OV - exec - Function flux_calc_kernel(int, int, int, int, double, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&) [clone .omp

	Function: flux_calc_kernel(int, int, int, int, double, clover::Buffer2D<double>&, clover::Buffer2D<d ...	Module: exec	Source: flux_calc.cpp:36-40 [...]	Coverage (incl. loops): 4.09% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/flux_calc.cpp: 36 - 40

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

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

37:   for (int j = (y_min + 1); j < (y_max + 1 + 2); j++) {

38:     for (int i = (x_min + 1); i < (x_max + 1 + 2); i++) {

39:       vol_flux_x(i, j) = 0.25 * dt * xarea(i, j) * (xvel0(i, j) + xvel0(i + 0, j + 1) + xvel1(i, j) + xvel1(i + 0, j + 1));

40:       vol_flux_y(i, j) = 0.25 * dt * yarea(i, j) * (yvel0(i, j) + yvel0(i + 1, j + 0) + yvel1(i, j) + yvel1(i + 1, j + 0));

/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]; }

0x23ce00 PUSH	%RBP

0x23ce01 MOV	%RSP,%RBP

0x23ce04 PUSH	%R15

0x23ce06 PUSH	%R14

0x23ce08 PUSH	%R13

0x23ce0a PUSH	%R12

0x23ce0c PUSH	%RBX

0x23ce0d SUB	$0xd8,%RSP

0x23ce14 MOV	(%RDX),%R14D

0x23ce17 MOV	(%RCX),%R15D

0x23ce1a INC	%R14D

0x23ce1d ADD	$0x3,%R15D

0x23ce21 SUB	%R14D,%R15D

0x23ce24 JLE	23d29d

0x23ce2a MOV	(%R8),%EAX

0x23ce2d MOV	(%R9),%EBX

0x23ce30 INC	%EAX

0x23ce32 ADD	$0x3,%EBX

0x23ce35 CMP	%EAX,%EBX

0x23ce37 JLE	23d29d

0x23ce3d MOV	%EAX,-0x2c(%RBP)

0x23ce40 SUB	%EAX,%EBX

0x23ce42 IMUL	%RBX,%R15

0x23ce46 DEC	%R15

0x23ce49 MOVQ	$0,-0xc0(%RBP)

0x23ce54 MOV	%R15,-0x50(%RBP)

0x23ce58 MOVQ	$0x1,-0xf8(%RBP)

0x23ce63 MOVL	$0,-0x58(%RBP)

0x23ce6a MOV	(%RDI),%ESI

0x23ce6c SUB	$0x8,%RSP

0x23ce70 LEA	-0xf8(%RBP),%RAX

0x23ce77 LEA	0x2199a(%RIP),%RDI

0x23ce7e LEA	-0x58(%RBP),%RCX

0x23ce82 LEA	-0xc0(%RBP),%R8

0x23ce89 LEA	-0x50(%RBP),%R9

0x23ce8d MOV	%ESI,-0x54(%RBP)

0x23ce90 MOV	$0x22,%EDX

0x23ce95 PUSH	$0x1

0x23ce97 PUSH	$0x1

0x23ce99 PUSH	%RAX

0x23ce9a CALL	25ccf0 <@plt_start@+0x530>

0x23ce9f ADD	$0x20,%RSP

0x23cea3 MOV	-0x50(%RBP),%RAX

0x23cea7 CMP	%R15,%RAX

0x23ceaa CMOVL	%RAX,%R15

0x23ceae MOV	%R15,-0x50(%RBP)

0x23ceb2 MOV	-0xc0(%RBP),%RSI

0x23ceb9 CMP	%R15,%RSI

0x23cebc JG	23d28e

0x23cec2 MOV	%RBX,-0x40(%RBP)

0x23cec6 MOV	0x50(%RBP),%RAX

0x23ceca MOV	0x48(%RBP),%RCX

0x23cece MOV	0x40(%RBP),%RDX

0x23ced2 MOV	0x30(%RBP),%RDI

0x23ced6 MOV	0x28(%RBP),%R8

0x23ceda MOV	0x20(%RBP),%R9

0x23cede MOV	0x10(%RBP),%RBX

0x23cee2 MOV	(%R9),%R11

0x23cee5 MOV	0x10(%R9),%R10

0x23cee9 MOV	(%R8),%R9

0x23ceec MOV	0x10(%R8),%R8

0x23cef0 MOV	%R8,-0x38(%RBP)

0x23cef4 MOV	(%RDI),%R12

0x23cef7 MOV	0x10(%RDI),%RDI

0x23cefb MOV	%RDI,-0xb8(%RBP)

0x23cf02 MOV	(%RBX),%RDI

0x23cf05 MOV	%RDI,-0xb0(%RBP)

0x23cf0c MOV	0x10(%RBX),%RDI

0x23cf10 MOV	%RDI,-0xa8(%RBP)

0x23cf17 MOV	(%RDX),%RDI

0x23cf1a MOV	%RDI,-0xa0(%RBP)

0x23cf21 MOV	0x10(%RDX),%RDX

0x23cf25 MOV	%RDX,-0x98(%RBP)

0x23cf2c MOV	(%RCX),%RDX

0x23cf2f MOV	%RDX,-0x90(%RBP)

0x23cf36 MOV	0x10(%RCX),%RCX

0x23cf3a MOV	%RCX,-0x88(%RBP)

0x23cf41 MOV	(%RAX),%RCX

0x23cf44 MOV	%RCX,-0x80(%RBP)

0x23cf48 MOV	0x10(%RAX),%RAX

0x23cf4c MOV	%RAX,-0x78(%RBP)

0x23cf50 MOV	0x38(%RBP),%RAX

0x23cf54 MOV	(%RAX),%RCX

0x23cf57 MOV	%RCX,-0x70(%RBP)

0x23cf5b MOV	0x10(%RAX),%RAX

0x23cf5f MOV	%RAX,-0x68(%RBP)

0x23cf63 MOV	%R15,%R13

0x23cf66 SUB	%RSI,%R13

0x23cf69 INC	%R13

0x23cf6c CMP	$0x2,%R13

0x23cf70 MOV	%R10,-0x48(%RBP)

0x23cf74 JAE	23cf86

0x23cf76 MOV	%RSI,%RCX

0x23cf79 MOV	-0x40(%RBP),%R8

0x23cf7d MOV	-0x38(%RBP),%RBX

0x23cf81 JMP	23d3e4

0x23cf86 MOV	%R15,-0xd8(%RBP)

0x23cf8d MOV	%R14,-0x60(%RBP)

0x23cf91 MOV	%R13,-0xd0(%RBP)

0x23cf98 AND	$-0x2,%R13

0x23cf9c LEA	(%RSI,%R13,1),%RCX

0x23cfa0 MOVSD	-0x2be60(%RIP),%XMM0

0x23cfa8 MOV	%R13,-0xc8(%RBP)

0x23cfaf MOV	%R11,-0xf0(%RBP)

0x23cfb6 MOV	%R9,-0xe8(%RBP)

0x23cfbd MOV	%R12,-0xe0(%RBP)

0x23cfc4 JMP	23d20e

0x23cfc9 NOPL	(%RAX)

(220) 0x23cfd0 CQTO

(220) 0x23cfd2 IDIV	%R10

(220) 0x23cfd5 MOV	-0x60(%RBP),%R15

(220) 0x23cfd9 LEA	(%R15,%RDI,1),%R10D

(220) 0x23cfdd LEA	(%R15,%RAX,1),%R11D

(220) 0x23cfe1 MOV	-0x2c(%RBP),%EBX

(220) 0x23cfe4 ADD	%EBX,%R8D

(220) 0x23cfe7 ADD	%EBX,%EDX

(220) 0x23cfe9 MOV	0x18(%RBP),%R9

(220) 0x23cfed MOVSD	(%R9),%XMM2

(220) 0x23cff2 MULSD	%XMM0,%XMM2

(220) 0x23cff6 UNPCKLPD	%XMM2,%XMM2

(220) 0x23cffa MOVSXD	%R8D,%RBX

(220) 0x23cffd MOVSXD	%EDX,%R14

(220) 0x23d000 MOVSXD	%R10D,%RDX

(220) 0x23d003 MOVSXD	%R11D,%R8

(220) 0x23d006 MOV	-0xf0(%RBP),%R11

(220) 0x23d00d MOV	%R11,%R10

(220) 0x23d010 IMUL	%RDX,%R10

(220) 0x23d014 ADD	%RBX,%R10

(220) 0x23d017 MOV	-0x48(%RBP),%R9

(220) 0x23d01b MOVSD	(%R9,%R10,8),%XMM1

(220) 0x23d021 MOV	%R11,%R10

(220) 0x23d024 IMUL	%R8,%R10

(220) 0x23d028 ADD	%R14,%R10

(220) 0x23d02b MOVHPD	(%R9,%R10,8),%XMM1

(220) 0x23d031 MOV	-0xe8(%RBP),%R9

(220) 0x23d038 MOV	%R9,%R10

(220) 0x23d03b IMUL	%RDX,%R10

(220) 0x23d03f ADD	%RBX,%R10

(220) 0x23d042 MOV	-0x38(%RBP),%R12

(220) 0x23d046 MOVSD	(%R12,%R10,8),%XMM3

(220) 0x23d04c MOV	%R9,%R10

(220) 0x23d04f IMUL	%R8,%R10

(220) 0x23d053 ADD	%R14,%R10

(220) 0x23d056 MOVHPD	(%R12,%R10,8),%XMM3

(220) 0x23d05c MULPD	%XMM2,%XMM1

(220) 0x23d060 ADD	%R15D,%EDI

(220) 0x23d063 INC	%EDI

(220) 0x23d065 LEA	0x1(%R15,%RAX,1),%EAX

(220) 0x23d06a MOVSXD	%EDI,%RDI

(220) 0x23d06d CLTQ

(220) 0x23d06f MOV	%R9,%R10

(220) 0x23d072 IMUL	%RDI,%R10

(220) 0x23d076 ADD	%RBX,%R10

(220) 0x23d079 MOVSD	(%R12,%R10,8),%XMM2

(220) 0x23d07f MOV	%R9,%R10

(220) 0x23d082 IMUL	%RAX,%R10

(220) 0x23d086 ADD	%R14,%R10

(220) 0x23d089 MOVHPD	(%R12,%R10,8),%XMM2

(220) 0x23d08f ADDPD	%XMM3,%XMM2

(220) 0x23d093 MOV	-0xe0(%RBP),%R12

(220) 0x23d09a MOV	%R12,%R10

(220) 0x23d09d IMUL	%RDX,%R10

(220) 0x23d0a1 ADD	%RBX,%R10

(220) 0x23d0a4 MOV	-0xb8(%RBP),%R15

(220) 0x23d0ab MOVSD	(%R15,%R10,8),%XMM3

(220) 0x23d0b1 MOV	%R12,%R10

(220) 0x23d0b4 IMUL	%R8,%R10

(220) 0x23d0b8 ADD	%R14,%R10

(220) 0x23d0bb MOVHPD	(%R15,%R10,8),%XMM3

(220) 0x23d0c1 ADDPD	%XMM2,%XMM3

(220) 0x23d0c5 IMUL	%R12,%RDI

(220) 0x23d0c9 IMUL	%R12,%RAX

(220) 0x23d0cd ADD	%RBX,%RDI

(220) 0x23d0d0 ADD	%R14,%RAX

(220) 0x23d0d3 MOVSD	(%R15,%RDI,8),%XMM2

(220) 0x23d0d9 MOVHPD	(%R15,%RAX,8),%XMM2

(220) 0x23d0df ADDPD	%XMM3,%XMM2

(220) 0x23d0e3 MULPD	%XMM1,%XMM2

(220) 0x23d0e7 MOV	-0xb0(%RBP),%RDI

(220) 0x23d0ee MOV	%RDI,%RAX

(220) 0x23d0f1 IMUL	%RDX,%RAX

(220) 0x23d0f5 IMUL	%R8,%RDI

(220) 0x23d0f9 ADD	%RBX,%RAX

(220) 0x23d0fc ADD	%R14,%RDI

(220) 0x23d0ff MOV	-0xa8(%RBP),%R10

(220) 0x23d106 MOVLPD	%XMM2,(%R10,%RAX,8)

(220) 0x23d10c MOVHPD	%XMM2,(%R10,%RDI,8)

(220) 0x23d112 MOV	-0xa0(%RBP),%RDI

(220) 0x23d119 MOV	%RDI,%RAX

(220) 0x23d11c IMUL	%RDX,%RAX

(220) 0x23d120 IMUL	%R8,%RDI

(220) 0x23d124 ADD	%RBX,%RAX

(220) 0x23d127 ADD	%R14,%RDI

(220) 0x23d12a MOV	-0x98(%RBP),%R10

(220) 0x23d131 MOVSD	(%R10,%RAX,8),%XMM1

(220) 0x23d137 MOVHPD	(%R10,%RDI,8),%XMM1

(220) 0x23d13d MOV	-0x90(%RBP),%RDI

(220) 0x23d144 MOV	%RDI,%RAX

(220) 0x23d147 IMUL	%RDX,%RAX

(220) 0x23d14b IMUL	%R8,%RDI

(220) 0x23d14f LEA	(%RAX,%RBX,1),%R10

(220) 0x23d153 MOV	-0x88(%RBP),%R15

(220) 0x23d15a MOVSD	(%R15,%R10,8),%XMM2

(220) 0x23d160 LEA	(%RDI,%R14,1),%R10

(220) 0x23d164 MOVHPD	(%R15,%R10,8),%XMM2

(220) 0x23d16a LEA	0x1(%RAX,%RBX,1),%RAX

(220) 0x23d16f LEA	0x1(%RDI,%R14,1),%RDI

(220) 0x23d174 MOVSD	(%R15,%RAX,8),%XMM3

(220) 0x23d17a MOVHPD	(%R15,%RDI,8),%XMM3

(220) 0x23d180 MOV	-0x80(%RBP),%RDI

(220) 0x23d184 MOV	%RDI,%RAX

(220) 0x23d187 IMUL	%RDX,%RAX

(220) 0x23d18b IMUL	%R8,%RDI

(220) 0x23d18f LEA	(%RAX,%RBX,1),%R10

(220) 0x23d193 MOV	-0x78(%RBP),%R15

(220) 0x23d197 MOVSD	(%R15,%R10,8),%XMM4

(220) 0x23d19d LEA	(%RDI,%R14,1),%R10

(220) 0x23d1a1 MOVHPD	(%R15,%R10,8),%XMM4

(220) 0x23d1a7 LEA	0x1(%RAX,%RBX,1),%RAX

(220) 0x23d1ac MOVSD	(%R15,%RAX,8),%XMM5

(220) 0x23d1b2 LEA	(%RDI,%R14,1),%RAX

(220) 0x23d1b6 INC	%RAX

(220) 0x23d1b9 MOVHPD	(%R15,%RAX,8),%XMM5

(220) 0x23d1bf MOV	-0x70(%RBP),%RAX

(220) 0x23d1c3 IMUL	%RAX,%RDX

(220) 0x23d1c7 ADD	%RBX,%RDX

(220) 0x23d1ca IMUL	%RAX,%R8

(220) 0x23d1ce ADD	%R14,%R8

(220) 0x23d1d1 MOV	0x18(%RBP),%RAX

(220) 0x23d1d5 MOVSD	(%RAX),%XMM6

(220) 0x23d1d9 MULSD	%XMM0,%XMM6

(220) 0x23d1dd UNPCKLPD	%XMM6,%XMM6

(220) 0x23d1e1 MULPD	%XMM6,%XMM1

(220) 0x23d1e5 ADDPD	%XMM2,%XMM3

(220) 0x23d1e9 ADDPD	%XMM3,%XMM4

(220) 0x23d1ed ADDPD	%XMM4,%XMM5

(220) 0x23d1f1 MULPD	%XMM1,%XMM5

(220) 0x23d1f5 MOV	-0x68(%RBP),%RAX

(220) 0x23d1f9 MOVLPD	%XMM5,(%RAX,%RDX,8)

(220) 0x23d1fe MOVHPD	%XMM5,(%RAX,%R8,8)

(220) 0x23d204 ADD	$0x2,%RSI

(220) 0x23d208 ADD	$-0x2,%R13

(220) 0x23d20c JE	23d267

(220) 0x23d20e MOV	%RSI,%RAX

(220) 0x23d211 SHR	$0x20,%RAX

(220) 0x23d215 MOV	-0x40(%RBP),%R10

(220) 0x23d219 JE	23d240

(220) 0x23d21b MOV	%RSI,%RAX

(220) 0x23d21e CQTO

(220) 0x23d220 IDIV	%R10

(220) 0x23d223 MOV	%RDX,%R8

(220) 0x23d226 MOV	%RAX,%RDI

(220) 0x23d229 LEA	0x1(%RSI),%RAX

(220) 0x23d22d MOV	%RAX,%RDX

(220) 0x23d230 SHR	$0x20,%RDX

(220) 0x23d234 JNE	23cfd0

(220) 0x23d23a JMP	23d25d

0x23d23c NOPL	(%RAX)

(220) 0x23d240 MOV	%ESI,%EAX

(220) 0x23d242 XOR	%EDX,%EDX

(220) 0x23d244 DIV	%R10D

(220) 0x23d247 MOV	%EDX,%R8D

(220) 0x23d24a MOV	%EAX,%EDI

(220) 0x23d24c LEA	0x1(%RSI),%RAX

(220) 0x23d250 MOV	%RAX,%RDX

(220) 0x23d253 SHR	$0x20,%RDX

(220) 0x23d257 JNE	23cfd0

(220) 0x23d25d XOR	%EDX,%EDX

(220) 0x23d25f DIV	%R10D

(220) 0x23d262 JMP	23cfd5

0x23d267 MOV	-0xc8(%RBP),%RAX

0x23d26e CMP	%RAX,-0xd0(%RBP)

0x23d275 MOV	-0x60(%RBP),%R14

0x23d279 MOV	-0xd8(%RBP),%R15

0x23d280 MOV	-0x40(%RBP),%R8

0x23d284 MOV	-0x38(%RBP),%RBX

0x23d288 JNE	23d3e4

0x23d28e LEA	0x2159b(%RIP),%RDI

0x23d295 MOV	-0x54(%RBP),%ESI

0x23d298 CALL	25cd00 <@plt_start@+0x540>

0x23d29d ADD	$0xd8,%RSP

0x23d2a4 POP	%RBX

0x23d2a5 POP	%R12

0x23d2a7 POP	%R13

0x23d2a9 POP	%R14

0x23d2ab POP	%R15

0x23d2ad POP	%RBP

0x23d2ae RET

0x23d2af NOP

(219) 0x23d2b0 MOV	%RCX,%RAX

(219) 0x23d2b3 CQTO

(219) 0x23d2b5 IDIV	%R8

(219) 0x23d2b8 MOV	-0x2c(%RBP),%EDI

(219) 0x23d2bb MOV	-0x48(%RBP),%R10

(219) 0x23d2bf LEA	(%R14,%RAX,1),%ESI

(219) 0x23d2c3 ADD	%EDI,%EDX

(219) 0x23d2c5 MOVSD	-0x2c185(%RIP),%XMM0

(219) 0x23d2cd MOV	0x18(%RBP),%R13

(219) 0x23d2d1 MOVSD	(%R13),%XMM1

(219) 0x23d2d7 MULSD	%XMM0,%XMM1

(219) 0x23d2db MOVSXD	%EDX,%RDX

(219) 0x23d2de MOVSXD	%ESI,%RSI

(219) 0x23d2e1 MOV	%R11,%RDI

(219) 0x23d2e4 IMUL	%RSI,%RDI

(219) 0x23d2e8 ADD	%RDX,%RDI

(219) 0x23d2eb MULSD	(%R10,%RDI,8),%XMM1

(219) 0x23d2f1 MOV	%R9,%RDI

(219) 0x23d2f4 IMUL	%RSI,%RDI

(219) 0x23d2f8 ADD	%RDX,%RDI

(219) 0x23d2fb MOVSD	(%RBX,%RDI,8),%XMM2

(219) 0x23d300 ADD	%R14D,%EAX

(219) 0x23d303 INC	%EAX

(219) 0x23d305 CLTQ

(219) 0x23d307 MOV	%R9,%RDI

(219) 0x23d30a IMUL	%RAX,%RDI

(219) 0x23d30e ADD	%RDX,%RDI

(219) 0x23d311 ADDSD	(%RBX,%RDI,8),%XMM2

(219) 0x23d316 MOV	%R12,%RDI

(219) 0x23d319 IMUL	%RSI,%RDI

(219) 0x23d31d ADD	%RDX,%RDI

(219) 0x23d320 MOV	-0xb8(%RBP),%R10

(219) 0x23d327 ADDSD	(%R10,%RDI,8),%XMM2

(219) 0x23d32d IMUL	%R12,%RAX

(219) 0x23d331 ADD	%RDX,%RAX

(219) 0x23d334 ADDSD	(%R10,%RAX,8),%XMM2

(219) 0x23d33a MULSD	%XMM1,%XMM2

(219) 0x23d33e MOV	-0xb0(%RBP),%RAX

(219) 0x23d345 IMUL	%RSI,%RAX

(219) 0x23d349 ADD	%RDX,%RAX

(219) 0x23d34c MOV	-0xa8(%RBP),%RDI

(219) 0x23d353 MOVSD	%XMM2,(%RDI,%RAX,8)

(219) 0x23d358 MULSD	(%R13),%XMM0

(219) 0x23d35e MOV	-0xa0(%RBP),%RAX

(219) 0x23d365 IMUL	%RSI,%RAX

(219) 0x23d369 ADD	%RDX,%RAX

(219) 0x23d36c MOV	-0x98(%RBP),%RDI

(219) 0x23d373 MULSD	(%RDI,%RAX,8),%XMM0

(219) 0x23d378 MOV	-0x90(%RBP),%RAX

(219) 0x23d37f IMUL	%RSI,%RAX

(219) 0x23d383 LEA	(%RAX,%RDX,1),%RDI

(219) 0x23d387 MOV	-0x88(%RBP),%R10

(219) 0x23d38e MOVSD	(%R10,%RDI,8),%XMM1

(219) 0x23d394 ADD	%RDX,%RAX

(219) 0x23d397 INC	%RAX

(219) 0x23d39a ADDSD	(%R10,%RAX,8),%XMM1

(219) 0x23d3a0 MOV	-0x80(%RBP),%RAX

(219) 0x23d3a4 IMUL	%RSI,%RAX

(219) 0x23d3a8 LEA	(%RAX,%RDX,1),%RDI

(219) 0x23d3ac MOV	-0x78(%RBP),%R10

(219) 0x23d3b0 ADDSD	(%R10,%RDI,8),%XMM1

(219) 0x23d3b6 ADD	%RDX,%RAX

(219) 0x23d3b9 INC	%RAX

(219) 0x23d3bc ADDSD	(%R10,%RAX,8),%XMM1

(219) 0x23d3c2 IMUL	-0x70(%RBP),%RSI

(219) 0x23d3c7 ADD	%RDX,%RSI

(219) 0x23d3ca MULSD	%XMM0,%XMM1

(219) 0x23d3ce MOV	-0x68(%RBP),%RAX

(219) 0x23d3d2 MOVSD	%XMM1,(%RAX,%RSI,8)

(219) 0x23d3d7 CMP	%R15,%RCX

(219) 0x23d3da LEA	0x1(%RCX),%RCX

(219) 0x23d3de JGE	23d28e

(219) 0x23d3e4 MOV	%RCX,%RAX

(219) 0x23d3e7 SHR	$0x20,%RAX

(219) 0x23d3eb JNE	23d2b0

(219) 0x23d3f1 MOV	%ECX,%EAX

(219) 0x23d3f3 XOR	%EDX,%EDX

(219) 0x23d3f5 DIV	%R8D

(219) 0x23d3f8 JMP	23d2b8

0x23d3fd NOPL	(%RAX)

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	flux_calc.cpp:36-40
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/flux_calc.cpp:36-40
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 17.75 to 1.67 cycles (10.65x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your function is not vectorized. Only 11% 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 17.75 to 1.58 cycles (11.25x 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

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 17.75 to 16.00 cycles (1.11x speedup).

Workaround

Read less array elements
Write less array elements

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/flux_calc.cpp:36
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/flux_calc.cpp:36

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/flux_calc.cpp:37

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 304 bytes. The binary function is storing 212 bytes.

General properties

nb instructions	129
nb uops	128
loop length	544
used x86 registers	16
used mmx registers	0
used xmm registers	1
used ymm registers	0
used zmm registers	0
nb stack references	35

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.00 cycles
front end	16.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.67	6.67	6.67	6.67	6.67	6.67	17.75	17.75	17.75	17.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.67	6.67	6.67	6.67	6.67	6.67	17.75	17.75	17.75	17.75	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	16.00
Dispatch	17.75
Overall L1	17.75

Vectorization ratios

INT

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	0%
load	0%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

INT

all	11%
load	10%
store	11%
mul	12%
add-sub	7%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	12%
load	12%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	11%
load	11%
store	11%
mul	12%
add-sub	7%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 17.75 cycles. At this rate:

6% of peak load performance is reached (17.13 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (11.94 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 23ce00

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 $0xd8,%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),%R14D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV (%RCX),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x3,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
SUB %R14D,%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 23d29d <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x49d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
INC %EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD $0x3,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP %EAX,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 23d29d <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x49d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	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%)
SUB %EAX,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
IMUL %RBX,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOVQ $0,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R15,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0xf8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $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 (%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 -0xf8(%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 0x2199a(%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 -0x58(%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 -0xc0(%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 -0x50(%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,-0x54(%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 -0x50(%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	scal (12.5%)
MOV %R15,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xc0(%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 23d28e <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x48e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RBX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x48(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x40(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x28(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%R9),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%R8),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R8,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RCX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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 %R15,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R10,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JAE 23cf86 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x186>	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
MOV -0x40(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 23d3e4 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x5e4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R15,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R14,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
AND $-0x2,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R13,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOVSD -0x2be60(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
MOV %R13,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R9,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R12,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 23d20e <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x40e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xc8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xd0(%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 -0x60(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0xd8(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x40(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 23d3e4 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x5e4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x2159b(%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 -0x54(%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 $0xd8,%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
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	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	flux_calc.cpp:36-40
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/flux_calc.cpp:36-40
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

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

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 17.75 to 16.00 cycles (1.11x speedup).

Workaround

Read less array elements
Write less array elements

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/flux_calc.cpp:36
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/flux_calc.cpp:36

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/flux_calc.cpp:37

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 304 bytes. The binary function is storing 212 bytes.

General properties

nb instructions	129
nb uops	128
loop length	544
used x86 registers	16
used mmx registers	0
used xmm registers	1
used ymm registers	0
used zmm registers	0
nb stack references	35

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.00 cycles
front end	16.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.67	6.67	6.67	6.67	6.67	6.67	17.75	17.75	17.75	17.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.67	6.67	6.67	6.67	6.67	6.67	17.75	17.75	17.75	17.75	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	16.00
Dispatch	17.75
Overall L1	17.75

Vectorization ratios

INT

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	0%
load	0%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

INT

all	11%
load	10%
store	11%
mul	12%
add-sub	7%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	12%
load	12%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	11%
load	11%
store	11%
mul	12%
add-sub	7%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 17.75 cycles. At this rate:

6% of peak load performance is reached (17.13 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (11.94 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 23ce00

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 $0xd8,%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),%R14D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV (%RCX),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x3,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
SUB %R14D,%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 23d29d <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x49d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
INC %EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD $0x3,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP %EAX,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 23d29d <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x49d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	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%)
SUB %EAX,%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
IMUL %RBX,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOVQ $0,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R15,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0xf8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $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 (%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 -0xf8(%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 0x2199a(%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 -0x58(%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 -0xc0(%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 -0x50(%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,-0x54(%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 -0x50(%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	scal (12.5%)
MOV %R15,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xc0(%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 23d28e <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x48e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RBX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x48(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x40(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x28(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%R9),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%R8),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R8,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RCX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RAX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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 %R15,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R10,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JAE 23cf86 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x186>	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
MOV -0x40(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 23d3e4 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x5e4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R15,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R14,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
AND $-0x2,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R13,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOVSD -0x2be60(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
MOV %R13,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R9,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R12,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 23d20e <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x40e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xc8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xd0(%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 -0x60(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0xd8(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x40(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 23d3e4 <_Z16flux_calc_kerneliiiidRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x5e4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x2159b(%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 -0x54(%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 $0xd8,%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
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼flux_calc_kernel(int, int, int, int, double, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D–	4.09	1.60
○Loop 220 - flux_calc.cpp:37-40 - exec	4.09	1.59
○Loop 219 - flux_calc.cpp:37-40 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

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

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

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