OV - exec - Function hypre_CSRMatrixMatvecOutOfPlace

	Function: hypre_CSRMatrixMatvecOutOfPlace	Module: exec	Source: csr_matvec.c:41-417 [...]	Coverage (incl. loops): 0.05% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c: 41 - 417

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

41: {

[...]

48:    HYPRE_Complex    *A_data   = hypre_CSRMatrixData(A);

49:    HYPRE_Int        *A_i      = hypre_CSRMatrixI(A) + offset;

50:    HYPRE_Int        *A_j      = hypre_CSRMatrixJ(A);

51:    HYPRE_Int         num_rows = hypre_CSRMatrixNumRows(A) - offset;

52:    HYPRE_Int         num_cols = hypre_CSRMatrixNumCols(A);

53:    /*HYPRE_Int         num_nnz  = hypre_CSRMatrixNumNonzeros(A);*/

54:

55:    HYPRE_Int        *A_rownnz = hypre_CSRMatrixRownnz(A);

56:    HYPRE_Int         num_rownnz = hypre_CSRMatrixNumRownnz(A);

57:

58:    HYPRE_Complex    *x_data = hypre_VectorData(x);

59:    HYPRE_Complex    *b_data = hypre_VectorData(b) + offset;

60:    HYPRE_Complex    *y_data = hypre_VectorData(y) + offset;

61:    HYPRE_Int         x_size = hypre_VectorSize(x);

62:    HYPRE_Int         b_size = hypre_VectorSize(b) - offset;

63:    HYPRE_Int         y_size = hypre_VectorSize(y) - offset;

64:    HYPRE_Int         num_vectors = hypre_VectorNumVectors(x);

65:    HYPRE_Int         idxstride_y = hypre_VectorIndexStride(y);

66:    HYPRE_Int         vecstride_y = hypre_VectorVectorStride(y);

67:    /*HYPRE_Int         idxstride_b = hypre_VectorIndexStride(b);

68:    HYPRE_Int         vecstride_b = hypre_VectorVectorStride(b);*/

69:    HYPRE_Int         idxstride_x = hypre_VectorIndexStride(x);

70:    HYPRE_Int         vecstride_x = hypre_VectorVectorStride(x);

[...]

94:    hypre_assert( num_vectors == hypre_VectorNumVectors(y) );

95:    hypre_assert( num_vectors == hypre_VectorNumVectors(b) );

96:

97:    if (num_cols != x_size)

98:       ierr = 1;

99:

100:    if (num_rows != y_size || num_rows != b_size)

101:       ierr = 2;

102:

103:    if (num_cols != x_size && (num_rows != y_size || num_rows != b_size))

[...]

110:    if (alpha == 0.0)

111:    {

112: #ifdef HYPRE_USING_OPENMP

113: #pragma omp parallel for private(i) HYPRE_SMP_SCHEDULE

114: #endif

115:       for (i = 0; i < num_rows*num_vectors; i++)

[...]

125:    if (x == y)

126:    {

127:       x_tmp = hypre_SeqVectorCloneDeep(x);

128:       x_data = hypre_VectorData(x_tmp);

[...]

135:    temp = beta / alpha;

136:

137: /* use rownnz pointer to do the A*x multiplication  when num_rownnz is smaller than num_rows */

138:

139:    if (num_rownnz < xpar*(num_rows) || num_vectors > 1)

[...]

145:       if (temp != 1.0)

146:       {

147:          if (temp == 0.0)

148:          {

149: #ifdef HYPRE_USING_OPENMP

150: #pragma omp parallel for private(i) HYPRE_SMP_SCHEDULE

151: #endif

152:             for (i = 0; i < num_rows*num_vectors; i++)

[...]

158: #pragma omp parallel for private(i) HYPRE_SMP_SCHEDULE

159: #endif

160:             for (i = 0; i < num_rows*num_vectors; i++)

[...]

166:             for (i = 0; i < num_rows*num_vectors; i++)

167:                y_data[i] = b_data[i];

[...]

175:       if (num_rownnz < xpar*(num_rows))

176:       {

177: #ifdef HYPRE_USING_OPENMP

178: #pragma omp parallel for private(i,j,jj,m,tempx) HYPRE_SMP_SCHEDULE

179: #endif

180:

181:          for (i = 0; i < num_rownnz; i++)

[...]

211: #pragma omp parallel for private(i,j,jj,tempx) HYPRE_SMP_SCHEDULE

212: #endif

213:          for (i = 0; i < num_rows; i++)

[...]

231:       if (alpha != 1.0)

232:       {

233: #ifdef HYPRE_USING_OPENMP

234: #pragma omp parallel for private(i) HYPRE_SMP_SCHEDULE

235: #endif

236:          for (i = 0; i < num_rows*num_vectors; i++)

[...]

243: #pragma omp parallel private(i,jj,tempx)

[...]

411:    if (x == y) hypre_SeqVectorDestroy(x_tmp);

[...]

417: }

0x50f8c0 PUSH	%RBP

0x50f8c1 MOV	%RSP,%RBP

0x50f8c4 PUSH	%R15

0x50f8c6 PUSH	%R14

0x50f8c8 PUSH	%R13

0x50f8ca PUSH	%R12

0x50f8cc PUSH	%RBX

0x50f8cd SUB	$0xc8,%RSP

0x50f8d4 MOV	%R8,%R15

0x50f8d7 MOV	%RDX,%R13

0x50f8da VMOVSD	%XMM1,-0x38(%RBP)

0x50f8df MOV	%RSI,%R14

0x50f8e2 MOV	%RDI,%R12

0x50f8e5 VMOVAPD	%XMM0,%XMM16

0x50f8eb MOV	0x30(%RDI),%RAX

0x50f8ef MOV	%RAX,-0x68(%RBP)

0x50f8f3 LEA	(,%R8,8),%RAX

0x50f8fb ADD	(%RDI),%RAX

0x50f8fe MOV	%RAX,-0x60(%RBP)

0x50f902 MOV	0x8(%RDI),%RAX

0x50f906 MOV	%RAX,-0x58(%RBP)

0x50f90a MOV	0x10(%RDI),%RAX

0x50f90e MOV	%RAX,-0xa8(%RBP)

0x50f915 MOV	0x18(%RDI),%RAX

0x50f919 MOV	%RAX,-0xe8(%RBP)

0x50f920 MOV	0x38(%RDI),%RAX

0x50f924 MOV	%RAX,-0xc8(%RBP)

0x50f92b MOV	0x40(%RDI),%RAX

0x50f92f MOV	%RAX,-0x98(%RBP)

0x50f936 MOV	(%RSI),%RAX

0x50f939 MOV	%RAX,-0x48(%RBP)

0x50f93d MOV	0x8(%RSI),%RAX

0x50f941 MOV	%RAX,-0xe0(%RBP)

0x50f948 MOV	(%RDX),%RSI

0x50f94b MOV	0x8(%RDX),%RAX

0x50f94f MOV	%RAX,-0xd8(%RBP)

0x50f956 MOV	(%RCX),%RDX

0x50f959 MOV	0x8(%RCX),%RAX

0x50f95d MOV	%RAX,-0xd0(%RBP)

0x50f964 MOV	0x18(%R14),%RBX

0x50f968 MOV	0x30(%RCX),%RAX

0x50f96c MOV	%RAX,-0x90(%RBP)

0x50f973 MOV	0x28(%RCX),%RAX

0x50f977 MOV	%RAX,-0x88(%RBP)

0x50f97e MOV	0x30(%R14),%RAX

0x50f982 MOV	%RAX,-0x80(%RBP)

0x50f986 MOV	0x28(%R14),%RAX

0x50f98a MOV	%RAX,-0x78(%RBP)

0x50f98e MOV	%RCX,-0xa0(%RBP)

0x50f995 CMP	0x18(%RCX),%RBX

0x50f999 VMOVSD	%XMM0,-0x30(%RBP)

0x50f99e MOV	%RSI,-0x40(%RBP)

0x50f9a2 JE	50f9f1

0x50f9a4 MOV	0x52255(%RIP),%RDI

0x50f9ab MOV	$0x53b763,%ESI

0x50f9b0 MOV	%RBX,-0x50(%RBP)

0x50f9b4 MOV	%R14,%RBX

0x50f9b7 MOV	%RDX,%R14

0x50f9ba MOV	$0x53def8,%EDX

0x50f9bf XOR	%EAX,%EAX

0x50f9c1 CALL	51bbf0 <hypre_fprintf>

0x50f9c6 MOV	$0x53df21,%EDI

0x50f9cb MOV	$0x5e,%ESI

0x50f9d0 MOV	$0x1,%EDX

0x50f9d5 XOR	%ECX,%ECX

0x50f9d7 CALL	51ec00 <hypre_error_handler>

0x50f9dc MOV	-0x40(%RBP),%RSI

0x50f9e0 MOV	%R14,%RDX

0x50f9e3 MOV	%RBX,%R14

0x50f9e6 MOV	-0x50(%RBP),%RBX

0x50f9ea VMOVSD	-0x30(%RBP),%XMM16

0x50f9f1 CMP	0x18(%R13),%RBX

0x50f9f5 JE	50fa42

0x50f9f7 MOV	0x52202(%RIP),%RDI

0x50f9fe MOV	$0x53b763,%ESI

0x50fa03 MOV	%RBX,%R13

0x50fa06 MOV	%R14,%RBX

0x50fa09 MOV	%RDX,%R14

0x50fa0c MOV	$0x53df76,%EDX

0x50fa11 XOR	%EAX,%EAX

0x50fa13 CALL	51bbf0 <hypre_fprintf>

0x50fa18 MOV	$0x53df21,%EDI

0x50fa1d MOV	$0x5f,%ESI

0x50fa22 MOV	$0x1,%EDX

0x50fa27 XOR	%ECX,%ECX

0x50fa29 CALL	51ec00 <hypre_error_handler>

0x50fa2e MOV	-0x40(%RBP),%RSI

0x50fa32 MOV	%R14,%RDX

0x50fa35 MOV	%RBX,%R14

0x50fa38 MOV	%R13,%RBX

0x50fa3b VMOVSD	-0x30(%RBP),%XMM16

0x50fa42 MOV	-0xa8(%RBP),%R13

0x50fa49 SUB	%R15,%R13

0x50fa4c LEA	(%RSI,%R15,8),%R8

0x50fa50 LEA	(%RDX,%R15,8),%R11

0x50fa54 VXORPD	%XMM0,%XMM0,%XMM0

0x50fa58 VUCOMISD	%XMM0,%XMM16

0x50fa5e JNE	50fac0

0x50fa60 IMUL	%R13,%RBX

0x50fa64 TEST	%RBX,%RBX

0x50fa67 JLE	50ff76

0x50fa6d DEC	%RBX

0x50fa70 VMOVQ	-0x38(%RBP),%XMM0

0x50fa75 VMOVQ	%XMM0,%RCX

0x50fa7a MOV	$0x560f10,%EDI

0x50fa7f MOV	$0x5126d0,%EDX

0x50fa84 MOV	$0x5,%ESI

0x50fa89 MOV	%R11,%R9

0x50fa8c XOR	%EAX,%EAX

0x50fa8e PUSH	%RBX

0x50fa8f PUSH	$0

0x50fa91 CALL	4103a0 <__kmpc_fork_call@plt>

0x50fa96 ADD	$0x10,%RSP

0x50fa9a JMP	50ff76

0x50fa9f NOPW	%CS:(%RAX,%RAX,1)

0x50faae NOPW	%CS:(%RAX,%RAX,1)

0x50fabd NOPL	(%RAX)

0x50fac0 CMP	-0xa0(%RBP),%R14

0x50fac7 JE	50fb00

0x50fac9 MOVQ	$0,-0x70(%RBP)

0x50fad1 JMP	50fb5b

0x50fad6 NOPW	%CS:(%RAX,%RAX,1)

0x50fae5 NOPW	%CS:(%RAX,%RAX,1)

0x50faf4 NOPW	%CS:(%RAX,%RAX,1)

0x50fb00 MOV	%R14,%RDI

0x50fb03 MOV	%R11,-0xc0(%RBP)

0x50fb0a MOV	%R8,-0xb8(%RBP)

0x50fb11 MOV	%RBX,-0x50(%RBP)

0x50fb15 MOV	%R14,-0xb0(%RBP)

0x50fb1c MOV	%RDX,%R14

0x50fb1f MOV	%RSI,%RBX

0x50fb22 CALL	514720 <hypre_SeqVectorCloneDeep>

0x50fb27 MOV	%RBX,%RSI

0x50fb2a MOV	%R14,%RDX

0x50fb2d MOV	-0xb0(%RBP),%R14

0x50fb34 MOV	-0x50(%RBP),%RBX

0x50fb38 MOV	-0xb8(%RBP),%R8

0x50fb3f MOV	-0xc0(%RBP),%R11

0x50fb46 VMOVSD	-0x30(%RBP),%XMM16

0x50fb4d MOV	%RAX,%RCX

0x50fb50 MOV	%RAX,-0x70(%RBP)

0x50fb54 MOV	(%RAX),%RAX

0x50fb57 MOV	%RAX,-0x48(%RBP)

0x50fb5b VCVTSI2SDQ	-0x98(%RBP),%XMM2,%XMM17

0x50fb62 VMOVSD	-0x38(%RBP),%XMM0

0x50fb67 VDIVSD	%XMM16,%XMM0,%XMM0

0x50fb6d VCVTSI2SD	%R13,%XMM2,%XMM1

0x50fb72 VMULSD	0x2e374(%RIP),%XMM1,%XMM18

0x50fb7c VUCOMISD	%XMM17,%XMM18

0x50fb82 JA	50fc00

0x50fb84 CMP	$0x2,%RBX

0x50fb88 JGE	50fc00

0x50fb8a VMOVQ	%XMM16,%RCX

0x50fb90 SUB	$0x40,%RSP

0x50fb94 VMOVSD	%XMM0,0x30(%RSP)

0x50fb9a MOV	%R11,0x28(%RSP)

0x50fb9f MOV	%R8,0x20(%RSP)

0x50fba4 MOV	-0x48(%RBP),%RAX

0x50fba8 MOV	%RAX,0x18(%RSP)

0x50fbad MOV	%R13,0x10(%RSP)

0x50fbb2 MOV	-0x58(%RBP),%RAX

0x50fbb6 MOV	%RAX,0x8(%RSP)

0x50fbbb MOV	-0x60(%RBP),%RAX

0x50fbbf MOV	%RAX,(%RSP)

0x50fbc3 MOV	$0x560cd0,%EDI

0x50fbc8 MOV	$0x510cf0,%EDX

0x50fbcd MOV	$0xa,%ESI

0x50fbd2 MOV	%R12,%R8

0x50fbd5 MOV	-0x68(%RBP),%R9

0x50fbd9 XOR	%EAX,%EAX

0x50fbdb CALL	4103a0 <__kmpc_fork_call@plt>

0x50fbe0 ADD	$0x40,%RSP

0x50fbe4 JMP	50ff61

0x50fbe9 NOPW	%CS:(%RAX,%RAX,1)

0x50fbf8 NOPL	(%RAX,%RAX,1)

0x50fc00 MOV	%RBX,%R12

0x50fc03 IMUL	%R13,%R12

0x50fc07 VUCOMISD	0x1a401(%RIP),%XMM0

0x50fc0f JE	50fc80

0x50fc11 VXORPD	%XMM1,%XMM1,%XMM1

0x50fc15 VUCOMISD	%XMM1,%XMM0

0x50fc19 JNE	50fd00

0x50fc1f TEST	%R12,%R12

0x50fc22 JLE	50fe40

0x50fc28 LEA	-0x1(%R12),%R9

0x50fc2d MOV	$0x560eb0,%EDI

0x50fc32 MOV	$0x512640,%EDX

0x50fc37 MOV	$0x3,%ESI

0x50fc3c MOV	%R11,%RCX

0x50fc3f XOR	%R8D,%R8D

0x50fc42 XOR	%EAX,%EAX

0x50fc44 MOV	%R11,%R15

0x50fc47 VMOVSD	%XMM17,-0x40(%RBP)

0x50fc4e VMOVSD	%XMM18,-0x38(%RBP)

0x50fc55 CALL	4103a0 <__kmpc_fork_call@plt>

0x50fc5a VMOVSD	-0x38(%RBP),%XMM18

0x50fc61 VMOVSD	-0x40(%RBP),%XMM17

0x50fc68 MOV	%R15,%R11

0x50fc6b VMOVSD	-0x30(%RBP),%XMM16

0x50fc72 JMP	50fe40

0x50fc77 NOPW	(%RAX,%RAX,1)

0x50fc80 TEST	%R12,%R12

0x50fc83 JLE	50fe40

0x50fc89 ADD	%R12,%R15

0x50fc8c LEA	-0x8(%RSI,%R15,8),%RAX

0x50fc91 CMP	%R11,%RAX

0x50fc94 JB	50fd80

0x50fc9a LEA	-0x8(%RDX,%R15,8),%RAX

0x50fc9f CMP	%R8,%RAX

0x50fca2 JB	50fd80

0x50fca8 XOR	%EAX,%EAX

0x50fcaa NOPW	(%RAX,%RAX,1)

(4282) 0x50fcb0 VMOVSD	(%R8,%RAX,8),%XMM0

(4282) 0x50fcb6 VMOVSD	%XMM0,(%R11,%RAX,8)

(4282) 0x50fcbc INC	%RAX

(4282) 0x50fcbf CMP	%RAX,%R12

(4282) 0x50fcc2 JNE	50fcb0

0x50fcc4 JMP	50fe40

0x50fcc9 NOPW	%CS:(%RAX,%RAX,1)

0x50fcd8 NOPW	%CS:(%RAX,%RAX,1)

0x50fce7 NOPW	%CS:(%RAX,%RAX,1)

0x50fcf6 NOPW	%CS:(%RAX,%RAX,1)

0x50fd00 TEST	%R12,%R12

0x50fd03 JLE	50fe40

0x50fd09 LEA	-0x1(%R12),%R10

0x50fd0e VMOVQ	%XMM0,%R9

0x50fd13 MOV	$0x560e50,%EDI

0x50fd18 MOV	$0x5124d0,%EDX

0x50fd1d MOV	$0x5,%ESI

0x50fd22 MOV	%R8,%RCX

0x50fd25 MOV	%R11,%R8

0x50fd28 XOR	%EAX,%EAX

0x50fd2a PUSH	%R10

0x50fd2c PUSH	$0

0x50fd2e MOV	%R11,%R15

0x50fd31 VMOVSD	%XMM17,-0x40(%RBP)

0x50fd38 VMOVSD	%XMM18,-0x38(%RBP)

0x50fd3f CALL	4103a0 <__kmpc_fork_call@plt>

0x50fd44 VMOVSD	-0x38(%RBP),%XMM18

0x50fd4b VMOVSD	-0x40(%RBP),%XMM17

0x50fd52 MOV	%R15,%R11

0x50fd55 VMOVSD	-0x30(%RBP),%XMM16

0x50fd5c ADD	$0x10,%RSP

0x50fd60 JMP	50fe40

0x50fd65 NOPW	%CS:(%RAX,%RAX,1)

0x50fd74 NOPW	%CS:(%RAX,%RAX,1)

0x50fd80 CMP	$0xd,%R12

0x50fd84 JB	50fdc0

0x50fd86 LEA	(,%R12,8),%RDX

0x50fd8e MOV	%R11,%RDI

0x50fd91 MOV	%R8,%RSI

0x50fd94 MOV	%R11,%R15

0x50fd97 CALL	526020 <__intel_avx_rep_memcpy>

0x50fd9c MOV	%R15,%R11

0x50fd9f JMP	50fe40

0x50fda4 NOPW	%CS:(%RAX,%RAX,1)

0x50fdb3 NOPW	%CS:(%RAX,%RAX,1)

0x50fdc0 MOV	%R12,%RAX

0x50fdc3 AND	$-0x4,%RAX

0x50fdc7 JE	50fe00

0x50fdc9 LEA	-0x1(%RAX),%RCX

0x50fdcd XOR	%EDX,%EDX

0x50fdcf NOP

(4281) 0x50fdd0 VMOVUPD	(%R8,%RDX,8),%YMM0

(4281) 0x50fdd6 VMOVUPD	%YMM0,(%R11,%RDX,8)

(4281) 0x50fddc ADD	$0x4,%RDX

(4281) 0x50fde0 CMP	%RCX,%RDX

(4281) 0x50fde3 JLE	50fdd0

0x50fde5 JMP	510000

0x50fdea NOPW	%CS:(%RAX,%RAX,1)

0x50fdf9 NOPL	(%RAX)

0x50fe00 XOR	%EAX,%EAX

0x50fe02 JMP	510009

0x50fe07 NOPW	%CS:(%RAX,%RAX,1)

0x50fe16 NOPW	%CS:(%RAX,%RAX,1)

0x50fe25 NOPW	%CS:(%RAX,%RAX,1)

0x50fe34 NOPW	%CS:(%RAX,%RAX,1)

0x50fe40 VUCOMISD	%XMM17,%XMM18

0x50fe46 JBE	50fec0

0x50fe48 MOV	-0x98(%RBP),%R10

0x50fe4f TEST	%R10,%R10

0x50fe52 JLE	50ff1e

0x50fe58 DEC	%R10

0x50fe5b MOV	$0x560df0,%EDI

0x50fe60 MOV	$0x5120e0,%EDX

0x50fe65 MOV	$0xd,%ESI

0x50fe6a MOV	-0x68(%RBP),%RCX

0x50fe6e MOV	-0x60(%RBP),%R8

0x50fe72 MOV	-0x58(%RBP),%R9

0x50fe76 XOR	%EAX,%EAX

0x50fe78 PUSH	%R10

0x50fe7a PUSH	$0

0x50fe7c PUSHQ	-0x78(%RBP)

0x50fe7f PUSHQ	-0x80(%RBP)

0x50fe82 PUSHQ	-0x88(%RBP)

0x50fe88 PUSHQ	-0x90(%RBP)

0x50fe8e PUSH	%RBX

0x50fe8f PUSH	%R11

0x50fe91 PUSHQ	-0x48(%RBP)

0x50fe94 PUSHQ	-0xc8(%RBP)

0x50fe9a JMP	50ff05

0x50fe9c NOPW	%CS:(%RAX,%RAX,1)

0x50feab NOPW	%CS:(%RAX,%RAX,1)

0x50feba NOPW	(%RAX,%RAX,1)

0x50fec0 TEST	%R13,%R13

0x50fec3 JLE	50ff1e

0x50fec5 DEC	%R13

0x50fec8 SUB	$0x8,%RSP

0x50fecc MOV	$0x560d90,%EDI

0x50fed1 MOV	$0x511e40,%EDX

0x50fed6 MOV	$0xc,%ESI

0x50fedb MOV	-0x68(%RBP),%RCX

0x50fedf MOV	-0x60(%RBP),%R8

0x50fee3 MOV	-0x58(%RBP),%R9

0x50fee7 XOR	%EAX,%EAX

0x50fee9 PUSH	%R13

0x50feeb PUSH	$0

0x50feed PUSHQ	-0x78(%RBP)

0x50fef0 PUSHQ	-0x80(%RBP)

0x50fef3 PUSHQ	-0x88(%RBP)

0x50fef9 PUSHQ	-0x90(%RBP)

0x50feff PUSH	%RBX

0x50ff00 PUSH	%R11

0x50ff02 PUSHQ	-0x48(%RBP)

0x50ff05 MOV	%R11,%RBX

0x50ff08 VZEROUPPER

0x50ff0b CALL	4103a0 <__kmpc_fork_call@plt>

0x50ff10 MOV	%RBX,%R11

0x50ff13 VMOVSD	-0x30(%RBP),%XMM16

0x50ff1a ADD	$0x50,%RSP

0x50ff1e VUCOMISD	0x1a0e8(%RIP),%XMM16

0x50ff28 JE	50ff61

0x50ff2a TEST	%R12,%R12

0x50ff2d JLE	50ff61

0x50ff2f DEC	%R12

0x50ff32 VMOVQ	%XMM16,%RCX

0x50ff38 SUB	$0x8,%RSP

0x50ff3c MOV	$0x560d30,%EDI

0x50ff41 MOV	$0x511d20,%EDX

0x50ff46 MOV	$0x4,%ESI

0x50ff4b MOV	%R11,%R8

0x50ff4e XOR	%R9D,%R9D

0x50ff51 XOR	%EAX,%EAX

0x50ff53 PUSH	%R12

0x50ff55 VZEROUPPER

0x50ff58 CALL	4103a0 <__kmpc_fork_call@plt>

0x50ff5d ADD	$0x10,%RSP

0x50ff61 CMP	-0xa0(%RBP),%R14

0x50ff68 JNE	50ff76

0x50ff6a MOV	-0x70(%RBP),%RDI

0x50ff6e VZEROUPPER

0x50ff71 CALL	513d90 <hypre_SeqVectorDestroy>

0x50ff76 XOR	%ECX,%ECX

0x50ff78 MOV	-0xe8(%RBP),%RSI

0x50ff7f MOV	-0xe0(%RBP),%RDI

0x50ff86 CMP	%RDI,%RSI

0x50ff89 SETNE	%CL

0x50ff8c MOV	-0xa8(%RBP),%RAX

0x50ff93 MOV	-0xd0(%RBP),%R8

0x50ff9a XOR	%RAX,%R8

0x50ff9d MOV	-0xd8(%RBP),%RDX

0x50ffa4 XOR	%RAX,%RDX

0x50ffa7 OR	%R8,%RDX

0x50ffaa MOV	$0x3,%EDX

0x50ffaf CMOVE	%RCX,%RDX

0x50ffb3 MOV	$0x2,%EAX

0x50ffb8 CMOVE	%RCX,%RAX

0x50ffbc CMP	%RDI,%RSI

0x50ffbf CMOVNE	%RDX,%RAX

0x50ffc3 ADD	$0xc8,%RSP

0x50ffca POP	%RBX

0x50ffcb POP	%R12

0x50ffcd POP	%R13

0x50ffcf POP	%R14

0x50ffd1 POP	%R15

0x50ffd3 POP	%RBP

0x50ffd4 VZEROUPPER

0x50ffd7 RET

0x50ffd8 NOPW	%CS:(%RAX,%RAX,1)

0x50ffe7 NOPW	%CS:(%RAX,%RAX,1)

0x50fff6 NOPW	%CS:(%RAX,%RAX,1)

(4280) 0x510000 CMP	%RAX,%R12

(4280) 0x510003 JE	50fe40

(4280) 0x510009 VMOVSD	(%R8,%RAX,8),%XMM0

(4280) 0x51000f VMOVSD	%XMM0,(%R11,%RAX,8)

(4280) 0x510015 INC	%RAX

(4280) 0x510018 JMP	510000

0x51001a NOPW	(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►84.81+	hypre_ParCSRMatrixMatvecOutOfP[...]	par_csr_matvec.c:237	exec
○	hypre_PCGSolve	pcg.c:496	exec
○	main	amg.c:419	exec
○	__libc_start_call_main		libc.so.6
►14.99+	hypre_ParCSRMatrixMatvecOutOfP[...]	par_csr_matvec.c:237	exec
○	hypre_PCGSolve	pcg.c:496	exec
○	main	amg.c:419	exec

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_4

Source file and lines	csr_matvec.c:41-417
Module	exec

The function is defined in /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:41,48-70,94-103,110-115,125-128,135-139,145-152,158-160,166-167,175-181,211-213,231-236,243,411,417.

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 67.17 to 16.50 cycles (4.07x 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 13% 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 67.17 to 5.32 cycles (12.64x 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

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.

__intel_avx_rep_memcpy: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:167
__kmpc_fork_call@plt: 6 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:113
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:243
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:150
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:158
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:234
hypre_SeqVectorCloneDeep: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:127
hypre_SeqVectorDestroy: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:411
hypre_error_handler: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:94
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:95
hypre_fprintf: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:94
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:95

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.

PUSH: 11 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
VCVTSI2SD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:139
VUCOMISD: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:145
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:231
VZEROUPPER: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:234
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:411
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:417

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTSI2SD (INT32/64 to FP64, scalar): 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:139
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:139

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

The binary function is composed of 2 FP arithmetical operations:

1: multiply
1: divide

The binary function is loading 616 bytes (77 double precision FP elements). The binary function is storing 304 bytes (38 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	372
nb uops	403
loop length	1821
used x86 registers	16
used mmx registers	0
used xmm registers	6
used ymm registers	0
used zmm registers	0
nb stack references	31

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	67.17 cycles
front end	67.17 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	21.00	21.00	28.00	28.00	40.50	21.00	21.00	40.50	40.50	40.50	21.00	28.00
cycles	21.00	21.00	28.00	28.00	40.50	21.00	21.00	40.50	40.50	40.50	21.00	28.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

4.00

Cycles summary

Front-end	67.17
Dispatch	40.50
DIV/SQRT	4.00
Overall L1	67.17

Vectorization ratios

INT

all	4%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	10%
load	0%
store	0%
mul	0%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	33%

INT+FP

all	6%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	14%

Vector efficiency ratios

INT

all	12%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	13%
load	12%
store	12%
mul	12%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	16%

INT+FP

all	13%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 67.17 cycles. At this rate:

4% of peak load performance is reached (9.17 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.53 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 67.17 to 40.50 cycles (1.66x speedup).

ASM code

In the binary file, the address of the function is: 50f8c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0xc8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R8,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM1,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVAPD %XMM0,%XMM16	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOV 0x30(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%R8,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD (%RDI),%RAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x10(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x18(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x38(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xc8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x40(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RSI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x8(%RSI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xe0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RDX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RDX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xd8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RCX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RCX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xd0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x18(%R14),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x30(%RCX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x28(%RCX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x30(%R14),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x28(%R14),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RCX,-0xa0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP 0x18(%RCX),%RBX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM0,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JE 50f9f1 <hypre_CSRMatrixMatvecOutOfPlace+0x131>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x52255(%RIP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x53b763,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RBX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R14,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x53def8,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 51bbf0 <hypre_fprintf>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x53df21,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5e,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x1,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 51ec00 <hypre_error_handler>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x40(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x50(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CMP 0x18(%R13),%RBX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 50fa42 <hypre_CSRMatrixMatvecOutOfPlace+0x182>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x52202(%RIP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x53b763,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RBX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x53df76,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 51bbf0 <hypre_fprintf>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x53df21,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5f,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x1,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 51ec00 <hypre_error_handler>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x40(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0xa8(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %R15,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%RSI,%R15,8),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RDX,%R15,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM0,%XMM16	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JNE 50fac0 <hypre_CSRMatrixMatvecOutOfPlace+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %R13,%RBX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
TEST %RBX,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50ff76 <hypre_CSRMatrixMatvecOutOfPlace+0x6b6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVQ -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVQ %XMM0,%RCX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOV $0x560f10,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5126d0,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x10,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 50ff76 <hypre_CSRMatrixMatvecOutOfPlace+0x6b6>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP -0xa0(%RBP),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 50fb00 <hypre_CSRMatrixMatvecOutOfPlace+0x240>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVQ $0,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JMP 50fb5b <hypre_CSRMatrixMatvecOutOfPlace+0x29b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,-0xc0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,-0xb8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RBX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R14,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CALL 514720 <hypre_SeqVectorCloneDeep>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0xb0(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x50(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0xb8(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xc0(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VCVTSI2SDQ -0x98(%RBP),%XMM2,%XMM17	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	7	0.50	scal (12.5%)
VMOVSD -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VDIVSD %XMM16,%XMM0,%XMM0	1	1	0	0	0	0	0	0	0	0	0	0	0	13-15	4	scal (12.5%)
VCVTSI2SD %R13,%XMM2,%XMM1	2	0.50	0.50	0	0	0	1	0	0	0	0	0	0	7	1	scal (12.5%)
VMULSD 0x2e374(%RIP),%XMM1,%XMM18	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VUCOMISD %XMM17,%XMM18	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JA 50fc00 <hypre_CSRMatrixMatvecOutOfPlace+0x340>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 50fc00 <hypre_CSRMatrixMatvecOutOfPlace+0x340>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVQ %XMM16,%RCX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
SUB $0x40,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM0,0x30(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R11,0x28(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,0x20(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,0x18(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R13,0x10(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x58(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,0x8(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x560cd0,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x510cf0,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xa,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R12,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x68(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x40,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 50ff61 <hypre_CSRMatrixMatvecOutOfPlace+0x6a1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RBX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %R13,%R12	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VUCOMISD 0x1a401(%RIP),%XMM0	2	1	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	scal (12.5%)
JE 50fc80 <hypre_CSRMatrixMatvecOutOfPlace+0x3c0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM1,%XMM0	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JNE 50fd00 <hypre_CSRMatrixMatvecOutOfPlace+0x440>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
TEST %R12,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%R12),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x560eb0,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x512640,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x3,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R11,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM17,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM18,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD -0x38(%RBP),%XMM18	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x40(%RBP),%XMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R15,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
JMP 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R12,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD %R12,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x8(%RSI,%R15,8),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %R11,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 50fd80 <hypre_CSRMatrixMatvecOutOfPlace+0x4c0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x8(%RDX,%R15,8),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %R8,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 50fd80 <hypre_CSRMatrixMatvecOutOfPlace+0x4c0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R12,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%R12),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVQ %XMM0,%R9	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOV $0x560e50,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5124d0,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R8,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R10	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %R11,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM17,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM18,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD -0x38(%RBP),%XMM18	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x40(%RBP),%XMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R15,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
ADD $0x10,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0xd,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 50fdc0 <hypre_CSRMatrixMatvecOutOfPlace+0x500>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R12,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R11,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R8,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 526020 <__intel_avx_rep_memcpy>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %R15,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JMP 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 50fe00 <hypre_CSRMatrixMatvecOutOfPlace+0x540>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%RAX),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 510000 <hypre_CSRMatrixMatvecOutOfPlace+0x740>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 510009 <hypre_CSRMatrixMatvecOutOfPlace+0x749>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VUCOMISD %XMM17,%XMM18	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 50fec0 <hypre_CSRMatrixMatvecOutOfPlace+0x600>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x98(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
TEST %R10,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50ff1e <hypre_CSRMatrixMatvecOutOfPlace+0x65e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x560df0,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5120e0,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xd,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x68(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R10	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSHQ -0x78(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x80(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x88(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x90(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R11	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSHQ -0x48(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0xc8(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
JMP 50ff05 <hypre_CSRMatrixMatvecOutOfPlace+0x645>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R13,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50ff1e <hypre_CSRMatrixMatvecOutOfPlace+0x65e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x560d90,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x511e40,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xc,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x68(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSHQ -0x78(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x80(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x88(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x90(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R11	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSHQ -0x48(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
MOV %R11,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RBX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
ADD $0x50,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VUCOMISD 0x1a0e8(%RIP),%XMM16	2	1	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	scal (12.5%)
JE 50ff61 <hypre_CSRMatrixMatvecOutOfPlace+0x6a1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
TEST %R12,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50ff61 <hypre_CSRMatrixMatvecOutOfPlace+0x6a1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVQ %XMM16,%RCX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x560d30,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x511d20,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x4,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x10,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP -0xa0(%RBP),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JNE 50ff76 <hypre_CSRMatrixMatvecOutOfPlace+0x6b6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 513d90 <hypre_SeqVectorDestroy>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0xe8(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xe0(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RDI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
SETNE %CL	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xd0(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
XOR %RAX,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV -0xd8(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
XOR %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
OR %R8,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV $0x3,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMOVE %RCX,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMOVE %RCX,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
CMP %RDI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
CMOVNE %RDX,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
ADD $0xc8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run icx_4

Source file and lines	csr_matvec.c:41-417
Module	exec

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

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

No data for this section

CALL instructions

Detected function call instructions.

Details

__intel_avx_rep_memcpy: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:167
__kmpc_fork_call@plt: 6 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:113
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:243
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:150
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:158
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:234
hypre_SeqVectorCloneDeep: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:127
hypre_SeqVectorDestroy: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:411
hypre_error_handler: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:94
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:95
hypre_fprintf: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:94
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:95

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.

PUSH: 11 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:178
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
VCVTSI2SD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:139
VUCOMISD: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:145
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:231
VZEROUPPER: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:211
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:234
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:411
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:417

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTSI2SD (INT32/64 to FP64, scalar): 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:139
- /home/eoseret/qaas_runs_GNR/173-927-0874/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:139

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

The binary function is composed of 2 FP arithmetical operations:

1: multiply
1: divide

The binary function is loading 616 bytes (77 double precision FP elements). The binary function is storing 304 bytes (38 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	372
nb uops	403
loop length	1821
used x86 registers	16
used mmx registers	0
used xmm registers	6
used ymm registers	0
used zmm registers	0
nb stack references	31

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	67.17 cycles
front end	67.17 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	21.00	21.00	28.00	28.00	40.50	21.00	21.00	40.50	40.50	40.50	21.00	28.00
cycles	21.00	21.00	28.00	28.00	40.50	21.00	21.00	40.50	40.50	40.50	21.00	28.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

4.00

Cycles summary

Front-end	67.17
Dispatch	40.50
DIV/SQRT	4.00
Overall L1	67.17

Vectorization ratios

INT

all	4%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	10%
load	0%
store	0%
mul	0%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	33%

INT+FP

all	6%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	14%

Vector efficiency ratios

INT

all	12%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	13%
load	12%
store	12%
mul	12%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	16%

INT+FP

all	13%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 67.17 cycles. At this rate:

4% of peak load performance is reached (9.17 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.53 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: 50f8c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0xc8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R8,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM1,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVAPD %XMM0,%XMM16	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOV 0x30(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%R8,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD (%RDI),%RAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x10(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x18(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x38(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xc8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x40(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RSI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x8(%RSI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xe0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RDX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RDX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xd8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RCX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RCX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xd0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x18(%R14),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x30(%RCX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x28(%RCX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x30(%R14),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x28(%R14),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RCX,-0xa0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP 0x18(%RCX),%RBX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM0,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JE 50f9f1 <hypre_CSRMatrixMatvecOutOfPlace+0x131>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x52255(%RIP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x53b763,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RBX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R14,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x53def8,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 51bbf0 <hypre_fprintf>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x53df21,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5e,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x1,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 51ec00 <hypre_error_handler>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x40(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x50(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CMP 0x18(%R13),%RBX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 50fa42 <hypre_CSRMatrixMatvecOutOfPlace+0x182>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x52202(%RIP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x53b763,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RBX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x53df76,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 51bbf0 <hypre_fprintf>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x53df21,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5f,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x1,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 51ec00 <hypre_error_handler>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0x40(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0xa8(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %R15,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%RSI,%R15,8),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RDX,%R15,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM0,%XMM16	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JNE 50fac0 <hypre_CSRMatrixMatvecOutOfPlace+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %R13,%RBX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
TEST %RBX,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50ff76 <hypre_CSRMatrixMatvecOutOfPlace+0x6b6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVQ -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVQ %XMM0,%RCX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOV $0x560f10,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5126d0,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x10,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 50ff76 <hypre_CSRMatrixMatvecOutOfPlace+0x6b6>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP -0xa0(%RBP),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 50fb00 <hypre_CSRMatrixMatvecOutOfPlace+0x240>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVQ $0,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JMP 50fb5b <hypre_CSRMatrixMatvecOutOfPlace+0x29b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,-0xc0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,-0xb8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RBX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R14,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CALL 514720 <hypre_SeqVectorCloneDeep>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0xb0(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x50(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0xb8(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xc0(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV (%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VCVTSI2SDQ -0x98(%RBP),%XMM2,%XMM17	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	7	0.50	scal (12.5%)
VMOVSD -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VDIVSD %XMM16,%XMM0,%XMM0	1	1	0	0	0	0	0	0	0	0	0	0	0	13-15	4	scal (12.5%)
VCVTSI2SD %R13,%XMM2,%XMM1	2	0.50	0.50	0	0	0	1	0	0	0	0	0	0	7	1	scal (12.5%)
VMULSD 0x2e374(%RIP),%XMM1,%XMM18	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VUCOMISD %XMM17,%XMM18	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JA 50fc00 <hypre_CSRMatrixMatvecOutOfPlace+0x340>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 50fc00 <hypre_CSRMatrixMatvecOutOfPlace+0x340>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVQ %XMM16,%RCX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
SUB $0x40,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM0,0x30(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R11,0x28(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R8,0x20(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,0x18(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R13,0x10(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x58(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,0x8(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x560cd0,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x510cf0,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xa,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R12,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x68(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x40,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 50ff61 <hypre_CSRMatrixMatvecOutOfPlace+0x6a1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RBX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %R13,%R12	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VUCOMISD 0x1a401(%RIP),%XMM0	2	1	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	scal (12.5%)
JE 50fc80 <hypre_CSRMatrixMatvecOutOfPlace+0x3c0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUCOMISD %XMM1,%XMM0	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JNE 50fd00 <hypre_CSRMatrixMatvecOutOfPlace+0x440>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
TEST %R12,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%R12),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x560eb0,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x512640,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x3,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R11,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM17,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM18,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD -0x38(%RBP),%XMM18	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x40(%RBP),%XMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R15,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
JMP 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R12,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD %R12,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x8(%RSI,%R15,8),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %R11,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 50fd80 <hypre_CSRMatrixMatvecOutOfPlace+0x4c0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x8(%RDX,%R15,8),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %R8,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 50fd80 <hypre_CSRMatrixMatvecOutOfPlace+0x4c0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R12,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%R12),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVQ %XMM0,%R9	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOV $0x560e50,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5124d0,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R8,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R10	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %R11,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM17,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM18,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
VMOVSD -0x38(%RBP),%XMM18	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x40(%RBP),%XMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R15,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
ADD $0x10,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0xd,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 50fdc0 <hypre_CSRMatrixMatvecOutOfPlace+0x500>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R12,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R11,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R8,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 526020 <__intel_avx_rep_memcpy>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %R15,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JMP 50fe40 <hypre_CSRMatrixMatvecOutOfPlace+0x580>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 50fe00 <hypre_CSRMatrixMatvecOutOfPlace+0x540>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%RAX),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 510000 <hypre_CSRMatrixMatvecOutOfPlace+0x740>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 510009 <hypre_CSRMatrixMatvecOutOfPlace+0x749>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VUCOMISD %XMM17,%XMM18	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JBE 50fec0 <hypre_CSRMatrixMatvecOutOfPlace+0x600>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x98(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
TEST %R10,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50ff1e <hypre_CSRMatrixMatvecOutOfPlace+0x65e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x560df0,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x5120e0,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xd,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x68(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R10	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSHQ -0x78(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x80(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x88(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x90(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R11	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSHQ -0x48(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0xc8(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
JMP 50ff05 <hypre_CSRMatrixMatvecOutOfPlace+0x645>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %R13,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50ff1e <hypre_CSRMatrixMatvecOutOfPlace+0x65e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x560d90,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x511e40,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xc,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x68(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x60(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSHQ -0x78(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x80(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x88(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSHQ -0x90(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R11	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSHQ -0x48(%RBP)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
MOV %R11,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %RBX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VMOVSD -0x30(%RBP),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
ADD $0x50,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VUCOMISD 0x1a0e8(%RIP),%XMM16	2	1	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	scal (12.5%)
JE 50ff61 <hypre_CSRMatrixMatvecOutOfPlace+0x6a1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
TEST %R12,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 50ff61 <hypre_CSRMatrixMatvecOutOfPlace+0x6a1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVQ %XMM16,%RCX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x560d30,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x511d20,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x4,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 4103a0 <__kmpc_fork_call@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x10,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP -0xa0(%RBP),%R14	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JNE 50ff76 <hypre_CSRMatrixMatvecOutOfPlace+0x6b6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 513d90 <hypre_SeqVectorDestroy>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0xe8(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xe0(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RDI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
SETNE %CL	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xd0(%RBP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
XOR %RAX,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV -0xd8(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
XOR %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
OR %R8,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV $0x3,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMOVE %RCX,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMOVE %RCX,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
CMP %RDI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
CMOVNE %RDX,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
ADD $0xc8,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼hypre_CSRMatrixMatvecOutOfPlace–	0.05	0.02
○Loop 4282 - csr_matvec.c:166-167 - exec	0.05	0.83
○Loop 4281 - csr_matvec.c:166-167 - exec	0.00	0.00
○Loop 4280 - csr_matvec.c:166-417 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

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

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code