x86_64: Fix svml_d_sinh4_core_avx2.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, 406 insertions, 408 deletions

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_sinh4_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_d_sinh4_core_avx2.S
index 53b8a32426..ae16600579 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_d_sinh4_core_avx2.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_d_sinh4_core_avx2.S
@@ -34,437 +34,435 @@
 
 /* Offsets for data table __svml_dsinh_data_internal
  */
-#define _dbInvLn2                     	0
-#define _dbLn2hi                      	32
-#define _dbLn2lo                      	64
-#define _dSign                        	96
-#define _dbT                          	128
-#define _dbShifter                    	2176
-#define _iDomainRange                 	2208
-#define _dPC2                         	2240
-#define _dPC3                         	2272
-#define _dPC4                         	2304
-#define _dPC5                         	2336
-#define _lIndexMask                   	2368
+#define _dbInvLn2			0
+#define _dbLn2hi			32
+#define _dbLn2lo			64
+#define _dSign				96
+#define _dbT				128
+#define _dbShifter			2176
+#define _iDomainRange			2208
+#define _dPC2				2240
+#define _dPC3				2272
+#define _dPC4				2304
+#define _dPC5				2336
+#define _lIndexMask			2368
 
 #include <sysdep.h>
 
-        .text
-	.section .text.avx2,"ax",@progbits
+	.section .text.avx2, "ax", @progbits
 ENTRY(_ZGVdN4v_sinh_avx2)
-        pushq     %rbp
-        cfi_def_cfa_offset(16)
-        movq      %rsp, %rbp
-        cfi_def_cfa(6, 16)
-        cfi_offset(6, -16)
-        andq      $-32, %rsp
-        subq      $96, %rsp
-        lea       _dbT+8+__svml_dsinh_data_internal(%rip), %r8
-        vmovupd   _dbShifter+__svml_dsinh_data_internal(%rip), %ymm12
-
-/*
- *  Load argument
- * dM = x*2^K/log(2) + RShifter
- */
-        vmovupd   _dbInvLn2+__svml_dsinh_data_internal(%rip), %ymm5
-        vmovupd   _dbLn2hi+__svml_dsinh_data_internal(%rip), %ymm13
-        vmovapd   %ymm0, %ymm8
-
-/*
- * VLOAD_CONST( D, dPC[0],         TAB._dPC1 );
- *  Abs argument
- */
-        vandpd    _dSign+__svml_dsinh_data_internal(%rip), %ymm8, %ymm7
-        vxorpd    %ymm8, %ymm7, %ymm6
-        vfmadd213pd %ymm12, %ymm6, %ymm5
-
-/*
- *  R
- * dN = dM - RShifter
- */
-        vsubpd    %ymm12, %ymm5, %ymm3
-
-/*
- *  Index and lookup
- * j
- */
-        vandps    _lIndexMask+__svml_dsinh_data_internal(%rip), %ymm5, %ymm4
-
-/*
- * Check for overflow\underflow
- *
- */
-        vextractf128 $1, %ymm6, %xmm9
-        vshufps   $221, %xmm9, %xmm6, %xmm10
-
-/* dR = dX - dN*Log2_hi/2^K */
-        vfnmadd231pd %ymm13, %ymm3, %ymm6
-        vpcmpgtd  _iDomainRange+__svml_dsinh_data_internal(%rip), %xmm10, %xmm11
-        vmovmskps %xmm11, %eax
-
-/* dR = (dX - dN*Log2_hi/2^K) - dN*Log2_lo/2^K */
-        vfnmadd231pd _dbLn2lo+__svml_dsinh_data_internal(%rip), %ymm3, %ymm6
-        vextractf128 $1, %ymm4, %xmm0
-        vmovd     %xmm4, %edx
-        vmovd     %xmm0, %esi
-        shll      $4, %edx
-        vpextrd   $2, %xmm4, %ecx
-
-/* split j and N */
-        vxorps    %ymm4, %ymm5, %ymm3
-        shll      $4, %esi
-        vpextrd   $2, %xmm0, %edi
-        shll      $4, %ecx
-
-/*
- *  G1,G2,G3: dTdif,dTn * 2^N,2^(-N)
- * lM now is an EXP(2^N)
- */
-        vpsllq    $45, %ymm3, %ymm4
-        vmovq     (%rdx,%r8), %xmm14
-        vmovq     (%rsi,%r8), %xmm1
-        vmovhpd   (%rcx,%r8), %xmm14, %xmm15
-        shll      $4, %edi
-        vmovhpd   (%rdi,%r8), %xmm1, %xmm2
-
-/* dR2 = dR^2 */
-        vmulpd    %ymm6, %ymm6, %ymm1
-        vmovq     -8(%rdx,%r8), %xmm9
-        vmovq     -8(%rsi,%r8), %xmm11
-        vmovhpd   -8(%rcx,%r8), %xmm9, %xmm10
-        vmovhpd   -8(%rdi,%r8), %xmm11, %xmm12
-        vinsertf128 $1, %xmm2, %ymm15, %ymm2
-
-/*  */
-        vpaddq    %ymm4, %ymm2, %ymm5
-
-/*  */
-        vpsubq    %ymm4, %ymm2, %ymm14
-
-/* dG3 = dTn*2^N + dTn*2^-N */
-        vaddpd    %ymm14, %ymm5, %ymm2
-
-/* dG2 = dTn*2^N - dTn*2^-N */
-        vsubpd    %ymm14, %ymm5, %ymm14
-
-/*
- * sinh(r) = r*((a1=1)+r^2*(a3+r^2*a5)) = r + r*(r^2*(a3+r^2*a5)) ....
- * dSinh_r = (a3+r^2*a5)
- */
-        vmovupd   _dPC5+__svml_dsinh_data_internal(%rip), %ymm5
-        vfmadd213pd _dPC3+__svml_dsinh_data_internal(%rip), %ymm1, %ymm5
-        vinsertf128 $1, %xmm12, %ymm10, %ymm13
-        vpaddq    %ymm4, %ymm13, %ymm0
-
-/* dSinh_r = r^2*(a3+r^2*a5) */
-        vmulpd    %ymm5, %ymm1, %ymm4
-
-/* dG2 += dG1 */
-        vaddpd    %ymm14, %ymm0, %ymm3
-
-/* dG1 += dG3 */
-        vaddpd    %ymm2, %ymm0, %ymm0
-
-/* dSinh_r = r + r*(r^2*(a3+r^2*a5)) */
-        vfmadd213pd %ymm6, %ymm6, %ymm4
-
-/*
- * poly(r) = (dG2+dG1)+dG3*sinh(dR)+dG1*sinh(dR)+(dG1+dG2)*dR2*(a2 +a4*dR2)
- * dOut = (a2 +a4*dR2)
- */
-        vmovupd   _dPC4+__svml_dsinh_data_internal(%rip), %ymm6
-        vfmadd213pd _dPC2+__svml_dsinh_data_internal(%rip), %ymm1, %ymm6
-
-/* dOut = dR2*(a2 +a4*dR2) */
-        vmulpd    %ymm6, %ymm1, %ymm1
-
-/* dOut = dG2*dR2*(a2 +a4*dR2) */
-        vmulpd    %ymm3, %ymm1, %ymm6
-
-/* dOut = dG1*sinh(dR)+dG2*dR2*(a2 +a4*dR2) */
-        vfmadd213pd %ymm6, %ymm0, %ymm4
-
-/* dOut = dG2 + dG1*sinh(dR)+dG2*dR2*(a2 +a4*dR2) */
-        vaddpd    %ymm4, %ymm3, %ymm5
-
-/*  Ret H  */
-        vorpd     %ymm5, %ymm7, %ymm0
-        testl     %eax, %eax
-
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 eax ymm0 ymm8
-
-/* Restore registers
- * and exit the function
- */
+	pushq	%rbp
+	cfi_def_cfa_offset(16)
+	movq	%rsp, %rbp
+	cfi_def_cfa(6, 16)
+	cfi_offset(6, -16)
+	andq	$-32, %rsp
+	subq	$96, %rsp
+	lea	_dbT+8+__svml_dsinh_data_internal(%rip), %r8
+	vmovupd	_dbShifter+__svml_dsinh_data_internal(%rip), %ymm12
+
+	/*
+	 *  Load argument
+	 * dM = x*2^K/log(2) + RShifter
+	 */
+	vmovupd	_dbInvLn2+__svml_dsinh_data_internal(%rip), %ymm5
+	vmovupd	_dbLn2hi+__svml_dsinh_data_internal(%rip), %ymm13
+	vmovapd	%ymm0, %ymm8
+
+	/*
+	 * VLOAD_CONST( D, dPC[0],         TAB._dPC1 );
+	 *  Abs argument
+	 */
+	vandpd	_dSign+__svml_dsinh_data_internal(%rip), %ymm8, %ymm7
+	vxorpd	%ymm8, %ymm7, %ymm6
+	vfmadd213pd %ymm12, %ymm6, %ymm5
+
+	/*
+	 *  R
+	 * dN = dM - RShifter
+	 */
+	vsubpd	%ymm12, %ymm5, %ymm3
+
+	/*
+	 *  Index and lookup
+	 * j
+	 */
+	vandps	_lIndexMask+__svml_dsinh_data_internal(%rip), %ymm5, %ymm4
+
+	/*
+	 * Check for overflow\underflow
+	 *
+	 */
+	vextractf128 $1, %ymm6, %xmm9
+	vshufps	$221, %xmm9, %xmm6, %xmm10
+
+	/* dR = dX - dN*Log2_hi/2^K */
+	vfnmadd231pd %ymm13, %ymm3, %ymm6
+	vpcmpgtd _iDomainRange+__svml_dsinh_data_internal(%rip), %xmm10, %xmm11
+	vmovmskps %xmm11, %eax
+
+	/* dR = (dX - dN*Log2_hi/2^K) - dN*Log2_lo/2^K */
+	vfnmadd231pd _dbLn2lo+__svml_dsinh_data_internal(%rip), %ymm3, %ymm6
+	vextractf128 $1, %ymm4, %xmm0
+	vmovd	%xmm4, %edx
+	vmovd	%xmm0, %esi
+	shll	$4, %edx
+	vpextrd	$2, %xmm4, %ecx
+
+	/* split j and N */
+	vxorps	%ymm4, %ymm5, %ymm3
+	shll	$4, %esi
+	vpextrd	$2, %xmm0, %edi
+	shll	$4, %ecx
+
+	/*
+	 *  G1, G2, G3: dTdif, dTn * 2^N, 2^(-N)
+	 * lM now is an EXP(2^N)
+	 */
+	vpsllq	$45, %ymm3, %ymm4
+	vmovq	(%rdx, %r8), %xmm14
+	vmovq	(%rsi, %r8), %xmm1
+	vmovhpd	(%rcx, %r8), %xmm14, %xmm15
+	shll	$4, %edi
+	vmovhpd	(%rdi, %r8), %xmm1, %xmm2
+
+	/* dR2 = dR^2 */
+	vmulpd	%ymm6, %ymm6, %ymm1
+	vmovq	-8(%rdx, %r8), %xmm9
+	vmovq	-8(%rsi, %r8), %xmm11
+	vmovhpd	-8(%rcx, %r8), %xmm9, %xmm10
+	vmovhpd	-8(%rdi, %r8), %xmm11, %xmm12
+	vinsertf128 $1, %xmm2, %ymm15, %ymm2
+
+	/*  */
+	vpaddq	%ymm4, %ymm2, %ymm5
+
+	/*  */
+	vpsubq	%ymm4, %ymm2, %ymm14
+
+	/* dG3 = dTn*2^N + dTn*2^-N */
+	vaddpd	%ymm14, %ymm5, %ymm2
+
+	/* dG2 = dTn*2^N - dTn*2^-N */
+	vsubpd	%ymm14, %ymm5, %ymm14
+
+	/*
+	 * sinh(r) = r*((a1=1)+r^2*(a3+r^2*a5)) = r + r*(r^2*(a3+r^2*a5)) ....
+	 * dSinh_r = (a3+r^2*a5)
+	 */
+	vmovupd	_dPC5+__svml_dsinh_data_internal(%rip), %ymm5
+	vfmadd213pd _dPC3+__svml_dsinh_data_internal(%rip), %ymm1, %ymm5
+	vinsertf128 $1, %xmm12, %ymm10, %ymm13
+	vpaddq	%ymm4, %ymm13, %ymm0
+
+	/* dSinh_r = r^2*(a3+r^2*a5) */
+	vmulpd	%ymm5, %ymm1, %ymm4
+
+	/* dG2 += dG1 */
+	vaddpd	%ymm14, %ymm0, %ymm3
+
+	/* dG1 += dG3 */
+	vaddpd	%ymm2, %ymm0, %ymm0
+
+	/* dSinh_r = r + r*(r^2*(a3+r^2*a5)) */
+	vfmadd213pd %ymm6, %ymm6, %ymm4
+
+	/*
+	 * poly(r) = (dG2+dG1)+dG3*sinh(dR)+dG1*sinh(dR)+(dG1+dG2)*dR2*(a2 +a4*dR2)
+	 * dOut = (a2 +a4*dR2)
+	 */
+	vmovupd	_dPC4+__svml_dsinh_data_internal(%rip), %ymm6
+	vfmadd213pd _dPC2+__svml_dsinh_data_internal(%rip), %ymm1, %ymm6
+
+	/* dOut = dR2*(a2 +a4*dR2) */
+	vmulpd	%ymm6, %ymm1, %ymm1
+
+	/* dOut = dG2*dR2*(a2 +a4*dR2) */
+	vmulpd	%ymm3, %ymm1, %ymm6
+
+	/* dOut = dG1*sinh(dR)+dG2*dR2*(a2 +a4*dR2) */
+	vfmadd213pd %ymm6, %ymm0, %ymm4
+
+	/* dOut = dG2 + dG1*sinh(dR)+dG2*dR2*(a2 +a4*dR2) */
+	vaddpd	%ymm4, %ymm3, %ymm5
+
+	/*  Ret H  */
+	vorpd	%ymm5, %ymm7, %ymm0
+	testl	%eax, %eax
+
+	/* Go to special inputs processing branch */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	# LOE rbx r12 r13 r14 r15 eax ymm0 ymm8
+
+	/* 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)
-
-/* Branch to process
- * special inputs
- */
+	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
+	 */
 
 L(SPECIAL_VALUES_BRANCH):
-        vmovupd   %ymm8, 32(%rsp)
-        vmovupd   %ymm0, 64(%rsp)
-                                # LOE rbx r12 r13 r14 r15 eax ymm0
-
-        xorl      %edx, %edx
-                                # 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: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
-        movl      %edx, %r12d
-        movq      %r13, 8(%rsp)
-        /*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
-        movl      %eax, %r13d
-        movq      %r14, (%rsp)
-        /*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r15 r12d r13d
-
-/* Range mask
- * bits check
- */
+	vmovupd	%ymm8, 32(%rsp)
+	vmovupd	%ymm0, 64(%rsp)
+	# LOE rbx r12 r13 r14 r15 eax ymm0
+
+	xorl	%edx, %edx
+	# 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: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
+	movl	%edx, %r12d
+	movq	%r13, 8(%rsp)
+	/*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
+	movl	%eax, %r13d
+	movq	%r14, (%rsp)
+	/*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r15 r12d r13d
+
+	/* 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      $4, %r12d
-
-/* 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)
-        vmovupd   64(%rsp), %ymm0
-
-/* Go to exit */
-        jmp       L(EXIT)
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
-        /*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
-        /*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r12 r13 r14 r15 ymm0
-
-/* Scalar math fucntion call
- * to process special input
- */
+	incl	%r12d
+	cmpl	$4, %r12d
+
+	/* 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)
+	vmovupd	64(%rsp), %ymm0
+
+	/* Go to exit */
+	jmp	L(EXIT)
+	/*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
+	/*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
+	/*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r12 r13 r14 r15 ymm0
+
+	/* Scalar math fucntion call
+	 * to process special input
+	 */
 
 L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movsd     32(%rsp,%r14,8), %xmm0
-        call      sinh@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
+	movl	%r12d, %r14d
+	movsd	32(%rsp, %r14, 8), %xmm0
+	call	sinh@PLT
+	# LOE rbx r14 r15 r12d r13d xmm0
 
-        movsd     %xmm0, 64(%rsp,%r14,8)
+	movsd	%xmm0, 64(%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(_ZGVdN4v_sinh_avx2)
 
-        .section .rodata, "a"
-        .align 32
+	.section .rodata, "a"
+	.align	32
 
 #ifdef __svml_dsinh_data_internal_typedef
 typedef unsigned int VUINT32;
-typedef struct
-{
-        __declspec(align(32)) VUINT32 _dbInvLn2[4][2];
-        __declspec(align(32)) VUINT32 _dbLn2hi[4][2];
-        __declspec(align(32)) VUINT32 _dbLn2lo[4][2];
-        __declspec(align(32)) VUINT32 _dSign[4][2];                //0x8000000000000000
-        __declspec(align(32)) VUINT32 _dbT[(1<<7)][2][2]; //precalc poly coeff
-        __declspec(align(32)) VUINT32 _dbShifter[4][2];
-        __declspec(align(32)) VUINT32 _iDomainRange[8][1];
-        __declspec(align(32)) VUINT32 _dPC2[4][2];
-        __declspec(align(32)) VUINT32 _dPC3[4][2];
-        __declspec(align(32)) VUINT32 _dPC4[4][2];
-        __declspec(align(32)) VUINT32 _dPC5[4][2];
-        __declspec(align(32)) VUINT32 _lIndexMask[4][2];
+typedef struct {
+	__declspec(align(32)) VUINT32 _dbInvLn2[4][2];
+	__declspec(align(32)) VUINT32 _dbLn2hi[4][2];
+	__declspec(align(32)) VUINT32 _dbLn2lo[4][2];
+	__declspec(align(32)) VUINT32 _dSign[4][2]; // 0x8000000000000000
+	__declspec(align(32)) VUINT32 _dbT[(1<<7)][2][2]; // precalc poly coeff
+	__declspec(align(32)) VUINT32 _dbShifter[4][2];
+	__declspec(align(32)) VUINT32 _iDomainRange[8][1];
+	__declspec(align(32)) VUINT32 _dPC2[4][2];
+	__declspec(align(32)) VUINT32 _dPC3[4][2];
+	__declspec(align(32)) VUINT32 _dPC4[4][2];
+	__declspec(align(32)) VUINT32 _dPC5[4][2];
+	__declspec(align(32)) VUINT32 _lIndexMask[4][2];
 } __svml_dsinh_data_internal;
 #endif
 __svml_dsinh_data_internal:
-        .quad 0x3FF71547652B82FE, 0x3FF71547652B82FE, 0x3FF71547652B82FE, 0x3FF71547652B82FE /* _dbInvLn2 = 1/log(2) */
-        .align 32
-        .quad 0x3FE62E42FEFA0000, 0x3FE62E42FEFA0000, 0x3FE62E42FEFA0000, 0x3FE62E42FEFA0000 /* _dbLn2hi  = log(2) hi*/
-        .align 32
-        .quad 0x3D7CF79ABC9E3B3A, 0x3D7CF79ABC9E3B3A, 0x3D7CF79ABC9E3B3A, 0x3D7CF79ABC9E3B3A /* _dbLn2lo  = log(2) lo*/
-        .align 32
-        .quad 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000 /* _dSign */
-        //_dbT
-        .align 32
-        .quad 0x0000000000000000, 0x3FE0000000000000  //2^( 0 /128-1) - 2^(- 0 /128-1), 2^(- 0 /128-1)
-        .quad 0x3F762E4A19BD1E74, 0x3FDFD3C22B8F71F1  //2^( 1 /128-1) - 2^(- 1 /128-1), 2^(- 1 /128-1)
-        .quad 0x3F862E5F6A0DFD36, 0x3FDFA7C1819E90D8  //2^( 2 /128-1) - 2^(- 2 /128-1), 2^(- 2 /128-1)
-        .quad 0x3F90A2E234040F5F, 0x3FDF7BFDAD9CBE14  //2^( 3 /128-1) - 2^(- 3 /128-1), 2^(- 3 /128-1)
-        .quad 0x3F962EB4ABCC5A81, 0x3FDF50765B6E4540  //2^( 4 /128-1) - 2^(- 4 /128-1), 2^(- 4 /128-1)
-        .quad 0x3F9BBAB1C5033244, 0x3FDF252B376BBA97  //2^( 5 /128-1) - 2^(- 5 /128-1), 2^(- 5 /128-1)
-        .quad 0x3FA0A372144EEB45, 0x3FDEFA1BEE615A27  //2^( 6 /128-1) - 2^(- 6 /128-1), 2^(- 6 /128-1)
-        .quad 0x3FA369AB3FFBF8B0, 0x3FDECF482D8E67F1  //2^( 7 /128-1) - 2^(- 7 /128-1), 2^(- 7 /128-1)
-        .quad 0x3FA63009BA740A2A, 0x3FDEA4AFA2A490DA  //2^( 8 /128-1) - 2^(- 8 /128-1), 2^(- 8 /128-1)
-        .quad 0x3FA8F692D8EA1B5A, 0x3FDE7A51FBC74C83  //2^( 9 /128-1) - 2^(- 9 /128-1), 2^(- 9 /128-1)
-        .quad 0x3FABBD4BF0E31A6F, 0x3FDE502EE78B3FF6  //2^( 10 /128-1) - 2^(- 10 /128-1), 2^(- 10 /128-1)
-        .quad 0x3FAE843A5840286A, 0x3FDE264614F5A129  //2^( 11 /128-1) - 2^(- 11 /128-1), 2^(- 11 /128-1)
-        .quad 0x3FB0A5B1B2A46D0A, 0x3FDDFC97337B9B5F  //2^( 12 /128-1) - 2^(- 12 /128-1), 2^(- 12 /128-1)
-        .quad 0x3FB20966375ABCDF, 0x3FDDD321F301B460  //2^( 13 /128-1) - 2^(- 13 /128-1), 2^(- 13 /128-1)
-        .quad 0x3FB36D3D65DCA4E8, 0x3FDDA9E603DB3285  //2^( 14 /128-1) - 2^(- 14 /128-1), 2^(- 14 /128-1)
-        .quad 0x3FB4D139EA06642A, 0x3FDD80E316C98398  //2^( 15 /128-1) - 2^(- 15 /128-1), 2^(- 15 /128-1)
-        .quad 0x3FB6355E6FFBF9BA, 0x3FDD5818DCFBA487  //2^( 16 /128-1) - 2^(- 16 /128-1), 2^(- 16 /128-1)
-        .quad 0x3FB799ADA42E4788, 0x3FDD2F87080D89F2  //2^( 17 /128-1) - 2^(- 17 /128-1), 2^(- 17 /128-1)
-        .quad 0x3FB8FE2A336035BC, 0x3FDD072D4A07897C  //2^( 18 /128-1) - 2^(- 18 /128-1), 2^(- 18 /128-1)
-        .quad 0x3FBA62D6CAABD6B6, 0x3FDCDF0B555DC3FA  //2^( 19 /128-1) - 2^(- 19 /128-1), 2^(- 19 /128-1)
-        .quad 0x3FBBC7B617878BAF, 0x3FDCB720DCEF9069  //2^( 20 /128-1) - 2^(- 20 /128-1), 2^(- 20 /128-1)
-        .quad 0x3FBD2CCAC7CB2A11, 0x3FDC8F6D9406E7B5  //2^( 21 /128-1) - 2^(- 21 /128-1), 2^(- 21 /128-1)
-        .quad 0x3FBE921789B52185, 0x3FDC67F12E57D14B  //2^( 22 /128-1) - 2^(- 22 /128-1), 2^(- 22 /128-1)
-        .quad 0x3FBFF79F0BEFA2C7, 0x3FDC40AB5FFFD07A  //2^( 23 /128-1) - 2^(- 23 /128-1), 2^(- 23 /128-1)
-        .quad 0x3FC0AEB1FECAE3A9, 0x3FDC199BDD85529C  //2^( 24 /128-1) - 2^(- 24 /128-1), 2^(- 24 /128-1)
-        .quad 0x3FC161B4871C5CEC, 0x3FDBF2C25BD71E09  //2^( 25 /128-1) - 2^(- 25 /128-1), 2^(- 25 /128-1)
-        .quad 0x3FC214D876F26FD0, 0x3FDBCC1E904BC1D2  //2^( 26 /128-1) - 2^(- 26 /128-1), 2^(- 26 /128-1)
-        .quad 0x3FC2C81F2693816F, 0x3FDBA5B030A1064A  //2^( 27 /128-1) - 2^(- 27 /128-1), 2^(- 27 /128-1)
-        .quad 0x3FC37B89EE88BEF7, 0x3FDB7F76F2FB5E47  //2^( 28 /128-1) - 2^(- 28 /128-1), 2^(- 28 /128-1)
-        .quad 0x3FC42F1A27A0B3CD, 0x3FDB59728DE5593A  //2^( 29 /128-1) - 2^(- 29 /128-1), 2^(- 29 /128-1)
-        .quad 0x3FC4E2D12AF1E037, 0x3FDB33A2B84F15FB  //2^( 30 /128-1) - 2^(- 30 /128-1), 2^(- 30 /128-1)
-        .quad 0x3FC596B051DD508D, 0x3FDB0E07298DB666  //2^( 31 /128-1) - 2^(- 31 /128-1), 2^(- 31 /128-1)
-        .quad 0x3FC64AB8F61134FA, 0x3FDAE89F995AD3AD  //2^( 32 /128-1) - 2^(- 32 /128-1), 2^(- 32 /128-1)
-        .quad 0x3FC6FEEC718B79D1, 0x3FDAC36BBFD3F37A  //2^( 33 /128-1) - 2^(- 33 /128-1), 2^(- 33 /128-1)
-        .quad 0x3FC7B34C1E9C607F, 0x3FDA9E6B5579FDBF  //2^( 34 /128-1) - 2^(- 34 /128-1), 2^(- 34 /128-1)
-        .quad 0x3FC867D957E91912, 0x3FDA799E1330B358  //2^( 35 /128-1) - 2^(- 35 /128-1), 2^(- 35 /128-1)
-        .quad 0x3FC91C95786E5C72, 0x3FDA5503B23E255D  //2^( 36 /128-1) - 2^(- 36 /128-1), 2^(- 36 /128-1)
-        .quad 0x3FC9D181DB83072F, 0x3FDA309BEC4A2D33  //2^( 37 /128-1) - 2^(- 37 /128-1), 2^(- 37 /128-1)
-        .quad 0x3FCA869FDCDAB512, 0x3FDA0C667B5DE565  //2^( 38 /128-1) - 2^(- 38 /128-1), 2^(- 38 /128-1)
-        .quad 0x3FCB3BF0D8885D4C, 0x3FD9E86319E32323  //2^( 39 /128-1) - 2^(- 39 /128-1), 2^(- 39 /128-1)
-        .quad 0x3FCBF1762B00EF69, 0x3FD9C49182A3F090  //2^( 40 /128-1) - 2^(- 40 /128-1), 2^(- 40 /128-1)
-        .quad 0x3FCCA731311DF0FB, 0x3FD9A0F170CA07BA  //2^( 41 /128-1) - 2^(- 41 /128-1), 2^(- 41 /128-1)
-        .quad 0x3FCD5D2348201C09, 0x3FD97D829FDE4E50  //2^( 42 /128-1) - 2^(- 42 /128-1), 2^(- 42 /128-1)
-        .quad 0x3FCE134DCDB1FE3E, 0x3FD95A44CBC8520F  //2^( 43 /128-1) - 2^(- 43 /128-1), 2^(- 43 /128-1)
-        .quad 0x3FCEC9B21FEA98EA, 0x3FD93737B0CDC5E5  //2^( 44 /128-1) - 2^(- 44 /128-1), 2^(- 44 /128-1)
-        .quad 0x3FCF80519D5001D3, 0x3FD9145B0B91FFC6  //2^( 45 /128-1) - 2^(- 45 /128-1), 2^(- 45 /128-1)
-        .quad 0x3FD01B96D26D026A, 0x3FD8F1AE99157736  //2^( 46 /128-1) - 2^(- 46 /128-1), 2^(- 46 /128-1)
-        .quad 0x3FD07723CAFA6331, 0x3FD8CF3216B5448C  //2^( 47 /128-1) - 2^(- 47 /128-1), 2^(- 47 /128-1)
-        .quad 0x3FD0D2D06841B373, 0x3FD8ACE5422AA0DB  //2^( 48 /128-1) - 2^(- 48 /128-1), 2^(- 48 /128-1)
-        .quad 0x3FD12E9D5A715381, 0x3FD88AC7D98A6699  //2^( 49 /128-1) - 2^(- 49 /128-1), 2^(- 49 /128-1)
-        .quad 0x3FD18A8B51F5C661, 0x3FD868D99B4492ED  //2^( 50 /128-1) - 2^(- 50 /128-1), 2^(- 50 /128-1)
-        .quad 0x3FD1E69AFF7B04D7, 0x3FD8471A4623C7AD  //2^( 51 /128-1) - 2^(- 51 /128-1), 2^(- 51 /128-1)
-        .quad 0x3FD242CD13EDD0F1, 0x3FD82589994CCE13  //2^( 52 /128-1) - 2^(- 52 /128-1), 2^(- 52 /128-1)
-        .quad 0x3FD29F22407D0A0C, 0x3FD80427543E1A12  //2^( 53 /128-1) - 2^(- 53 /128-1), 2^(- 53 /128-1)
-        .quad 0x3FD2FB9B369B0153, 0x3FD7E2F336CF4E62  //2^( 54 /128-1) - 2^(- 54 /128-1), 2^(- 54 /128-1)
-        .quad 0x3FD35838A7FECEC8, 0x3FD7C1ED0130C132  //2^( 55 /128-1) - 2^(- 55 /128-1), 2^(- 55 /128-1)
-        .quad 0x3FD3B4FB46A5A6CC, 0x3FD7A11473EB0187  //2^( 56 /128-1) - 2^(- 56 /128-1), 2^(- 56 /128-1)
-        .quad 0x3FD411E3C4D4302F, 0x3FD780694FDE5D3F  //2^( 57 /128-1) - 2^(- 57 /128-1), 2^(- 57 /128-1)
-        .quad 0x3FD46EF2D517DAC8, 0x3FD75FEB564267C9  //2^( 58 /128-1) - 2^(- 58 /128-1), 2^(- 58 /128-1)
-        .quad 0x3FD4CC292A48369E, 0x3FD73F9A48A58174  //2^( 59 /128-1) - 2^(- 59 /128-1), 2^(- 59 /128-1)
-        .quad 0x3FD5298777884B96, 0x3FD71F75E8EC5F74  //2^( 60 /128-1) - 2^(- 60 /128-1), 2^(- 60 /128-1)
-        .quad 0x3FD5870E7047F1BC, 0x3FD6FF7DF9519484  //2^( 61 /128-1) - 2^(- 61 /128-1), 2^(- 61 /128-1)
-        .quad 0x3FD5E4BEC8452A1A, 0x3FD6DFB23C651A2F  //2^( 62 /128-1) - 2^(- 62 /128-1), 2^(- 62 /128-1)
-        .quad 0x3FD64299338D7827, 0x3FD6C012750BDABF  //2^( 63 /128-1) - 2^(- 63 /128-1), 2^(- 63 /128-1)
-        .quad 0x3FD6A09E667F3BCD, 0x3FD6A09E667F3BCD  //2^( 64 /128-1) - 2^(- 64 /128-1), 2^(- 64 /128-1)
-        .quad 0x3FD6FECF15CB0C0B, 0x3FD68155D44CA973  //2^( 65 /128-1) - 2^(- 65 /128-1), 2^(- 65 /128-1)
-        .quad 0x3FD75D2BF6751239, 0x3FD6623882552225  //2^( 66 /128-1) - 2^(- 66 /128-1), 2^(- 66 /128-1)
-        .quad 0x3FD7BBB5BDD665E8, 0x3FD6434634CCC320  //2^( 67 /128-1) - 2^(- 67 /128-1), 2^(- 67 /128-1)
-        .quad 0x3FD81A6D219E6963, 0x3FD6247EB03A5585  //2^( 68 /128-1) - 2^(- 68 /128-1), 2^(- 68 /128-1)
-        .quad 0x3FD87952D7D426DF, 0x3FD605E1B976DC09  //2^( 69 /128-1) - 2^(- 69 /128-1), 2^(- 69 /128-1)
-        .quad 0x3FD8D86796D7AE49, 0x3FD5E76F15AD2148  //2^( 70 /128-1) - 2^(- 70 /128-1), 2^(- 70 /128-1)
-        .quad 0x3FD937AC156373C8, 0x3FD5C9268A5946B7  //2^( 71 /128-1) - 2^(- 71 /128-1