OV - exec - Function viscosity_kernel(int, int, int, int, clover::Buffer1D<double>&, clover::Buffer1D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&) [clone .extracted]

	Function: viscosity_kernel(int, int, int, int, clover::Buffer1D<double>&, clover::Buffer1D<double>&, ...	Module: exec	Source: viscosity.cpp:36-64 [...]	Coverage (incl. loops): 2.24% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: 46 - 69

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

46:   T &operator[](size_t i) const { return data[i]; }

[...]

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/viscosity.cpp: 36 - 64

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

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

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

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

39:       double ugrad = (xvel0(i + 1, j + 0) + xvel0(i + 1, j + 1)) - (xvel0(i, j) + xvel0(i + 0, j + 1));

40:       double vgrad = (yvel0(i + 0, j + 1) + yvel0(i + 1, j + 1)) - (yvel0(i, j) + yvel0(i + 1, j + 0));

41:       double div = (celldx[i] * (ugrad) + celldy[j] * (vgrad));

42:       double strain2 = 0.5 * (xvel0(i + 0, j + 1) + xvel0(i + 1, j + 1) - xvel0(i, j) - xvel0(i + 1, j + 0)) / celldy[j] +

43:                        0.5 * (yvel0(i + 1, j + 0) + yvel0(i + 1, j + 1) - yvel0(i, j) - yvel0(i + 0, j + 1)) / celldx[i];

44:       double pgradx = (pressure(i + 1, j + 0) - pressure(i - 1, j + 0)) / (celldx[i] + celldx[i + 1]);

45:       double pgrady = (pressure(i + 0, j + 1) - pressure(i + 0, j - 1)) / (celldy[j] + celldy[j + 2]);

46:       double pgradx2 = pgradx * pgradx;

47:       double pgrady2 = pgrady * pgrady;

48:       double limiter = ((0.5 * (ugrad) / celldx[i]) * pgradx2 + (0.5 * (vgrad) / celldy[j]) * pgrady2 + strain2 * pgradx * pgrady) /

49:                        std::fmax(pgradx2 + pgrady2, g_small);

50:       if ((limiter > 0.0) || (div >= 0.0)) {

51:         viscosity(i, j) = 0.0;

52:       } else {

53:         double dirx = 1.0;

54:         if (pgradx < 0.0) dirx = -1.0;

55:         pgradx = dirx * std::fmax(g_small, std::fabs(pgradx));

56:         double diry = 1.0;

57:         if (pgradx < 0.0) diry = -1.0;

58:         pgrady = diry * std::fmax(g_small, std::fabs(pgrady));

59:         double pgrad = std::sqrt(pgradx * pgradx + pgrady * pgrady);

60:         double xgrad = std::fabs(celldx[i] * pgrad / pgradx);

61:         double ygrad = std::fabs(celldy[j] * pgrad / pgrady);

62:         double grad = std::fmin(xgrad, ygrad);

63:         double grad2 = grad * grad;

64:         viscosity(i, j) = 2.0 * density0(i, j) * grad2 * limiter * limiter;

0x4619a0 PUSH	%RBP

0x4619a1 MOV	%RSP,%RBP

0x4619a4 PUSH	%R15

0x4619a6 PUSH	%R14

0x4619a8 PUSH	%R13

0x4619aa PUSH	%R12

0x4619ac PUSH	%RBX

0x4619ad SUB	$0xb8,%RSP

0x4619b4 MOV	%R8,-0x78(%RBP)

0x4619b8 MOV	%RCX,%RSI

0x4619bb MOV	0x48(%RBP),%RAX

0x4619bf MOV	0x38(%RBP),%R15

0x4619c3 MOV	0x30(%RBP),%RCX

0x4619c7 MOV	%RCX,-0x60(%RBP)

0x4619cb MOV	0x28(%RBP),%RCX

0x4619cf MOV	%RCX,-0x58(%RBP)

0x4619d3 MOV	0x20(%RBP),%RBX

0x4619d7 MOV	0x18(%RBP),%R14

0x4619db MOV	0x10(%RBP),%R12

0x4619df MOVL	$0,-0x40(%RBP)

0x4619e6 TEST	%RAX,%RAX

0x4619e9 JS	461a74

0x4619ef MOV	%R9,%R13

0x4619f2 MOV	%RDX,-0x38(%RBP)

0x4619f6 MOV	%RSI,-0x30(%RBP)

0x4619fa MOV	(%RDI),%ESI

0x4619fc MOVQ	$0,-0x70(%RBP)

0x461a04 MOV	%RAX,-0x68(%RBP)

0x461a08 MOVQ	$0x1,-0xd8(%RBP)

0x461a13 SUB	$0x8,%RSP

0x461a17 LEA	-0xd8(%RBP),%RAX

0x461a1e LEA	-0x40(%RBP),%RCX

0x461a22 LEA	-0x70(%RBP),%R8

0x461a26 LEA	-0x68(%RBP),%R9

0x461a2a MOV	$0x4956e0,%EDI

0x461a2f MOV	%ESI,-0x3c(%RBP)

0x461a32 MOV	$0x22,%EDX

0x461a37 PUSH	$0x1

0x461a39 PUSH	$0x1

0x461a3b PUSH	%RAX

0x461a3c CALL	404230 <__kmpc_for_static_init_8@plt>

0x461a41 ADD	$0x20,%RSP

0x461a45 MOV	-0x70(%RBP),%RCX

0x461a49 MOV	-0x68(%RBP),%RAX

0x461a4d MOV	%RAX,-0x50(%RBP)

0x461a51 CMP	%RAX,%RCX

0x461a54 JBE	461a86

0x461a56 MOV	$0x495700,%EDI

0x461a5b MOV	-0x3c(%RBP),%ESI

0x461a5e ADD	$0xb8,%RSP

0x461a65 POP	%RBX

0x461a66 POP	%R12

0x461a68 POP	%R13

0x461a6a POP	%R14

0x461a6c POP	%R15

0x461a6e POP	%RBP

0x461a6f JMP	404050

0x461a74 ADD	$0xb8,%RSP

0x461a7b POP	%RBX

0x461a7c POP	%R12

0x461a7e POP	%R13

0x461a80 POP	%R14

0x461a82 POP	%R15

0x461a84 POP	%RBP

0x461a85 RET

0x461a86 MOV	(%R14),%RAX

0x461a89 MOV	%RAX,-0xd0(%RBP)

0x461a90 MOV	0x10(%R14),%RAX

0x461a94 MOV	%RAX,-0xc0(%RBP)

0x461a9b MOV	(%RBX),%RAX

0x461a9e MOV	%RAX,-0xc8(%RBP)

0x461aa5 MOV	0x10(%RBX),%RAX

0x461aa9 MOV	%RAX,-0xb0(%RBP)

0x461ab0 MOV	-0x38(%RBP),%RAX

0x461ab4 MOV	0x8(%RAX),%RAX

0x461ab8 MOV	%RAX,-0x38(%RBP)

0x461abc MOV	-0x30(%RBP),%RAX

0x461ac0 MOV	0x8(%RAX),%RAX

0x461ac4 MOV	%RAX,-0x30(%RBP)

0x461ac8 MOV	(%R13),%RAX

0x461acc MOV	%RAX,-0xb8(%RBP)

0x461ad3 MOV	0x10(%R13),%R14

0x461ad7 MOV	(%R12),%RAX

0x461adb MOV	%RAX,-0xa8(%RBP)

0x461ae2 MOV	0x10(%R12),%RAX

0x461ae7 MOV	%RAX,-0xa0(%RBP)

0x461aee MOV	-0x60(%RBP),%RAX

0x461af2 SUB	%EAX,%R15D

0x461af5 MOV	%RAX,%RDX

0x461af8 INC	%RDX

0x461afb MOV	%RDX,-0x98(%RBP)

0x461b02 MOV	-0x58(%RBP),%RDX

0x461b06 LEA	0x1(%RDX),%RSI

0x461b0a MOV	%RSI,-0x90(%RBP)

0x461b11 MOV	$-0x1,%ESI

0x461b16 ADD	%RDX,%RSI

0x461b19 MOV	%RSI,-0x88(%RBP)

0x461b20 INCQ	-0x50(%RBP)

0x461b24 MOVSD	0x129b4(%RIP),%XMM0

0x461b2c XORPD	%XMM4,%XMM4

0x461b30 DEC	%EAX

0x461b32 MOV	%RAX,-0x80(%RBP)

0x461b36 MOV	%R15,-0x48(%RBP)

0x461b3a MOV	-0x58(%RBP),%RDI

0x461b3e MOV	-0x60(%RBP),%R10

0x461b42 JMP	461b78

0x461b44 NOPW	%CS:(%RAX,%RAX,1)

(813) 0x461b50 MOV	-0x48(%RBP),%R15

(813) 0x461b54 IMUL	-0xa8(%RBP),%RDX

(813) 0x461b5c ADD	%R13,%RDX

(813) 0x461b5f MOV	-0xa0(%RBP),%RAX

(813) 0x461b66 MOVSD	%XMM1,(%RAX,%RDX,8)

(813) 0x461b6b INC	%RCX

(813) 0x461b6e CMP	%RCX,-0x50(%RBP)

(813) 0x461b72 JE	461a56

(813) 0x461b78 MOV	%RCX,%R8

(813) 0x461b7b SHR	$0x20,%R8

(813) 0x461b7f JE	461b90

(813) 0x461b81 MOV	%RCX,%RAX

(813) 0x461b84 CQTO

(813) 0x461b86 IDIV	%R15

(813) 0x461b89 MOV	%RDX,%RSI

(813) 0x461b8c JMP	461b99

0x461b8e XCHG	%AX,%AX

(813) 0x461b90 MOV	%ECX,%EAX

(813) 0x461b92 XOR	%EDX,%EDX

(813) 0x461b94 DIV	%R15D

(813) 0x461b97 MOV	%EDX,%ESI

(813) 0x461b99 MOV	-0x98(%RBP),%RAX

(813) 0x461ba0 ADD	%ESI,%EAX

(813) 0x461ba2 MOVSXD	%EAX,%R12

(813) 0x461ba5 TEST	%R8,%R8

(813) 0x461ba8 JE	461bc0

(813) 0x461baa MOV	%RCX,%RAX

(813) 0x461bad XOR	%EDX,%EDX

(813) 0x461baf DIV	%R15

(813) 0x461bb2 JMP	461bc7

0x461bb4 NOPW	%CS:(%RAX,%RAX,1)

(813) 0x461bc0 MOV	%ECX,%EAX

(813) 0x461bc2 XOR	%EDX,%EDX

(813) 0x461bc4 DIV	%R15D

(813) 0x461bc7 LEA	(%RDI,%RAX,1),%EDX

(813) 0x461bca MOVSXD	%EDX,%RDX

(813) 0x461bcd MOV	-0xd0(%RBP),%RBX

(813) 0x461bd4 MOV	%RBX,%R15

(813) 0x461bd7 IMUL	%RDX,%R15

(813) 0x461bdb LEA	(%R12,%R15,1),%R8

(813) 0x461bdf MOV	-0xc0(%RBP),%R9

(813) 0x461be6 MOVSD	(%R9,%R8,8),%XMM6

(813) 0x461bec MOV	-0x90(%RBP),%R8

(813) 0x461bf3 ADD	%EAX,%R8D

(813) 0x461bf6 MOVSXD	%R8D,%R8

(813) 0x461bf9 IMUL	%R8,%RBX

(813) 0x461bfd LEA	(%R12,%RBX,1),%R13

(813) 0x461c01 MOVSD	(%R9,%R13,8),%XMM5

(813) 0x461c07 LEA	(%R10,%RSI,1),%R13D

(813) 0x461c0b MOVSXD	%R13D,%R13

(813) 0x461c0e ADD	%R13,%R15

(813) 0x461c11 MOVSD	(%R9,%R15,8),%XMM9

(813) 0x461c17 ADD	%R13,%RBX

(813) 0x461c1a MOVSD	(%R9,%RBX,8),%XMM8

(813) 0x461c20 MOV	-0xc8(%RBP),%R9

(813) 0x461c27 MOV	%R9,%RBX

(813) 0x461c2a IMUL	%R8,%RBX

(813) 0x461c2e LEA	(%RBX,%R13,1),%R15

(813) 0x461c32 MOV	-0xb0(%RBP),%R11

(813) 0x461c39 MOVSD	(%R11,%R15,8),%XMM11

(813) 0x461c3f ADD	%R12,%RBX

(813) 0x461c42 MOVSD	(%R11,%RBX,8),%XMM3

(813) 0x461c48 IMUL	%RDX,%R9

(813) 0x461c4c LEA	(%R9,%R13,1),%R15

(813) 0x461c50 MOVSD	(%R11,%R15,8),%XMM15

(813) 0x461c56 ADD	%R12,%R9

(813) 0x461c59 MOVSD	(%R11,%R9,8),%XMM14

(813) 0x461c5f MOV	-0xb8(%RBP),%R11

(813) 0x461c66 MOV	%R11,%RBX

(813) 0x461c69 IMUL	%RDX,%RBX

(813) 0x461c6d ADD	%RBX,%R12

(813) 0x461c70 MOVSD	(%R14,%R12,8),%XMM10

(813) 0x461c76 MOV	-0x80(%RBP),%R9

(813) 0x461c7a LEA	(%R9,%RSI,1),%R15D

(813) 0x461c7e MOVSXD	%R15D,%R15

(813) 0x461c81 ADD	%RBX,%R15

(813) 0x461c84 SUBSD	(%R14,%R15,8),%XMM10

(813) 0x461c8a ADD	%R10D,%ESI

(813) 0x461c8d INC	%ESI

(813) 0x461c8f MOVSXD	%ESI,%RSI

(813) 0x461c92 MOV	-0x38(%RBP),%R9

(813) 0x461c96 MOVSD	(%R9,%RSI,8),%XMM1

(813) 0x461c9c IMUL	%R11,%R8

(813) 0x461ca0 ADD	%R13,%R8

(813) 0x461ca3 MOVSD	(%R14,%R8,8),%XMM13

(813) 0x461ca9 MOV	-0x88(%RBP),%RSI

(813) 0x461cb0 ADD	%EAX,%ESI

(813) 0x461cb2 MOVSXD	%ESI,%RSI

(813) 0x461cb5 IMUL	%R11,%RSI

(813) 0x461cb9 ADD	%R13,%RSI

(813) 0x461cbc SUBSD	(%R14,%RSI,8),%XMM13

(813) 0x461cc2 ADD	%EDI,%EAX

(813) 0x461cc4 ADD	$0x2,%EAX

(813) 0x461cc7 CLTQ

(813) 0x461cc9 MOV	-0x30(%RBP),%RSI

(813) 0x461ccd MOVSD	(%RSI,%RAX,8),%XMM2

(813) 0x461cd2 MOVAPD	%XMM5,%XMM7

(813) 0x461cd6 ADDSD	%XMM6,%XMM7

(813) 0x461cda ADDSD	%XMM9,%XMM6

(813) 0x461cdf ADDSD	%XMM8,%XMM9

(813) 0x461ce4 SUBSD	%XMM9,%XMM7

(813) 0x461ce9 MOVAPD	%XMM3,%XMM12

(813) 0x461cee ADDSD	%XMM11,%XMM12

(813) 0x461cf3 ADDSD	%XMM15,%XMM11

(813) 0x461cf8 ADDSD	%XMM14,%XMM15

(813) 0x461cfd SUBSD	%XMM15,%XMM12

(813) 0x461d02 SUBSD	%XMM6,%XMM5

(813) 0x461d06 MOVSD	(%R9,%R13,8),%XMM9

(813) 0x461d0c ADDSD	%XMM8,%XMM5

(813) 0x461d11 MOVSD	(%RSI,%RDX,8),%XMM6

(813) 0x461d16 MULSD	%XMM0,%XMM5

(813) 0x461d1a SUBSD	%XMM11,%XMM3

(813) 0x461d1f ADDSD	%XMM14,%XMM3

(813) 0x461d24 MOVSD	0x11d3b(%RIP),%XMM14

(813) 0x461d2d MOVAPD	%XMM14,%XMM11

(813) 0x461d32 DIVSD	%XMM9,%XMM11

(813) 0x461d37 MOVAPD	%XMM0,%XMM8

(813) 0x461d3c MULSD	%XMM11,%XMM8

(813) 0x461d41 MULSD	%XMM3,%XMM8

(813) 0x461d46 MOVAPD	%XMM14,%XMM3

(813) 0x461d4b DIVSD	%XMM6,%XMM3

(813) 0x461d4f MULSD	%XMM3,%XMM5

(813) 0x461d53 ADDSD	%XMM5,%XMM8

(813) 0x461d58 ADDSD	%XMM9,%XMM1

(813) 0x461d5d DIVSD	%XMM1,%XMM10

(813) 0x461d62 ADDSD	%XMM6,%XMM2

(813) 0x461d66 DIVSD	%XMM2,%XMM13

(813) 0x461d6b MOVAPD	%XMM10,%XMM1

(813) 0x461d70 MULSD	%XMM10,%XMM1

(813) 0x461d75 MOVAPD	%XMM13,%XMM2

(813) 0x461d7a MULSD	%XMM13,%XMM2

(813) 0x461d7f MOVAPD	%XMM7,%XMM5

(813) 0x461d83 MULSD	%XMM0,%XMM5

(813) 0x461d87 MULSD	%XMM11,%XMM5

(813) 0x461d8c MULSD	%XMM1,%XMM5

(813) 0x461d90 MOVAPD	%XMM12,%XMM11

(813) 0x461d95 MULSD	%XMM0,%XMM11

(813) 0x461d9a MULSD	%XMM3,%XMM11

(813) 0x461d9f MULSD	%XMM2,%XMM11

(813) 0x461da4 MULSD	%XMM10,%XMM8

(813) 0x461da9 MULSD	%XMM13,%XMM8

(813) 0x461dae ADDSD	%XMM5,%XMM8

(813) 0x461db3 ADDSD	%XMM11,%XMM8

(813) 0x461db8 ADDSD	%XMM1,%XMM2

(813) 0x461dbc MAXSD	0x115dc(%RIP),%XMM2

(813) 0x461dc4 DIVSD	%XMM2,%XMM8

(813) 0x461dc9 XORPD	%XMM1,%XMM1

(813) 0x461dcd UCOMISD	%XMM1,%XMM8

(813) 0x461dd2 JA	461b50

(813) 0x461dd8 MULSD	%XMM9,%XMM7

(813) 0x461ddd MULSD	%XMM6,%XMM12

(813) 0x461de2 ADDSD	%XMM7,%XMM12

(813) 0x461de7 UCOMISD	%XMM4,%XMM12

(813) 0x461dec MOV	-0x48(%RBP),%R15

(813) 0x461df0 JAE	461b54

(813) 0x461df6 MOVAPD	%XMM10,%XMM3

(813) 0x461dfb MOVAPD	0x11ccd(%RIP),%XMM7

(813) 0x461e03 ANDPD	%XMM7,%XMM3

(813) 0x461e07 MOVSD	0x11591(%RIP),%XMM2

(813) 0x461e0f MAXSD	%XMM2,%XMM3

(813) 0x461e13 XORPD	%XMM5,%XMM5

(813) 0x461e17 CMPSD	$0x1,%XMM5,%XMM10

(813) 0x461e1d MOVAPD	%XMM10,%XMM1

(813) 0x461e22 ANDNPD	%XMM3,%XMM1

(813) 0x461e26 MOVAPD	0x12822(%RIP),%XMM4

(813) 0x461e2e XORPD	%XMM4,%XMM3

(813) 0x461e32 ANDPD	%XMM10,%XMM3

(813) 0x461e37 ORPD	%XMM1,%XMM3

(813) 0x461e3b ANDPD	%XMM7,%XMM13

(813) 0x461e40 MAXSD	%XMM2,%XMM13

(813) 0x461e45 MOVAPD	%XMM13,%XMM1

(813) 0x461e4a XORPD	%XMM4,%XMM1

(813) 0x461e4e MOVAPD	%XMM3,%XMM2

(813) 0x461e52 XORPD	%XMM4,%XMM4

(813) 0x461e56 CMPSD	$0x1,%XMM5,%XMM2

(813) 0x461e5b ANDPD	%XMM2,%XMM1

(813) 0x461e5f ANDNPD	%XMM13,%XMM2

(813) 0x461e64 ORPD	%XMM1,%XMM2

(813) 0x461e68 MOVAPD	%XMM3,%XMM1

(813) 0x461e6c MULSD	%XMM3,%XMM1

(813) 0x461e70 MOVAPD	%XMM2,%XMM5

(813) 0x461e74 MULSD	%XMM2,%XMM5

(813) 0x461e78 ADDSD	%XMM1,%XMM5

(813) 0x461e7c XORPS	%XMM1,%XMM1

(813) 0x461e7f SQRTSD	%XMM5,%XMM1

(813) 0x461e83 MULSD	%XMM1,%XMM9

(813) 0x461e88 DIVSD	%XMM3,%XMM9

(813) 0x461e8d ANDPD	%XMM7,%XMM9

(813) 0x461e92 MULSD	%XMM1,%XMM6

(813) 0x461e96 DIVSD	%XMM2,%XMM6

(813) 0x461e9a ANDPD	%XMM7,%XMM6

(813) 0x461e9e MINSD	%XMM9,%XMM6

(813) 0x461ea3 MOV	-0x78(%RBP),%RSI

(813) 0x461ea7 MOV	0x10(%RSI),%RAX

(813) 0x461eab MULSD	%XMM8,%XMM6

(813) 0x461eb0 MULSD	%XMM6,%XMM6

(813) 0x461eb4 MOV	(%RSI),%RSI

(813) 0x461eb7 IMUL	%RDX,%RSI

(813) 0x461ebb ADD	%R13,%RSI

(813) 0x461ebe MOVSD	(%RAX,%RSI,8),%XMM1

(813) 0x461ec3 ADDSD	%XMM1,%XMM1

(813) 0x461ec7 MULSD	%XMM6,%XMM1

(813) 0x461ecb JMP	461b54

Coverage (%)	Name	Source Location	Module
►47.89+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►39.71+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
►6.07+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
►3.02+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
►2.79+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	viscosity	viscosity.cpp:36	exec
○	timestep	timestep.cpp:64	exec
○	hydro	basic_string.h:1024	exec
○	main	clover_leaf.cpp:208	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	definitions.cpp:0	exec

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 icx_10

Source file and lines	viscosity.cpp:36-64
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:46,69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/viscosity.cpp:36-64

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 13.75 to 0.67 cycles (20.62x speedup).

Workaround

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

Vectorization

Your function is probably 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 13.75 to 1.30 cycles (10.60x speedup).

Details

Store and arithmetical 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)

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.

__kmpc_for_static_init_8@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/viscosity.cpp:36

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 224 bytes. The binary function is storing 200 bytes.

General properties

nb instructions	109
nb uops	107
loop length	446
used x86 registers	15
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	30

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.38 cycles
front end	13.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.50	4.50	4.50	4.50	4.50	4.50	13.75	13.75	13.75	13.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	4.50	4.50	4.50	4.50	4.50	4.50	13.75	13.75	13.75	13.75	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	13.38
Dispatch	13.75
Overall L1	13.75

Vectorization ratios

INT

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

all	50%
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	100%

INT+FP

all	2%
load	0%
store	0%
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	20%

Vector efficiency ratios

INT

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

all	18%
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	25%

INT+FP

all	11%
load	11%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	11%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 13.75 cycles. At this rate:

6% of peak load performance is reached (16.29 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.55 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: 4619a0

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 $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R8,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV 0x48(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x38(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x28(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x20(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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%)
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JS 461a74 <_Z16viscosity_kerneliiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_.extracted+0xd4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R9,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RSI,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOVQ $0,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
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%)
MOVQ $0x1,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
LEA -0xd8(%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 -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 -0x70(%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 -0x68(%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 $0x4956e0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	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 404230 <__kmpc_for_static_init_8@plt>	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	scal (12.5%)
MOV -0x70(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x68(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %RAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JBE 461a86 <_Z16viscosity_kerneliiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_.extracted+0xe6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV $0x495700,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x3c(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
ADD $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
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
JMP 404050 <__kmpc_for_static_fini@plt>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
ADD $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
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
MOV (%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RBX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xc8(%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),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xb0(%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 0x8(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%R13),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%R13),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R12),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%R12),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SUB %EAX,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	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 -0x58(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA 0x1(%RDX),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RSI,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV $-0x1,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD %RDX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %RSI,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
INCQ -0x50(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
MOVSD 0x129b4(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
XORPD %XMM4,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
DEC %EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x48(%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),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x60(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JMP 461b78 <_Z16viscosity_kerneliiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_.extracted+0x1d8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	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 icx_10

Source file and lines	viscosity.cpp:36-64
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:46,69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/viscosity.cpp:36-64

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)

Workaround

Read less array elements
Write less array elements

No data for this section

CALL instructions

Detected function call instructions.

Details

__kmpc_for_static_init_8@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/viscosity.cpp:36

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 224 bytes. The binary function is storing 200 bytes.

General properties

nb instructions	109
nb uops	107
loop length	446
used x86 registers	15
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	30

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.38 cycles
front end	13.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.50	4.50	4.50	4.50	4.50	4.50	13.75	13.75	13.75	13.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	4.50	4.50	4.50	4.50	4.50	4.50	13.75	13.75	13.75	13.75	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	13.38
Dispatch	13.75
Overall L1	13.75

Vectorization ratios

INT

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

all	50%
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	100%

INT+FP

all	2%
load	0%
store	0%
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	20%

Vector efficiency ratios

INT

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

all	18%
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	25%

INT+FP

all	11%
load	11%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	11%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 13.75 cycles. At this rate:

6% of peak load performance is reached (16.29 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.55 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: 4619a0

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 $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R8,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV 0x48(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x38(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x28(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RCX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x20(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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%)
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JS 461a74 <_Z16viscosity_kerneliiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_.extracted+0xd4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R9,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RSI,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOVQ $0,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
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%)
MOVQ $0x1,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
LEA -0xd8(%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 -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 -0x70(%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 -0x68(%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 $0x4956e0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	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 404230 <__kmpc_for_static_init_8@plt>	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	scal (12.5%)
MOV -0x70(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x68(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %RAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JBE 461a86 <_Z16viscosity_kerneliiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_.extracted+0xe6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV $0x495700,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x3c(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
ADD $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
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
JMP 404050 <__kmpc_for_static_fini@plt>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
ADD $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
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
MOV (%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RBX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xc8(%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),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xb0(%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 0x8(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%R13),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%R13),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R12),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%R12),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SUB %EAX,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	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 -0x58(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA 0x1(%RDX),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RSI,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV $-0x1,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD %RDX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %RSI,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
INCQ -0x50(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
MOVSD 0x129b4(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
XORPD %XMM4,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
DEC %EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x48(%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),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x60(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JMP 461b78 <_Z16viscosity_kerneliiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_.extracted+0x1d8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	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)
▼viscosity_kernel(int, int, int, int, clover::Buffer1D&, clover::Buffer1D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&) [clone .extracted]–	2.24	0.84
○Loop 813 - viscosity.cpp:36-64 - exec	2.24	0.84

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

CALL 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

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