OV - exec - Function __libm_log

	Function: __libm_log_z0	Module: exec	Source: :0-0	Coverage (incl. loops): 0.02% \| (excl. loops): 0.02%

  ***  This Panel is Intentionally Left Blank.  ***

It is due to a lack of debug symbols in the given object
(loop or function).

0x411d10 ENDBR64

0x411d14 SUB	$0x18,%RSP

0x411d18 VMOVQ	%XMM0,%RAX

0x411d1d SHR	$0x20,%RAX

0x411d21 LEA	-0x7ff00000(%RAX),%ECX

0x411d27 CMP	$-0x7fe00000,%ECX

0x411d2d JB	411e1f

0x411d33 VPBROADCASTQ	0x16b64(%RIP),%XMM1

0x411d3c VPTERNLOGQ	$-0x8,0x16b61(%RIP){1to2},%XMM0,%XMM1

0x411d47 VPSRLQ	$0x34,%XMM0,%XMM0

0x411d4c VMOVD	%XMM0,%EAX

0x411d50 ADD	$-0x3ff,%EAX

0x411d55 VCVTSI2SD	%EAX,%XMM2,%XMM0

0x411d59 VMOVQ	%XMM1,%XMM2

0x411d5d VPSRLQ	$0x1d,%XMM2,%XMM2

0x411d62 VRCPSS	%XMM2,%XMM2,%XMM2

0x411d66 VPADDD	0x162c4(%RIP){1to4},%XMM2,%XMM2

0x411d70 VPSRLD	$0x10,%XMM2,%XMM2

0x411d75 VPSLLQ	$0x2d,%XMM2,%XMM3

0x411d7a VPORQ	0x16b2c(%RIP){1to2},%XMM1,%XMM1

0x411d84 VFMADD213SD	0x1195b(%RIP),%XMM3,%XMM1

0x411d8d VMOVSD	0x162bb(%RIP),%XMM3

0x411d95 VFMADD213SD	0x162ba(%RIP),%XMM1,%XMM3

0x411d9e VMOVSD	0x162ba(%RIP),%XMM4

0x411da6 VFMADD213SD	0x162b9(%RIP),%XMM1,%XMM4

0x411daf VMOVSD	0x162b9(%RIP),%XMM5

0x411db7 VFMADD213SD	0x162b8(%RIP),%XMM1,%XMM5

0x411dc0 VPADDQ	%XMM2,%XMM2,%XMM2

0x411dc4 VMOVD	%XMM2,%EAX

0x411dc8 AND	$0x1fe,%EAX

0x411dcd LEA	0x1(%RAX),%ECX

0x411dd0 LEA	0x16ae9(%RIP),%RDX

0x411dd7 VMOVSD	0x162a1(%RIP),%XMM2

0x411ddf VFMADD213SD	(%RDX,%RCX,8),%XMM0,%XMM2

0x411de5 VMOVSD	0x1629b(%RIP),%XMM6

0x411ded VFMADD213SD	(%RDX,%RAX,8),%XMM0,%XMM6

0x411df3 VADDSD	%XMM1,%XMM6,%XMM0

0x411df7 VSUBSD	%XMM6,%XMM0,%XMM6

0x411dfb VSUBSD	%XMM6,%XMM1,%XMM6

0x411dff VADDSD	%XMM6,%XMM2,%XMM2

0x411e03 VMULSD	%XMM1,%XMM1,%XMM1

0x411e07 VFMADD231SD	%XMM3,%XMM1,%XMM4

0x411e0c VFMADD213SD	%XMM5,%XMM1,%XMM4

0x411e11 VFMADD213SD	%XMM2,%XMM1,%XMM4

0x411e16 VADDSD	%XMM4,%XMM0,%XMM0

0x411e1a ADD	$0x18,%RSP

0x411e1e RET

0x411e1f VXORPD	%XMM1,%XMM1,%XMM1

0x411e23 VADDSD	%XMM1,%XMM0,%XMM0

0x411e27 VMOVSD	%XMM0,0x10(%RSP)

0x411e2d VMOVQ	%XMM0,%RCX

0x411e32 TEST	%RCX,%RCX

0x411e35 JE	411e79

0x411e37 CMP	$0xfffff,%EAX

0x411e3c JA	411e79

0x411e3e VMULSD	0x161fa(%RIP),%XMM0,%XMM0

0x411e46 VPBROADCASTQ	0x16a51(%RIP),%XMM1

0x411e4f VPTERNLOGQ	$-0x8,0x16a4e(%RIP){1to2},%XMM0,%XMM1

0x411e5a VPSRLQ	$0x34,%XMM0,%XMM0

0x411e5f VMOVD	%XMM0,%EAX

0x411e63 ADD	$-0x3ff,%EAX

0x411e68 VCVTSI2SD	%EAX,%XMM2,%XMM0

0x411e6c VADDSD	0x161d4(%RIP),%XMM0,%XMM0

0x411e74 JMP	411d59

0x411e79 MOV	$0x7ff0000000000000,%RDX

0x411e83 CMP	%RDX,%RCX

0x411e86 JE	411f07

0x411e88 MOV	$0x3f,%AL

0x411e8a BZHI	%RAX,%RCX,%RAX

0x411e8f CMP	%RDX,%RAX

0x411e92 JBE	411ea1

0x411e94 VADDSD	0x103a4(%RIP),%XMM0,%XMM0

0x411e9c ADD	$0x18,%RSP

0x411ea0 RET

0x411ea1 VMOVSS	0x16187(%RIP),%XMM0

0x411ea9 VRCPSS	%XMM0,%XMM0,%XMM0

0x411ead VCVTSS2SD	%XMM0,%XMM0,%XMM0

0x411eb1 TEST	%RAX,%RAX

0x411eb4 JE	411ed8

0x411eb6 VMULSD	0x1617a(%RIP),%XMM0,%XMM0

0x411ebe VMOVSD	%XMM0,0x8(%RSP)

0x411ec4 LEA	0x10(%RSP),%RDI

0x411ec9 LEA	0x8(%RSP),%RDX

0x411ece MOV	%RDI,%RSI

0x411ed1 MOV	$0x3,%ECX

0x411ed6 JMP	411efc

0x411ed8 VMOVSD	0x11808(%RIP),%XMM1

0x411ee0 VDIVSD	%XMM0,%XMM1,%XMM0

0x411ee4 VMOVSD	%XMM0,0x8(%RSP)

0x411eea LEA	0x10(%RSP),%RDI

0x411eef LEA	0x8(%RSP),%RDX

0x411ef4 MOV	%RDI,%RSI

0x411ef7 MOV	$0x2,%ECX

0x411efc CALL	4111f0 <__libm_error_support>

0x411f01 VMOVSD	0x8(%RSP),%XMM0

0x411f07 ADD	$0x18,%RSP

0x411f0b RET

0x411f0c NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►37.31+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►19.84+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►15.87+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►13.49+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
►7.14+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
►6.35+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6

Coverage (%)	Name	Source Location	Module
►39.58+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__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
►21.88+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__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
►20.83+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__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
►6.25+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►5.21+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►3.12+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
►2.08+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►1.04+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6

Coverage (%)	Name	Source Location	Module
►39.71+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__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
►25.00+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__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
►25.00+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__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
►4.41+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►2.94+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►1.47+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
►1.47+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6

Coverage (%)	Name	Source Location	Module
►40.87+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__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
►25.80+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__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
►23.66+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__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
►4.30+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
►2.15+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
►1.08+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►1.08+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►1.07+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6

Coverage (%)	Name	Source Location	Module
►43.05+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__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
►23.61+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__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
►22.23+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__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
►6.94+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►2.78+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►1.39+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6

Coverage (%)	Name	Source Location	Module
►38.16+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__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
►32.89+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__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
►26.32+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__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
►2.63+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6

Coverage (%)	Name	Source Location	Module
►37.36+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__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
►31.87+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__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
►20.88+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__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
►3.30+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
►3.30+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:160	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
►1.10+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
►1.10+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:161	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
►1.10+	gasdev	random.c:31	exec
○	setTemperature.extracted.30	initAtoms.c:162	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	setTemperature	initAtoms.c:151	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6

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 0.02% of application time for run 8x1

Source file and lines
Module	exec

Warnings:

Ignoring paths for analysis
Too many paths. Rerun with max-paths=10

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This function has 10 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside function: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the function)
turning them into conditional moves, MIN or MAX

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 12.38 to 9.75 cycles (1.27x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 13% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 12.38 to 1.44 cycles (8.61x speedup).

Details

17% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

16% of SSE/AVX loads are used in vector version.
0% of SSE/AVX stores are used in vector version.
20% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
0% of SSE/AVX fused multiply-add instructions are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
32% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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)

Execution units bottlenecks

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

FMA

Detected 9 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

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.

__libm_error_support: 1 occurrences►

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.

VCVTSI2SD: 2 occurrences►

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTSI2SD (INT32/64 to FP64, scalar): 2 occurrences►
VCVTSS2SD (FP32 to FP64, scalar): 1 occurrences►

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements. Use double instead of single precision only when/where needed by numerical stability and avoid mixing precision.

Type of elements and instruction set

2 SSE or AVX instructions are processing arithmetic or math operations on single precision FP elements in scalar mode (one at a time). 21 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 32 FP arithmetical operations:

17: addition or subtraction (9 inside FMA instructions)
12: multiply (9 inside FMA instructions)
1: divide
2: fast reciprocal

The binary function is loading 184 bytes (23 double precision FP elements). The binary function is storing 24 bytes (3 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.15 FP operations per loaded or stored byte.

General properties

nb instructions	98
nb uops	99
loop length	512
used x86 registers	6
used mmx registers	0
used xmm registers	7
used ymm registers	0
used zmm registers	0
nb stack references	2
ADD-SUB / MUL ratio	2.67

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.38 cycles
front end	12.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.33	6.33	6.33	6.33	6.33	6.33	7.25	7.25	7.25	7.25	9.75	9.75	9.75	9.75	4.00	4.00
cycles	6.33	6.33	6.33	6.33	6.33	6.33	7.25	7.25	7.25	7.25	9.75	9.75	9.75	9.75	4.00	4.00

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

4.00

Cycles summary

Front-end	12.38
Dispatch	9.75
DIV/SQRT	4.00
Overall L1	12.38

Vectorization ratios

INT

all	35%
load	66%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
other	30%

all	2%
load	0%
store	0%
mul	0%
add-sub	0%
fma	0%
div/sqrt	0%
other	50%

INT+FP

all	17%
load	16%
store	0%
mul	0%
add-sub	20%
fma	0%
div/sqrt	0%
other	32%

Vector efficiency ratios

INT

all	15%
load	20%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
other	14%

all	12%
load	12%
store	12%
mul	12%
add-sub	12%
fma	12%
div/sqrt	8%
other	15%

INT+FP

all	13%
load	14%
store	12%
mul	12%
add-sub	15%
fma	12%
div/sqrt	8%
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 12.38 cycles. At this rate:

5% of peak load performance is reached (14.87 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (1.94 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 12.38 to 9.75 cycles (1.27x speedup).

ASM code

In the binary file, the address of the function is: 411d10

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
ENDBR64																				N/A
SUB $0x18,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVQ %XMM0,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
SHR $0x20,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA -0x7ff00000(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP $-0x7fe00000,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JB 411e1f <__libm_log_z0+0x10f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VPBROADCASTQ 0x16b64(%RIP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VPTERNLOGQ $-0x8,0x16b61(%RIP){1to2},%XMM0,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	vect (25.0%)
VPSRLQ $0x34,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VMOVD %XMM0,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	5	0.50	scal (6.3%)
ADD $-0x3ff,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VCVTSI2SD %EAX,%XMM2,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1	scal (6.3%)
VMOVQ %XMM1,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VPSRLQ $0x1d,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VRCPSS %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	4	0.50	scal (6.3%)
VPADDD 0x162c4(%RIP){1to4},%XMM2,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	vect (25.0%)
VPSRLD $0x10,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VPSLLQ $0x2d,%XMM2,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VPORQ 0x16b2c(%RIP){1to2},%XMM1,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	vect (25.0%)
VFMADD213SD 0x1195b(%RIP),%XMM3,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVSD 0x162bb(%RIP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD 0x162ba(%RIP),%XMM1,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVSD 0x162ba(%RIP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD 0x162b9(%RIP),%XMM1,%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVSD 0x162b9(%RIP),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD 0x162b8(%RIP),%XMM1,%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VPADDQ %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
VMOVD %XMM2,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	5	0.50	scal (6.3%)
AND $0x1fe,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x1(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x16ae9(%RIP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD 0x162a1(%RIP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD (%RDX,%RCX,8),%XMM0,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVSD 0x1629b(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD (%RDX,%RAX,8),%XMM0,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VADDSD %XMM1,%XMM6,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VSUBSD %XMM6,%XMM0,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VSUBSD %XMM6,%XMM1,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VADDSD %XMM6,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMULSD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VFMADD231SD %XMM3,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM5,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM2,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VADDSD %XMM4,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADD $0x18,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VADDSD %XMM1,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,0x10(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVQ %XMM0,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 411e79 <__libm_log_z0+0x169>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0xfffff,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JA 411e79 <__libm_log_z0+0x169>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMULSD 0x161fa(%RIP),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VPBROADCASTQ 0x16a51(%RIP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VPTERNLOGQ $-0x8,0x16a4e(%RIP){1to2},%XMM0,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	vect (25.0%)
VPSRLQ $0x34,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VMOVD %XMM0,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	5	0.50	scal (6.3%)
ADD $-0x3ff,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VCVTSI2SD %EAX,%XMM2,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1	scal (6.3%)
VADDSD 0x161d4(%RIP),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
JMP 411d59 <__libm_log_z0+0x49>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV $0x7ff0000000000000,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 411f07 <__libm_log_z0+0x1f7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV $0x3f,%AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
BZHI %RAX,%RCX,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP %RDX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JBE 411ea1 <__libm_log_z0+0x191>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VADDSD 0x103a4(%RIP),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADD $0x18,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
VMOVSS 0x16187(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (6.3%)
VRCPSS %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	4	0.50	scal (6.3%)
VCVTSS2SD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	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	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 411ed8 <__libm_log_z0+0x1c8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMULSD 0x1617a(%RIP),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM0,0x8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
LEA 0x10(%RSP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x8(%RSP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RDI,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV $0x3,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 411efc <__libm_log_z0+0x1ec>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VMOVSD 0x11808(%RIP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VDIVSD %XMM0,%XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	13	4	scal (12.5%)
VMOVSD %XMM0,0x8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
LEA 0x10(%RSP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x8(%RSP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RDI,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV $0x2,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4111f0 <__libm_error_support>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
VMOVSD 0x8(%RSP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
ADD $0x18,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	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 0.02% of application time for run 8x1

Source file and lines
Module	exec

Warnings:

Ignoring paths for analysis
Too many paths. Rerun with max-paths=10

hoisting them (moving them outside the function)
turning them into conditional moves, MIN or MAX

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 12.38 to 9.75 cycles (1.27x speedup).

Workaround

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

Vectorization

Details

17% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

16% of SSE/AVX loads are used in vector version.
0% of SSE/AVX stores are used in vector version.
20% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
0% of SSE/AVX fused multiply-add instructions are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
32% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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)

Execution units bottlenecks

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

FMA

Detected 9 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

CALL instructions

Detected function call instructions.

Details

__libm_error_support: 1 occurrences►

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.

VCVTSI2SD: 2 occurrences►

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTSI2SD (INT32/64 to FP64, scalar): 2 occurrences►
VCVTSS2SD (FP32 to FP64, scalar): 1 occurrences►

Workaround

Type of elements and instruction set

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

The binary function is composed of 32 FP arithmetical operations:

17: addition or subtraction (9 inside FMA instructions)
12: multiply (9 inside FMA instructions)
1: divide
2: fast reciprocal

The binary function is loading 184 bytes (23 double precision FP elements). The binary function is storing 24 bytes (3 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.15 FP operations per loaded or stored byte.

General properties

nb instructions	98
nb uops	99
loop length	512
used x86 registers	6
used mmx registers	0
used xmm registers	7
used ymm registers	0
used zmm registers	0
nb stack references	2
ADD-SUB / MUL ratio	2.67

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.38 cycles
front end	12.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.33	6.33	6.33	6.33	6.33	6.33	7.25	7.25	7.25	7.25	9.75	9.75	9.75	9.75	4.00	4.00
cycles	6.33	6.33	6.33	6.33	6.33	6.33	7.25	7.25	7.25	7.25	9.75	9.75	9.75	9.75	4.00	4.00

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

4.00

Cycles summary

Front-end	12.38
Dispatch	9.75
DIV/SQRT	4.00
Overall L1	12.38

Vectorization ratios

INT

all	35%
load	66%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
other	30%

all	2%
load	0%
store	0%
mul	0%
add-sub	0%
fma	0%
div/sqrt	0%
other	50%

INT+FP

all	17%
load	16%
store	0%
mul	0%
add-sub	20%
fma	0%
div/sqrt	0%
other	32%

Vector efficiency ratios

INT

all	15%
load	20%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
other	14%

all	12%
load	12%
store	12%
mul	12%
add-sub	12%
fma	12%
div/sqrt	8%
other	15%

INT+FP

all	13%
load	14%
store	12%
mul	12%
add-sub	15%
fma	12%
div/sqrt	8%
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 12.38 cycles. At this rate:

5% of peak load performance is reached (14.87 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (1.94 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: 411d10

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
ENDBR64																				N/A
SUB $0x18,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVQ %XMM0,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
SHR $0x20,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA -0x7ff00000(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP $-0x7fe00000,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JB 411e1f <__libm_log_z0+0x10f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VPBROADCASTQ 0x16b64(%RIP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VPTERNLOGQ $-0x8,0x16b61(%RIP){1to2},%XMM0,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	vect (25.0%)
VPSRLQ $0x34,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VMOVD %XMM0,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	5	0.50	scal (6.3%)
ADD $-0x3ff,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VCVTSI2SD %EAX,%XMM2,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1	scal (6.3%)
VMOVQ %XMM1,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VPSRLQ $0x1d,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VRCPSS %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	4	0.50	scal (6.3%)
VPADDD 0x162c4(%RIP){1to4},%XMM2,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	vect (25.0%)
VPSRLD $0x10,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VPSLLQ $0x2d,%XMM2,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VPORQ 0x16b2c(%RIP){1to2},%XMM1,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	vect (25.0%)
VFMADD213SD 0x1195b(%RIP),%XMM3,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVSD 0x162bb(%RIP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD 0x162ba(%RIP),%XMM1,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVSD 0x162ba(%RIP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD 0x162b9(%RIP),%XMM1,%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVSD 0x162b9(%RIP),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD 0x162b8(%RIP),%XMM1,%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VPADDQ %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
VMOVD %XMM2,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	5	0.50	scal (6.3%)
AND $0x1fe,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x1(%RAX),%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x16ae9(%RIP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD 0x162a1(%RIP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD (%RDX,%RCX,8),%XMM0,%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVSD 0x1629b(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD213SD (%RDX,%RAX,8),%XMM0,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VADDSD %XMM1,%XMM6,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VSUBSD %XMM6,%XMM0,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VSUBSD %XMM6,%XMM1,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VADDSD %XMM6,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMULSD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VFMADD231SD %XMM3,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM5,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFMADD213SD %XMM2,%XMM1,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VADDSD %XMM4,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADD $0x18,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VADDSD %XMM1,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,0x10(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVQ %XMM0,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 411e79 <__libm_log_z0+0x169>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0xfffff,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JA 411e79 <__libm_log_z0+0x169>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMULSD 0x161fa(%RIP),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VPBROADCASTQ 0x16a51(%RIP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VPTERNLOGQ $-0x8,0x16a4e(%RIP){1to2},%XMM0,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	vect (25.0%)
VPSRLQ $0x34,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	1	0.50	vect (25.0%)
VMOVD %XMM0,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	5	0.50	scal (6.3%)
ADD $-0x3ff,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VCVTSI2SD %EAX,%XMM2,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1	scal (6.3%)
VADDSD 0x161d4(%RIP),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
JMP 411d59 <__libm_log_z0+0x49>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV $0x7ff0000000000000,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 411f07 <__libm_log_z0+0x1f7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV $0x3f,%AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
BZHI %RAX,%RCX,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP %RDX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JBE 411ea1 <__libm_log_z0+0x191>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VADDSD 0x103a4(%RIP),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ADD $0x18,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
VMOVSS 0x16187(%RIP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (6.3%)
VRCPSS %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	4	0.50	scal (6.3%)
VCVTSS2SD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	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	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 411ed8 <__libm_log_z0+0x1c8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMULSD 0x1617a(%RIP),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM0,0x8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
LEA 0x10(%RSP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x8(%RSP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RDI,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV $0x3,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 411efc <__libm_log_z0+0x1ec>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VMOVSD 0x11808(%RIP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VDIVSD %XMM0,%XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	13	4	scal (12.5%)
VMOVSD %XMM0,0x8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
LEA 0x10(%RSP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x8(%RSP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RDI,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV $0x2,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4111f0 <__libm_error_support>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
VMOVSD 0x8(%RSP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
ADD $0x18,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

▶Scalability Runs Description

Run 8x1	Number processes: 8Number nodes: 1Run Command: <executable> -x 200 -y 200 -z 200 --xproc=2 --yproc=2 --zproc=2MPI Command: mpirun -n <number_processes> Dataset: Run Directory: /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/run/oneview_runs/multicore/icx/oneview_run_1740438801OMP_NUM_THREADS: 1I_MPI_PIN_ORDER: bunchOMP_DISPLAY_AFFINITY: TRUEOMP_PROC_BIND: spreadOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEI_MPI_PIN_DOMAIN: autoI_MPI_DEBUG: 4OMP_PLACES: threads
Run 8x12	Number processes: 8Number nodes: 1Run Command: <executable> -x 200 -y 200 -z 200 --xproc=2 --yproc=2 --zproc=2MPI Command: mpirun -n <number_processes> Dataset: Run Directory: /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/run/oneview_runs/multicore/icx/oneview_run_1740438801OMP_NUM_THREADS: 12I_MPI_PIN_ORDER: bunchOMP_DISPLAY_AFFINITY: TRUEOMP_PROC_BIND: spreadOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEI_MPI_PIN_DOMAIN: autoI_MPI_DEBUG: 4OMP_PLACES: threads
Run 8x16	Number processes: 8Number nodes: 1Run Command: <executable> -x 200 -y 200 -z 200 --xproc=2 --yproc=2 --zproc=2MPI Command: mpirun -n <number_processes> Dataset: Run Directory: /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/run/oneview_runs/multicore/icx/oneview_run_1740438801OMP_NUM_THREADS: 16I_MPI_PIN_ORDER: bunchOMP_DISPLAY_AFFINITY: TRUEOMP_PROC_BIND: spreadOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEI_MPI_PIN_DOMAIN: autoI_MPI_DEBUG: 4OMP_PLACES: threads
Run 8x20	Number processes: 8Number nodes: 1Run Command: <executable> -x 200 -y 200 -z 200 --xproc=2 --yproc=2 --zproc=2MPI Command: mpirun -n <number_processes> Dataset: Run Directory: /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/run/oneview_runs/multicore/icx/oneview_run_1740438801OMP_NUM_THREADS: 20I_MPI_PIN_ORDER: bunchOMP_DISPLAY_AFFINITY: TRUEOMP_PROC_BIND: spreadOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEI_MPI_PIN_DOMAIN: autoI_MPI_DEBUG: 4OMP_PLACES: threads
Run 8x24	Number processes: 8Number nodes: 1Run Command: <executable> -x 200 -y 200 -z 200 --xproc=2 --yproc=2 --zproc=2MPI Command: mpirun -n <number_processes> Dataset: Run Directory: /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/run/oneview_runs/multicore/icx/oneview_run_1740438801OMP_NUM_THREADS: 24I_MPI_PIN_ORDER: bunchOMP_DISPLAY_AFFINITY: TRUEOMP_PROC_BIND: spreadOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEI_MPI_PIN_DOMAIN: autoI_MPI_DEBUG: 4OMP_PLACES: threads
Run 8x28	Number processes: 8Number nodes: 1Run Command: <executable> -x 200 -y 200 -z 200 --xproc=2 --yproc=2 --zproc=2MPI Command: mpirun -n <number_processes> Dataset: Run Directory: /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/run/oneview_runs/multicore/icx/oneview_run_1740438801OMP_NUM_THREADS: 28I_MPI_PIN_ORDER: bunchOMP_DISPLAY_AFFINITY: TRUEOMP_PROC_BIND: spreadOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEI_MPI_PIN_DOMAIN: autoI_MPI_DEBUG: 4OMP_PLACES: threads
Run 8x32	Number processes: 8Number nodes: 1Run Command: <executable> -x 200 -y 200 -z 200 --xproc=2 --yproc=2 --zproc=2MPI Command: mpirun -n <number_processes> Dataset: Run Directory: /home/eoseret/qaas_runs_ZEN5/174-043-3878/intel/CoMD/run/oneview_runs/multicore/icx/oneview_run_1740438801OMP_NUM_THREADS: 32I_MPI_PIN_ORDER: bunchOMP_DISPLAY_AFFINITY: TRUEOMP_PROC_BIND: spreadOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEI_MPI_PIN_DOMAIN: autoI_MPI_DEBUG: 4OMP_PLACES: threads

(8x1) Efficiency	(8x1) Potential Speed-Up (%)	(8x12) Efficiency	(8x12) Potential Speed-Up (%)	(8x16) Efficiency	(8x16) Potential Speed-Up (%)	(8x20) Efficiency	(8x20) Potential Speed-Up (%)	(8x24) Efficiency	(8x24) Potential Speed-Up (%)	(8x28) Efficiency	(8x28) Potential Speed-Up (%)	(8x32) Efficiency	(8x32) Potential Speed-Up (%)
1	0	1.31	-0	1.85	0	1.35	-0	1.74	-0	1.65	-0	1.38	-0

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency

Run	Number of threads	Efficiency (ideal is 1)	Speedup	Ideal Speedup	Time (s)	Coverage (%)
8x1	8	1	1	1	0.099980838596821	0.01580492220819
8x12	60	1.31	15.73	12	0.019999999552965	0.010112335905433
8x16	55	1.85	29.58	16	0.010000000707805	0.0068699554540217
8x20	76	1.35	27.03	20	0.015000000596046	0.0083430549129844
8x24	69	1.74	41.86	24	0.0099999997764826	0.0060956501401961
8x28	70	1.65	46.27	28	0.010000000707805	0.0059268628247082
8x32	81	1.38	44.18	32	0.010000000707805	0.0065700626000762

Name	Coverage (%)	Time (s)
○__libm_log_z0	0.02	0.08

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

Workaround

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

FMA

Workaround

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

▶Scalability Runs Description

▼Columns Filter

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency