x86_64: Fix svml_d_erfc8_core_avx512.S code formatting

This commit contains following formatting changes

1. Instructions proceeded by a tab.
2. Instruction less than 8 characters in length have a tab
   between it and the first operand.
3. Instruction greater than 7 characters in length have a
   space between it and the first operand.
4. Tabs after `#define`d names and their value.
5. 8 space at the beginning of line replaced by tab.
6. Indent comments with code.
7. Remove redundent .text section.
8. 1 space between line content and line comment.
9. Space after all commas.

Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>

1 files changed, 3779 insertions, 3781 deletions

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_erfc8_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_d_erfc8_core_avx512.S
index bd2c3bef7d..77228814d3 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_d_erfc8_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_d_erfc8_core_avx512.S
@@ -29,3832 +29,3830 @@
 
 /* Offsets for data table __svml_derfc_data_internal
  */
-#define _erfc_tbl                     	0
-#define _AbsMask                      	55808
-#define _MaxThreshold                 	55872
-#define _SgnMask                      	55936
-#define _One                          	56000
-#define _TwoM128                      	56064
-#define _SRound                       	56128
-#define _poly1_0                      	56192
-#define _poly1_1                      	56256
-#define _poly3_0                      	56320
-#define _poly3_1                      	56384
-#define _poly5_0                      	56448
-#define _poly5_1                      	56512
-#define _poly1_2                      	56576
-#define _poly3_2                      	56640
-#define _poly5_2                      	56704
-#define _poly1_3                      	56768
-#define _poly3_3                      	56832
-#define _poly5_3                      	56896
-#define _poly1_4                      	56960
-#define _poly3_4                      	57024
-#define _poly1_5                      	57088
-#define _poly3_5                      	57152
-#define _poly3_6                      	57216
-#define _poly1_6                      	57280
-#define _poly1_7                      	57344
-#define _UF_Threshold                 	57408
-#define _Mask32                       	57472
+#define _erfc_tbl			0
+#define _AbsMask			55808
+#define _MaxThreshold			55872
+#define _SgnMask			55936
+#define _One				56000
+#define _TwoM128			56064
+#define _SRound				56128
+#define _poly1_0			56192
+#define _poly1_1			56256
+#define _poly3_0			56320
+#define _poly3_1			56384
+#define _poly5_0			56448
+#define _poly5_1			56512
+#define _poly1_2			56576
+#define _poly3_2			56640
+#define _poly5_2			56704
+#define _poly1_3			56768
+#define _poly3_3			56832
+#define _poly5_3			56896
+#define _poly1_4			56960
+#define _poly3_4			57024
+#define _poly1_5			57088
+#define _poly3_5			57152
+#define _poly3_6			57216
+#define _poly1_6			57280
+#define _poly1_7			57344
+#define _UF_Threshold			57408
+#define _Mask32				57472
 
 #include <sysdep.h>
 
-        .text
-	.section .text.evex512,"ax",@progbits
+	.section .text.evex512, "ax", @progbits
 ENTRY(_ZGVeN8v_erfc_skx)
-        pushq     %rbp
-        cfi_def_cfa_offset(16)
-        movq      %rsp, %rbp
-        cfi_def_cfa(6, 16)
-        cfi_offset(6, -16)
-        andq      $-64, %rsp
-        subq      $192, %rsp
+	pushq	%rbp
+	cfi_def_cfa_offset(16)
+	movq	%rsp, %rbp
+	cfi_def_cfa(6, 16)
+	cfi_offset(6, -16)
+	andq	$-64, %rsp
+	subq	$192, %rsp
 
-/* vector gather: erfc_h(x0), (erfc_l(x0), 2/sqrt(pi)*exp(-x0^2)) */
-        lea       __svml_derfc_data_internal(%rip), %rax
+	/* vector gather: erfc_h(x0), (erfc_l(x0), 2/sqrt(pi)*exp(-x0^2)) */
+	lea	__svml_derfc_data_internal(%rip), %rax
 
-/*
- * erfc(27.25) underflows to 0
- * can compute all results in the main path
- */
-        vmovups   _MaxThreshold+__svml_derfc_data_internal(%rip), %zmm13
-        vmovups   _SRound+__svml_derfc_data_internal(%rip), %zmm7
-        vmovups   _One+__svml_derfc_data_internal(%rip), %zmm14
-        kxnorw    %k0, %k0, %k2
-        kxnorw    %k0, %k0, %k1
-        vmovaps   %zmm0, %zmm11
-        vandpd    _AbsMask+__svml_derfc_data_internal(%rip), %zmm11, %zmm12
-        vandpd    _SgnMask+__svml_derfc_data_internal(%rip), %zmm11, %zmm3
-        vmovups   _TwoM128+__svml_derfc_data_internal(%rip), %zmm0
-        vminpd    {sae}, %zmm13, %zmm12, %zmm6
+	/*
+	 * erfc(27.25) underflows to 0
+	 * can compute all results in the main path
+	 */
+	vmovups	_MaxThreshold+__svml_derfc_data_internal(%rip), %zmm13
+	vmovups	_SRound+__svml_derfc_data_internal(%rip), %zmm7
+	vmovups	_One+__svml_derfc_data_internal(%rip), %zmm14
+	kxnorw	%k0, %k0, %k2
+	kxnorw	%k0, %k0, %k1
+	vmovaps	%zmm0, %zmm11
+	vandpd	_AbsMask+__svml_derfc_data_internal(%rip), %zmm11, %zmm12
+	vandpd	_SgnMask+__svml_derfc_data_internal(%rip), %zmm11, %zmm3
+	vmovups	_TwoM128+__svml_derfc_data_internal(%rip), %zmm0
+	vminpd	{sae}, %zmm13, %zmm12, %zmm6
 
-/* Start polynomial evaluation */
-        vmovups   _poly1_0+__svml_derfc_data_internal(%rip), %zmm12
-        vmovups   _poly3_0+__svml_derfc_data_internal(%rip), %zmm13
-        vaddpd    {rn-sae}, %zmm7, %zmm6, %zmm1
-        vorpd     %zmm3, %zmm14, %zmm15
-        vmaxpd    {sae}, %zmm0, %zmm6, %zmm2
-        vmovups   _poly1_1+__svml_derfc_data_internal(%rip), %zmm6
-        vpsllq    $4, %zmm1, %zmm4
-        vsubpd    {rn-sae}, %zmm7, %zmm1, %zmm5
+	/* Start polynomial evaluation */
+	vmovups	_poly1_0+__svml_derfc_data_internal(%rip), %zmm12
+	vmovups	_poly3_0+__svml_derfc_data_internal(%rip), %zmm13
+	vaddpd	{rn-sae}, %zmm7, %zmm6, %zmm1
+	vorpd	%zmm3, %zmm14, %zmm15
+	vmaxpd	{sae}, %zmm0, %zmm6, %zmm2
+	vmovups	_poly1_1+__svml_derfc_data_internal(%rip), %zmm6
+	vpsllq	$4, %zmm1, %zmm4
+	vsubpd	{rn-sae}, %zmm7, %zmm1, %zmm5
 
-/* 2.0 if x<0, 0.0 otherwise */
-        vsubpd    {rn-sae}, %zmm15, %zmm14, %zmm10
+	/* 2.0 if x<0, 0.0 otherwise */
+	vsubpd	{rn-sae}, %zmm15, %zmm14, %zmm10
 
-/* 2^(-128) with sign of input */
-        vorpd     %zmm3, %zmm0, %zmm7
-        vsubpd    {rn-sae}, %zmm5, %zmm2, %zmm9
-        vmovups   _poly1_2+__svml_derfc_data_internal(%rip), %zmm15
-        vmovups   _poly5_1+__svml_derfc_data_internal(%rip), %zmm3
-        vmovups   _poly5_0+__svml_derfc_data_internal(%rip), %zmm14
-        vmovups   _poly1_3+__svml_derfc_data_internal(%rip), %zmm0
-        vmovups   _poly5_2+__svml_derfc_data_internal(%rip), %zmm1
-        vmovups   _poly3_2+__svml_derfc_data_internal(%rip), %zmm2
-        vmulpd    {rn-sae}, %zmm9, %zmm5, %zmm8
-        vmovups   _poly3_1+__svml_derfc_data_internal(%rip), %zmm5
-        vfmadd231pd {rn-sae}, %zmm8, %zmm12, %zmm6
-        vfmadd231pd {rn-sae}, %zmm8, %zmm14, %zmm3
-        vfmadd231pd {rn-sae}, %zmm8, %zmm13, %zmm5
-        vmovups   _poly3_3+__svml_derfc_data_internal(%rip), %zmm12
-        vmovups   _poly5_3+__svml_derfc_data_internal(%rip), %zmm13
-        vfmadd213pd {rn-sae}, %zmm15, %zmm8, %zmm6
-        vfmadd213pd {rn-sae}, %zmm1, %zmm8, %zmm3
-        vfmadd213pd {rn-sae}, %zmm2, %zmm8, %zmm5
-        vmovups   _poly3_5+__svml_derfc_data_internal(%rip), %zmm14
+	/* 2^(-128) with sign of input */
+	vorpd	%zmm3, %zmm0, %zmm7
+	vsubpd	{rn-sae}, %zmm5, %zmm2, %zmm9
+	vmovups	_poly1_2+__svml_derfc_data_internal(%rip), %zmm15
+	vmovups	_poly5_1+__svml_derfc_data_internal(%rip), %zmm3
+	vmovups	_poly5_0+__svml_derfc_data_internal(%rip), %zmm14
+	vmovups	_poly1_3+__svml_derfc_data_internal(%rip), %zmm0
+	vmovups	_poly5_2+__svml_derfc_data_internal(%rip), %zmm1
+	vmovups	_poly3_2+__svml_derfc_data_internal(%rip), %zmm2
+	vmulpd	{rn-sae}, %zmm9, %zmm5, %zmm8
+	vmovups	_poly3_1+__svml_derfc_data_internal(%rip), %zmm5
+	vfmadd231pd {rn-sae}, %zmm8, %zmm12, %zmm6
+	vfmadd231pd {rn-sae}, %zmm8, %zmm14, %zmm3
+	vfmadd231pd {rn-sae}, %zmm8, %zmm13, %zmm5
+	vmovups	_poly3_3+__svml_derfc_data_internal(%rip), %zmm12
+	vmovups	_poly5_3+__svml_derfc_data_internal(%rip), %zmm13
+	vfmadd213pd {rn-sae}, %zmm15, %zmm8, %zmm6
+	vfmadd213pd {rn-sae}, %zmm1, %zmm8, %zmm3
+	vfmadd213pd {rn-sae}, %zmm2, %zmm8, %zmm5
+	vmovups	_poly3_5+__svml_derfc_data_internal(%rip), %zmm14
 
-/* P5 = P5 + D2*P07 */
-        vmovups   _poly3_6+__svml_derfc_data_internal(%rip), %zmm15
-        vfmadd213pd {rn-sae}, %zmm0, %zmm8, %zmm6
-        vfmadd213pd {rn-sae}, %zmm13, %zmm8, %zmm3
-        vfmadd213pd {rn-sae}, %zmm12, %zmm8, %zmm5
-        vmovups   _poly3_4+__svml_derfc_data_internal(%rip), %zmm12
-        vmovups   _poly1_5+__svml_derfc_data_internal(%rip), %zmm13
-        vfmadd213pd {rn-sae}, %zmm12, %zmm8, %zmm5
-        vfmadd213pd {rn-sae}, %zmm14, %zmm8, %zmm5
-        vpandq    _Mask32+__svml_derfc_data_internal(%rip), %zmm4, %zmm4
-        vpmovqd   %zmm4, %ymm0
-        vmovups   _poly1_4+__svml_derfc_data_internal(%rip), %zmm4
-        vfmadd213pd {rn-sae}, %zmm4, %zmm8, %zmm6
+	/* P5 = P5 + D2*P07 */
+	vmovups	_poly3_6+__svml_derfc_data_internal(%rip), %zmm15
+	vfmadd213pd {rn-sae}, %zmm0, %zmm8, %zmm6
+	vfmadd213pd {rn-sae}, %zmm13, %zmm8, %zmm3
+	vfmadd213pd {rn-sae}, %zmm12, %zmm8, %zmm5
+	vmovups	_poly3_4+__svml_derfc_data_internal(%rip), %zmm12
+	vmovups	_poly1_5+__svml_derfc_data_internal(%rip), %zmm13
+	vfmadd213pd {rn-sae}, %zmm12, %zmm8, %zmm5
+	vfmadd213pd {rn-sae}, %zmm14, %zmm8, %zmm5
+	vpandq	_Mask32+__svml_derfc_data_internal(%rip), %zmm4, %zmm4
+	vpmovqd	%zmm4, %ymm0
+	vmovups	_poly1_4+__svml_derfc_data_internal(%rip), %zmm4
+	vfmadd213pd {rn-sae}, %zmm4, %zmm8, %zmm6
 
-/* T^2 */
-        vmulpd    {rn-sae}, %zmm8, %zmm8, %zmm4
-        vfmadd213pd {rn-sae}, %zmm13, %zmm8, %zmm6
-        vpxord    %zmm1, %zmm1, %zmm1
-        vgatherdpd 8(%rax,%ymm0), %zmm1{%k2}
-        vpxord    %zmm2, %zmm2, %zmm2
-        vgatherdpd (%rax,%ymm0), %zmm2{%k1}
+	/* T^2 */
+	vmulpd	{rn-sae}, %zmm8, %zmm8, %zmm4
+	vfmadd213pd {rn-sae}, %zmm13, %zmm8, %zmm6
+	vpxord	%zmm1, %zmm1, %zmm1
+	vgatherdpd 8(%rax, %ymm0), %zmm1{%k2}
+	vpxord	%zmm2, %zmm2, %zmm2
+	vgatherdpd (%rax, %ymm0), %zmm2{%k1}
 
-/* Diff^2 */
-        vmulpd    {rn-sae}, %zmm9, %zmm9, %zmm0
-        vfmadd231pd {rn-sae}, %zmm0, %zmm3, %zmm15
-        vmovups   _poly1_6+__svml_derfc_data_internal(%rip), %zmm3
-        vfmadd213pd {rn-sae}, %zmm15, %zmm8, %zmm5
-        vfmadd213pd {rn-sae}, %zmm3, %zmm8, %zmm6
-        vmovups   _poly1_7+__svml_derfc_data_internal(%rip), %zmm3
-        vfmsub213pd {rn-sae}, %zmm8, %zmm0, %zmm5
-        vfmadd213pd {rn-sae}, %zmm3, %zmm8, %zmm6
+	/* Diff^2 */
+	vmulpd	{rn-sae}, %zmm9, %zmm9, %zmm0
+	vfmadd231pd {rn-sae}, %zmm0, %zmm3, %zmm15
+	vmovups	_poly1_6+__svml_derfc_data_internal(%rip), %zmm3
+	vfmadd213pd {rn-sae}, %zmm15, %zmm8, %zmm5
+	vfmadd213pd {rn-sae}, %zmm3, %zmm8, %zmm6
+	vmovups	_poly1_7+__svml_derfc_data_internal(%rip), %zmm3
+	vfmsub213pd {rn-sae}, %zmm8, %zmm0, %zmm5
+	vfmadd213pd {rn-sae}, %zmm3, %zmm8, %zmm6
 
-/* EXP_X0H *= Diff */
-        vmulpd    {rn-sae}, %zmm9, %zmm1, %zmm8
+	/* EXP_X0H *= Diff */
+	vmulpd	{rn-sae}, %zmm9, %zmm1, %zmm8
 
-/* Special arguments (for flags only) */
-        vmovups   _UF_Threshold+__svml_derfc_data_internal(%rip), %zmm9
-        vfmadd213pd {rn-sae}, %zmm5, %zmm4, %zmm6
-        vcmppd    $21, {sae}, %zmm9, %zmm11, %k0
+	/* Special arguments (for flags only) */
+	vmovups	_UF_Threshold+__svml_derfc_data_internal(%rip), %zmm9
+	vfmadd213pd {rn-sae}, %zmm5, %zmm4, %zmm6
+	vcmppd	$21, {sae}, %zmm9, %zmm11, %k0
 
-/* EXP_x0H*Diff*(1+P1) */
-        vfmadd213pd {rn-sae}, %zmm8, %zmm8, %zmm6
-        kmovw     %k0, %edx
+	/* EXP_x0H*Diff*(1+P1) */
+	vfmadd213pd {rn-sae}, %zmm8, %zmm8, %zmm6
+	kmovw	%k0, %edx
 
-/* erfc(|_VARG1|) = erfc_h(x0) - P1 */
-        vsubpd    {rn-sae}, %zmm6, %zmm2, %zmm0
-        vfmadd213pd {rn-sae}, %zmm10, %zmm7, %zmm0
-        testl     %edx, %edx
+	/* erfc(|_VARG1|) = erfc_h(x0) - P1 */
+	vsubpd	{rn-sae}, %zmm6, %zmm2, %zmm0
+	vfmadd213pd {rn-sae}, %zmm10, %zmm7, %zmm0
+	testl	%edx, %edx
 
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 edx zmm0 zmm11
+	/* Go to special inputs processing branch */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	# LOE rbx r12 r13 r14 r15 edx zmm0 zmm11
 
-/* Restore registers
- * and exit the function
- */
+	/* Restore registers
+	 * and exit the function
+	 */
 
 L(EXIT):
-        movq      %rbp, %rsp
-        popq      %rbp
-        cfi_def_cfa(7, 8)
-        cfi_restore(6)
-        ret
-        cfi_def_cfa(6, 16)
-        cfi_offset(6, -16)
+	movq	%rbp, %rsp
+	popq	%rbp
+	cfi_def_cfa(7, 8)
+	cfi_restore(6)
+	ret
+	cfi_def_cfa(6, 16)
+	cfi_offset(6, -16)
 
-/* Branch to process
- * special inputs
- */
+	/* Branch to process
+	 * special inputs
+	 */
 
 L(SPECIAL_VALUES_BRANCH):
-        vmovups   %zmm11, 64(%rsp)
-        vmovups   %zmm0, 128(%rsp)
-                                # LOE rbx r12 r13 r14 r15 edx zmm0
+	vmovups	%zmm11, 64(%rsp)
+	vmovups	%zmm0, 128(%rsp)
+	# LOE rbx r12 r13 r14 r15 edx zmm0
 
-        xorl      %eax, %eax
-                                # LOE rbx r12 r13 r14 r15 eax edx
+	xorl	%eax, %eax
+	# LOE rbx r12 r13 r14 r15 eax edx
 
-        vzeroupper
-        movq      %r12, 16(%rsp)
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
-        movl      %eax, %r12d
-        movq      %r13, 8(%rsp)
-        /*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
-        movl      %edx, %r13d
-        movq      %r14, (%rsp)
-        /*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r15 r12d r13d
+	vzeroupper
+	movq	%r12, 16(%rsp)
+	/*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
+	movl	%eax, %r12d
+	movq	%r13, 8(%rsp)
+	/*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
+	movl	%edx, %r13d
+	movq	%r14, (%rsp)
+	/*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r15 r12d r13d
 
-/* Range mask
- * bits check
- */
+	/* Range mask
+	 * bits check
+	 */
 
 L(RANGEMASK_CHECK):
-        btl       %r12d, %r13d
+	btl	%r12d, %r13d
 
-/* Call scalar math function */
-        jc        L(SCALAR_MATH_CALL)
-                                # LOE rbx r15 r12d r13d
+	/* Call scalar math function */
+	jc	L(SCALAR_MATH_CALL)
+	# LOE rbx r15 r12d r13d
 
-/* Special inputs
- * processing loop
- */
+	/* Special inputs
+	 * processing loop
+	 */
 
 L(SPECIAL_VALUES_LOOP):
-        incl      %r12d
-        cmpl      $8, %r12d
+	incl	%r12d
+	cmpl	$8, %r12d
 
-/* Check bits in range mask */
-        jl        L(RANGEMASK_CHECK)
-                                # LOE rbx r15 r12d r13d
+	/* Check bits in range mask */
+	jl	L(RANGEMASK_CHECK)
+	# LOE rbx r15 r12d r13d
 
-        movq      16(%rsp), %r12
-        cfi_restore(12)
-        movq      8(%rsp), %r13
-        cfi_restore(13)
-        movq      (%rsp), %r14
-        cfi_restore(14)
-        vmovups   128(%rsp), %zmm0
+	movq	16(%rsp), %r12
+	cfi_restore(12)
+	movq	8(%rsp), %r13
+	cfi_restore(13)
+	movq	(%rsp), %r14
+	cfi_restore(14)
+	vmovups	128(%rsp), %zmm0
 
-/* Go to exit */
-        jmp       L(EXIT)
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
-        /*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
-        /*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r12 r13 r14 r15 zmm0
+	/* Go to exit */
+	jmp	L(EXIT)
+	/*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
+	/*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
+	/*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r12 r13 r14 r15 zmm0
 
-/* Scalar math fucntion call
- * to process special input
- */
+	/* Scalar math fucntion call
+	 * to process special input
+	 */
 
 L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movsd     64(%rsp,%r14,8), %xmm0
-        call      erfc@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
+	movl	%r12d, %r14d
+	movsd	64(%rsp, %r14, 8), %xmm0
+	call	erfc@PLT
+	# LOE rbx r14 r15 r12d r13d xmm0
 
-        movsd     %xmm0, 128(%rsp,%r14,8)
+	movsd	%xmm0, 128(%rsp, %r14, 8)
 
-/* Process special inputs in loop */
-        jmp       L(SPECIAL_VALUES_LOOP)
-                                # LOE rbx r15 r12d r13d
+	/* Process special inputs in loop */
+	jmp	L(SPECIAL_VALUES_LOOP)
+	# LOE rbx r15 r12d r13d
 END(_ZGVeN8v_erfc_skx)
 
-        .section .rodata, "a"
-        .align 64
+	.section .rodata, "a"
+	.align	64
 
 #ifdef __svml_derfc_data_internal_typedef
 typedef unsigned int VUINT32;
-typedef struct
-{
-        __declspec(align(64)) VUINT32 _erfc_tbl[3488*2][2];
-        __declspec(align(64)) VUINT32 _AbsMask[8][2];
-        __declspec(align(64)) VUINT32 _MaxThreshold[8][2];
-        __declspec(align(64)) VUINT32 _SgnMask[8][2];
-        __declspec(align(64)) VUINT32 _One[8][2];
-        __declspec(align(64)) VUINT32 _TwoM128[8][2];
-        __declspec(align(64)) VUINT32 _SRound[8][2];
-        __declspec(align(64)) VUINT32 _poly1_0[8][2];
-        __declspec(align(64)) VUINT32 _poly1_1[8][2];
-        __declspec(align(64)) VUINT32 _poly3_0[8][2];
-        __declspec(align(64)) VUINT32 _poly3_1[8][2];
-        __declspec(align(64)) VUINT32 _poly5_0[8][2];
-        __declspec(align(64)) VUINT32 _poly5_1[8][2];
-        __declspec(align(64)) VUINT32 _poly1_2[8][2];
-        __declspec(align(64)) VUINT32 _poly3_2[8][2];
-        __declspec(align(64)) VUINT32 _poly5_2[8][2];
-        __declspec(align(64)) VUINT32 _poly1_3[8][2];
-        __declspec(align(64)) VUINT32 _poly3_3[8][2];
-        __declspec(align(64)) VUINT32 _poly5_3[8][2];
-        __declspec(align(64)) VUINT32 _poly1_4[8][2];
-        __declspec(align(64)) VUINT32 _poly3_4[8][2];
-        __declspec(align(64)) VUINT32 _poly1_5[8][2];
-        __declspec(align(64)) VUINT32 _poly3_5[8][2];
-        __declspec(align(64)) VUINT32 _poly3_6[8][2];
-        __declspec(align(64)) VUINT32 _poly1_6[8][2];
-        __declspec(align(64)) VUINT32 _poly1_7[8][2];
-        __declspec(align(64)) VUINT32 _UF_Threshold[8][2];
-        __declspec(align(64)) VUINT32 _Mask32[8][2];
+typedef struct {
+	__declspec(align(64)) VUINT32 _erfc_tbl[3488*2][2];
+	__declspec(align(64)) VUINT32 _AbsMask[8][2];
+	__declspec(align(64)) VUINT32 _MaxThreshold[8][2];
+	__declspec(align(64)) VUINT32 _SgnMask[8][2];
+	__declspec(align(64)) VUINT32 _One[8][2];
+	__declspec(align(64)) VUINT32 _TwoM128[8][2];
+	__declspec(align(64)) VUINT32 _SRound[8][2];
+	__declspec(align(64)) VUINT32 _poly1_0[8][2];
+	__declspec(align(64)) VUINT32 _poly1_1[8][2];
+	__declspec(align(64)) VUINT32 _poly3_0[8][2];
+	__declspec(align(64)) VUINT32 _poly3_1[8][2];
+	__declspec(align(64)) VUINT32 _poly5_0[8][2];
+	__declspec(align(64)) VUINT32 _poly5_1[8][2];
+	__declspec(align(64)) VUINT32 _poly1_2[8][2];
+	__declspec(align(64)) VUINT32 _poly3_2[8][2];
+	__declspec(align(64)) VUINT32 _poly5_2[8][2];
+	__declspec(align(64)) VUINT32 _poly1_3[8][2];
+	__declspec(align(64)) VUINT32 _poly3_3[8][2];
+	__declspec(align(64)) VUINT32 _poly5_3[8][2];
+	__declspec(align(64)) VUINT32 _poly1_4[8][2];
+	__declspec(align(64)) VUINT32 _poly3_4[8][2];
+	__declspec(align(64)) VUINT32 _poly1_5[8][2];
+	__declspec(align(64)) VUINT32 _poly3_5[8][2];
+	__declspec(align(64)) VUINT32 _poly3_6[8][2];
+	__declspec(align(64)) VUINT32 _poly1_6[8][2];
+	__declspec(align(64)) VUINT32 _poly1_7[8][2];
+	__declspec(align(64)) VUINT32 _UF_Threshold[8][2];
+	__declspec(align(64)) VUINT32 _Mask32[8][2];
 } __svml_derfc_data_internal;
 #endif
 __svml_derfc_data_internal:
-        /*== _erfc_tbl ==*/
-        .quad 0x47f0000000000000, 0x47f20dd750429b6d
-        .quad 0x47efb7c9030853b3, 0x47f20d8f1975c85d
-        .quad 0x47ef6f9447be0743, 0x47f20cb67bd452c7
-        .quad 0x47ef27640f9853d9, 0x47f20b4d8bac36c1
-        .quad 0x47eedf3a9ba22dad, 0x47f209546ad13ccf
-        .quad 0x47ee971a2c4436ae, 0x47f206cb4897b148
-        .quad 0x47ee4f05010eca8c, 0x47f203b261cd0053
-        .quad 0x47ee06fd58842c7e, 0x47f2000a00ae3804
-        .quad 0x47edbf056fe2df35, 0x47f1fbd27cdc72d3
-        .quad 0x47ed771f82f02f4e, 0x47f1f70c3b4f2cc8
-        .quad 0x47ed2f4dcbc2f894, 0x47f1f1b7ae44867f
-        .quad 0x47ece792828eae5c, 0x47f1ebd5552f795b
-        .quad 0x47ec9fefdd6eaf19, 0x47f1e565bca400d4
-        .quad 0x47ec58681031eb6a, 0x47f1de697e413d29
-        .quad 0x47ec10fd4c26e896, 0x47f1d6e14099944a
-        .quad 0x47ebc9b1bfe82687, 0x47f1cecdb718d61c
-        .quad 0x47eb82879728f11e, 0x47f1c62fa1e869b6
-        .quad 0x47eb3b80fa82a4bb, 0x47f1bd07cdd189ac
-        .quad 0x47eaf4a00f426daa, 0x47f1b357141d95d5
-        .quad 0x47eaade6f7378a0e, 0x47f1a91e5a748165
-        .quad 0x47ea6757d08215d8, 0x47f19e5e92b964ab
-        .quad 0x47ea20f4b5626818, 0x47f19318bae53a04
-        .quad 0x47e9dabfbc090901, 0x47f1874ddcdfce24
-        .quad 0x47e994baf66747ad, 0x47f17aff0e56ec10
-        .quad 0x47e94ee8720076b6, 0x47f16e2d7093cd8c
-        .quad 0x47e9094a37bbd66e, 0x47f160da304ed92f
-        .quad 0x47e8c3e24bb73372, 0x47f153068581b781
-        .quad 0x47e87eb2ad1a4032, 0x47f144b3b337c90c
-        .quad 0x47e839bd55eaafc8, 0x47f135e3075d076b
-        .quad 0x47e7f5043ae11862, 0x47f12695da8b5bde
-        .quad 0x47e7b0894b3ea35c, 0x47f116cd8fd67618
-        .quad 0x47e76c4e70a390e7, 0x47f1068b94962e5e
-        .quad 0x47e728558ee694fc, 0x47f0f5d1602f7e41
-        .quad 0x47e6e4a083ed132f, 0x47f0e4a073dc1b91
-        .quad 0x47e6a13127843ec1, 0x47f0d2fa5a70c168
-        .quad 0x47e65e094b3b2413, 0x47f0c0e0a8223359
-        .quad 0x47e61b2aba3da093, 0x47f0ae54fa490723
-        .quad 0x47e5d89739304dcf, 0x47f09b58f724416b
-        .quad 0x47e59650860d6469, 0x47f087ee4d9ad247
-        .quad 0x47e5545858029b39, 0x47f07416b4fbfe7c
-        .quad 0x47e512b05f5006e1, 0x47f05fd3ecbec298
-        .quad 0x47e4d15a4527fdc7, 0x47f04b27bc403d30
-        .quad 0x47e49057ab900447, 0x47f03613f2812daf
-        .quad 0x47e44faa2d42c4a0, 0x47f0209a65e29545
-        .quad 0x47e40f535d93160e, 0x47f00abcf3e187a9
-        .quad 0x47e3cf54c8501620, 0x47efe8fb01a47307
-        .quad 0x47e38faff1aa574a, 0x47efbbbbef34b4b2
-        .quad 0x47e35066561a275d, 0x47ef8dc092d58ff8
-        .quad 0x47e311796a46f064, 0x47ef5f0cdaf15313
-        .quad 0x47e2d2ea9aefb636, 0x47ef2fa4c16c0019
-        .quad 0x47e294bb4cd4b2bd, 0x47eeff8c4b1375db
-        .quad 0x47e256ecdca212cc, 0x47eecec7870ebca8
-        .quad 0x47e219809edbd524, 0x47ee9d5a8e4c934e
-        .quad 0x47e1dc77dfcacd02, 0x47ee6b4982f158b9
-        .quad 0x47e19fd3e36ac96a, 0x47ee38988fc46e72
-        .quad 0x47e16395e559e218, 0x47ee054be79d3042
-        .quad 0x47e127bf18c8eadc, 0x47edd167c4cf9d2a
-        .quad 0x47e0ec50a86d0dd4, 0x47ed9cf06898cdaf
-        .quad 0x47e0b14bb6728cd8, 0x47ed67ea1a8b5368
-        .quad 0x47e076b15c70aa28, 0x47ed325927fb9d89
-        .quad 0x47e03c82ab5eb831, 0x47ecfc41e36c7df9
-        .quad 0x47e002c0ab8a5018, 0x47ecc5a8a3fbea40
-        .quad 0x47df92d8b91d5cc7, 0x47ec8e91c4d01368
-        .quad 0x47df210d6a9a6a31, 0x47ec5701a484ef9d
-        .quad 0x47deb02147ce245c, 0x47ec1efca49a5011
-        .quad 0x47de40161b701275, 0x47ebe68728e29d5e
-        .quad 0x47ddd0ed9ea4bdd6, 0x47ebada596f25436
-        .quad 0x47dd62a978f7c957, 0x47eb745c55905bf8
-        .quad 0x47dcf54b4058455f, 0x47eb3aafcc27502e
-        .quad 0x47dc88d479173cce, 0x47eb00a46237d5be
-        .quad 0x47dc1d4695e87644, 0x47eac63e7ecc1411
-        .quad 0x47dbb2a2f7e56520, 0x47ea8b8287ec6a09
-        .quad 0x47db48eaee924501, 0x47ea5074e2157620
-        .quad 0x47dae01fb7e55a66, 0x47ea1519efaf889e
-        .quad 0x47da78428050527e, 0x47e9d97610879642
-        .quad 0x47da115462cbbc17, 0x47e99d8da149c13f
-        .quad 0x47d9ab5668e4930a, 0x47e96164fafd8de3
-        .quad 0x47d946498acbd766, 0x47e925007283d7aa
-        .quad 0x47d8e22eaf68291e, 0x47e8e86458169af8