP	%R15,%RCX

(188) 0x239437 MOV	%RAX,%RCX

(188) 0x23943a JGE	2393d0

(188) 0x23943c MOV	%RCX,%RAX

(188) 0x23943f OR	%R13,%RAX

(188) 0x239442 SHR	$0x20,%RAX

(188) 0x239446 JNE	2393f0

(188) 0x239448 MOV	%ECX,%EAX

(188) 0x23944a XOR	%EDX,%EDX

(188) 0x23944c DIVL	-0x2c(%RBP)

(188) 0x23944f JMP	2393f8

0x239451 NOPW	%CS:(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

Average path: Display a virtual path defined by average values of all real paths

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	build_field.cpp:133-138
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:133-138

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 10% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 11.00 to 0.83 cycles (13.31x speedup).

Details

All SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:133
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:133

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:134

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

Matching between your function (in the source code) and the binary function

The binary function does not contain any FP arithmetical operations. The binary function is loading 128 bytes. The binary function is storing 92 bytes.

General properties

nb instructions	89
nb uops	88
loop length	353
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	12

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	11.00 cycles
front end	11.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.00	6.00	6.00	6.00	6.00	6.00	8.25	8.25	8.25	8.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.00	6.00	6.00	6.00	6.00	6.00	8.25	8.25	8.25	8.25	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.00
Dispatch	8.25
Overall L1	11.00

Vectorization ratios

all	0%
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	0%

Vector efficiency ratios

all	10%
load	12%
store	10%
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	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 11.00 cycles. At this rate:

4% of peak load performance is reached (11.64 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.36 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 11.00 to 8.25 cycles (1.33x speedup).

ASM code

In the binary file, the address of the function is: 2391d0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x58,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV (%RDX),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %R15D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 2393df <_Z11build_fieldR16global_variables.omp_outlined.4+0x20f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%RCX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %EAX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 2393df <_Z11build_fieldR16global_variables.omp_outlined.4+0x20f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVSXD %EAX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
IMUL %R13,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
DEC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R15,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x80(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA 0x25375(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x40(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x58(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x38(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x3c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R15,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%R15	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %R15,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x58(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R15,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 2393d0 <_Z11build_fieldR16global_variables.omp_outlined.4+0x200>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x108(%R14),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x118(%R14),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x130(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x120(%R14),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x2b8(%R14),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x2a8(%R14),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R15,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 2392b2 <_Z11build_fieldR16global_variables.omp_outlined.4+0xe2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 23943c <_Z11build_fieldR16global_variables.omp_outlined.4+0x26c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R8,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDI,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R15,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R15,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x48(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JMP 239368 <_Z11build_fieldR16global_variables.omp_outlined.4+0x198>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x68(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
MOV -0x70(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x50(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x48(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 23943c <_Z11build_fieldR16global_variables.omp_outlined.4+0x26c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x251e9(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x3c(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x58,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	build_field.cpp:133-138
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:133-138

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Details

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

CALL instructions

Detected function call instructions.

Details

unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:133
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:133

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:134

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

Matching between your function (in the source code) and the binary function

The binary function does not contain any FP arithmetical operations. The binary function is loading 128 bytes. The binary function is storing 92 bytes.

General properties

nb instructions	89
nb uops	88
loop length	353
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	12

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	11.00 cycles
front end	11.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.00	6.00	6.00	6.00	6.00	6.00	8.25	8.25	8.25	8.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.00	6.00	6.00	6.00	6.00	6.00	8.25	8.25	8.25	8.25	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.00
Dispatch	8.25
Overall L1	11.00

Vectorization ratios

all	0%
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	0%

Vector efficiency ratios

all	10%
load	12%
store	10%
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	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 11.00 cycles. At this rate:

4% of peak load performance is reached (11.64 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.36 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 2391d0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x58,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV (%RDX),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %R15D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 2393df <_Z11build_fieldR16global_variables.omp_outlined.4+0x20f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%RCX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %EAX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 2393df <_Z11build_fieldR16global_variables.omp_outlined.4+0x20f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVSXD %EAX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
IMUL %R13,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
DEC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R15,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x80(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA 0x25375(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x40(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x58(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x38(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x3c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R15,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%R15	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %R15,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x58(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R15,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 2393d0 <_Z11build_fieldR16global_variables.omp_outlined.4+0x200>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x108(%R14),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x118(%R14),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x130(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x120(%R14),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x2b8(%R14),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x2a8(%R14),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R15,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 2392b2 <_Z11build_fieldR16global_variables.omp_outlined.4+0xe2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 23943c <_Z11build_fieldR16global_variables.omp_outlined.4+0x26c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R8,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDI,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R15,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R15,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x48(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JMP 239368 <_Z11build_fieldR16global_variables.omp_outlined.4+0x198>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x68(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
MOV -0x70(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x50(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x48(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 23943c <_Z11build_fieldR16global_variables.omp_outlined.4+0x26c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x251e9(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x3c(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x58,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼build_field(global_variables&) [clone .omp_outlined.4]–	0.02	0.01
○Loop 189 - build_field.cpp:134-138 - exec	0.02	0.01
○Loop 188 - build_field.cpp:134-138 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code