x86_64: Fix svml_s_atan2f8_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, 296 insertions, 297 deletions

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_atan2f8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_atan2f8_core_avx2.S
index 1488945943..29ebbb6db2 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_atan2f8_core_avx2.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_atan2f8_core_avx2.S
@@ -30,333 +30,332 @@
 
 /* Offsets for data table __svml_satan2_data_internal
  */
-#define sZERO                         	0
-#define sSIGN_MASK                    	32
-#define sABS_MASK                     	64
-#define sPIO2                         	96
-#define sPI                           	128
-#define sPC8                          	160
-#define sPC7                          	192
-#define sPC6                          	224
-#define sPC5                          	256
-#define sPC4                          	288
-#define sPC3                          	320
-#define sPC2                          	352
-#define sPC1                          	384
-#define sPC0                          	416
-#define iCHK_WORK_SUB                 	448
-#define iCHK_WORK_CMP                 	480
+#define sZERO				0
+#define sSIGN_MASK			32
+#define sABS_MASK			64
+#define sPIO2				96
+#define sPI				128
+#define sPC8				160
+#define sPC7				192
+#define sPC6				224
+#define sPC5				256
+#define sPC4				288
+#define sPC3				320
+#define sPC2				352
+#define sPC1				384
+#define sPC0				416
+#define iCHK_WORK_SUB			448
+#define iCHK_WORK_CMP			480
 
 #include <sysdep.h>
 
-        .text
-	.section .text.avx2,"ax",@progbits
+	.section .text.avx2, "ax", @progbits
 ENTRY(_ZGVdN8vv_atan2f_avx2)
-        pushq     %rbp
-        cfi_def_cfa_offset(16)
-        movq      %rsp, %rbp
-        cfi_def_cfa(6, 16)
-        cfi_offset(6, -16)
-        andq      $-32, %rsp
-        subq      $128, %rsp
-        xorl      %edx, %edx
-
-/*
- * #define NO_VECTOR_ZERO_ATAN2_ARGS
- *  Declarations
- * Variables
- * Constants
- *  The end of declarations
- *  Implementation
- * Arguments signs
- */
-        vmovups   sABS_MASK+__svml_satan2_data_internal(%rip), %ymm2
-
-/* Testing on working interval. */
-        vmovups   iCHK_WORK_SUB+__svml_satan2_data_internal(%rip), %ymm15
-        vmovups   iCHK_WORK_CMP+__svml_satan2_data_internal(%rip), %ymm9
-
-/* if x<0, sPI = Pi, else sPI =0 */
-        vmovups   __svml_satan2_data_internal(%rip), %ymm5
-        vmovaps   %ymm1, %ymm7
-        vandps    %ymm2, %ymm7, %ymm13
-        vandps    %ymm2, %ymm0, %ymm12
-        vcmplt_oqps %ymm13, %ymm12, %ymm4
-        vcmple_oqps %ymm5, %ymm7, %ymm6
-        vpsubd    %ymm15, %ymm13, %ymm10
-        vpsubd    %ymm15, %ymm12, %ymm8
-
-/*
- * 1) If y<x then a= y, b=x, PIO2=0
- * 2) If y>x then a=-x, b=y, PIO2=Pi/2
- */
-        vorps     sSIGN_MASK+__svml_satan2_data_internal(%rip), %ymm13, %ymm3
-        vblendvps %ymm4, %ymm12, %ymm3, %ymm14
-        vblendvps %ymm4, %ymm13, %ymm12, %ymm3
-
-/* Division a/b. */
-        vdivps    %ymm3, %ymm14, %ymm11
-        vpcmpgtd  %ymm9, %ymm10, %ymm14
-        vpcmpeqd  %ymm9, %ymm10, %ymm15
-        vpor      %ymm15, %ymm14, %ymm10
-        vmovups   sPC7+__svml_satan2_data_internal(%rip), %ymm15
-        vpcmpgtd  %ymm9, %ymm8, %ymm14
-        vpcmpeqd  %ymm9, %ymm8, %ymm8
-        vpor      %ymm8, %ymm14, %ymm9
-        vmovups   sPC8+__svml_satan2_data_internal(%rip), %ymm14
-        vpor      %ymm9, %ymm10, %ymm10
-
-/* Polynomial. */
-        vmulps    %ymm11, %ymm11, %ymm9
-        vmulps    %ymm9, %ymm9, %ymm8
-        vfmadd213ps sPC6+__svml_satan2_data_internal(%rip), %ymm8, %ymm14
-        vfmadd213ps sPC5+__svml_satan2_data_internal(%rip), %ymm8, %ymm15
-        vfmadd213ps sPC4+__svml_satan2_data_internal(%rip), %ymm8, %ymm14
-        vfmadd213ps sPC3+__svml_satan2_data_internal(%rip), %ymm8, %ymm15
-        vfmadd213ps sPC2+__svml_satan2_data_internal(%rip), %ymm8, %ymm14
-        vfmadd213ps sPC1+__svml_satan2_data_internal(%rip), %ymm8, %ymm15
-        vfmadd213ps sPC0+__svml_satan2_data_internal(%rip), %ymm8, %ymm14
-        vfmadd213ps %ymm14, %ymm9, %ymm15
-        vandnps   sPIO2+__svml_satan2_data_internal(%rip), %ymm4, %ymm4
-
-/* Reconstruction. */
-        vfmadd213ps %ymm4, %ymm11, %ymm15
-        vxorps    %ymm13, %ymm7, %ymm1
-        vandps    sPI+__svml_satan2_data_internal(%rip), %ymm6, %ymm6
-        vorps     %ymm1, %ymm15, %ymm11
-        vaddps    %ymm11, %ymm6, %ymm8
-        vmovmskps %ymm10, %eax
-        vxorps    %ymm12, %ymm0, %ymm2
-        vorps     %ymm2, %ymm8, %ymm9
-
-/*  Special branch for fast (vector) processing of zero arguments  */
-        testl     %eax, %eax
-
-/* Go to auxilary branch */
-        jne       L(AUX_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 edx ymm0 ymm1 ymm2 ymm3 ymm4 ymm5 ymm6 ymm7 ymm9 ymm10 ymm12 ymm13
-
-/* Return from auxilary branch
- * for out of main path inputs
- */
+	pushq	%rbp
+	cfi_def_cfa_offset(16)
+	movq	%rsp, %rbp
+	cfi_def_cfa(6, 16)
+	cfi_offset(6, -16)
+	andq	$-32, %rsp
+	subq	$128, %rsp
+	xorl	%edx, %edx
+
+	/*
+	 * #define NO_VECTOR_ZERO_ATAN2_ARGS
+	 *  Declarations
+	 * Variables
+	 * Constants
+	 *  The end of declarations
+	 *  Implementation
+	 * Arguments signs
+	 */
+	vmovups	sABS_MASK+__svml_satan2_data_internal(%rip), %ymm2
+
+	/* Testing on working interval. */
+	vmovups	iCHK_WORK_SUB+__svml_satan2_data_internal(%rip), %ymm15
+	vmovups	iCHK_WORK_CMP+__svml_satan2_data_internal(%rip), %ymm9
+
+	/* if x<0, sPI = Pi, else sPI =0 */
+	vmovups	__svml_satan2_data_internal(%rip), %ymm5
+	vmovaps	%ymm1, %ymm7
+	vandps	%ymm2, %ymm7, %ymm13
+	vandps	%ymm2, %ymm0, %ymm12
+	vcmplt_oqps %ymm13, %ymm12, %ymm4
+	vcmple_oqps %ymm5, %ymm7, %ymm6
+	vpsubd	%ymm15, %ymm13, %ymm10
+	vpsubd	%ymm15, %ymm12, %ymm8
+
+	/*
+	 * 1) If y<x then a= y, b=x, PIO2=0
+	 * 2) If y>x then a=-x, b=y, PIO2=Pi/2
+	 */
+	vorps	sSIGN_MASK+__svml_satan2_data_internal(%rip), %ymm13, %ymm3
+	vblendvps %ymm4, %ymm12, %ymm3, %ymm14
+	vblendvps %ymm4, %ymm13, %ymm12, %ymm3
+
+	/* Division a/b. */
+	vdivps	%ymm3, %ymm14, %ymm11
+	vpcmpgtd %ymm9, %ymm10, %ymm14
+	vpcmpeqd %ymm9, %ymm10, %ymm15
+	vpor	%ymm15, %ymm14, %ymm10
+	vmovups	sPC7+__svml_satan2_data_internal(%rip), %ymm15
+	vpcmpgtd %ymm9, %ymm8, %ymm14
+	vpcmpeqd %ymm9, %ymm8, %ymm8
+	vpor	%ymm8, %ymm14, %ymm9
+	vmovups	sPC8+__svml_satan2_data_internal(%rip), %ymm14
+	vpor	%ymm9, %ymm10, %ymm10
+
+	/* Polynomial. */
+	vmulps	%ymm11, %ymm11, %ymm9
+	vmulps	%ymm9, %ymm9, %ymm8
+	vfmadd213ps sPC6+__svml_satan2_data_internal(%rip), %ymm8, %ymm14
+	vfmadd213ps sPC5+__svml_satan2_data_internal(%rip), %ymm8, %ymm15
+	vfmadd213ps sPC4+__svml_satan2_data_internal(%rip), %ymm8, %ymm14
+	vfmadd213ps sPC3+__svml_satan2_data_internal(%rip), %ymm8, %ymm15
+	vfmadd213ps sPC2+__svml_satan2_data_internal(%rip), %ymm8, %ymm14
+	vfmadd213ps sPC1+__svml_satan2_data_internal(%rip), %ymm8, %ymm15
+	vfmadd213ps sPC0+__svml_satan2_data_internal(%rip), %ymm8, %ymm14
+	vfmadd213ps %ymm14, %ymm9, %ymm15
+	vandnps	sPIO2+__svml_satan2_data_internal(%rip), %ymm4, %ymm4
+
+	/* Reconstruction. */
+	vfmadd213ps %ymm4, %ymm11, %ymm15
+	vxorps	%ymm13, %ymm7, %ymm1
+	vandps	sPI+__svml_satan2_data_internal(%rip), %ymm6, %ymm6
+	vorps	%ymm1, %ymm15, %ymm11
+	vaddps	%ymm11, %ymm6, %ymm8
+	vmovmskps %ymm10, %eax
+	vxorps	%ymm12, %ymm0, %ymm2
+	vorps	%ymm2, %ymm8, %ymm9
+
+	/*  Special branch for fast (vector) processing of zero arguments  */
+	testl	%eax, %eax
+
+	/* Go to auxilary branch */
+	jne	L(AUX_BRANCH)
+	# LOE rbx r12 r13 r14 r15 edx ymm0 ymm1 ymm2 ymm3 ymm4 ymm5 ymm6 ymm7 ymm9 ymm10 ymm12 ymm13
+
+	/* Return from auxilary branch
+	 * for out of main path inputs
+	 */
 
 L(AUX_BRANCH_RETURN):
-/*
- *  Special branch for fast (vector) processing of zero arguments
- *  The end of implementation
- */
-        testl     %edx, %edx
+	/*
+	 *  Special branch for fast (vector) processing of zero arguments
+	 *  The end of implementation
+	 */
+	testl	%edx, %edx
 
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 edx ymm0 ymm7 ymm9
+	/* Go to special inputs processing branch */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	# LOE rbx r12 r13 r14 r15 edx ymm0 ymm7 ymm9
 
-/* Restore registers
- * and exit the function
- */
+	/* Restore registers
+	 * and exit the function
+	 */
 
 L(EXIT):
-        vmovaps   %ymm9, %ymm0
-        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
- */
+	vmovaps	%ymm9, %ymm0
+	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):
-        vmovups   %ymm0, 32(%rsp)
-        vmovups   %ymm7, 64(%rsp)
-        vmovups   %ymm9, 96(%rsp)
-                                # LOE rbx r12 r13 r14 r15 edx ymm9
-
-        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: -32; DW_OP_and; DW_OP_const4s: -112; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x90, 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: -32; DW_OP_and; DW_OP_const4s: -120; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x88, 0xff, 0xff, 0xff, 0x22
-        movl      %edx, %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: -128; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x80, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r15 r12d r13d
-
-/* Range mask
- * bits check
- */
+	vmovups	%ymm0, 32(%rsp)
+	vmovups	%ymm7, 64(%rsp)
+	vmovups	%ymm9, 96(%rsp)
+	# LOE rbx r12 r13 r14 r15 edx ymm9
+
+	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: -32; DW_OP_and; DW_OP_const4s: -112; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x90, 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: -32; DW_OP_and; DW_OP_const4s: -120; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x88, 0xff, 0xff, 0xff, 0x22
+	movl	%edx, %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: -128; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x80, 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      $8, %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)
-        vmovups   96(%rsp), %ymm9
-
-/* 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: -112; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x90, 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: -120; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x88, 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: -128; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x80, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r12 r13 r14 r15 ymm9
-
-/* Scalar math fucntion call
- * to process special input
- */
+	incl	%r12d
+	cmpl	$8, %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)
+	vmovups	96(%rsp), %ymm9
+
+	/* 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: -112; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x90, 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: -120; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x88, 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: -128; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x80, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r12 r13 r14 r15 ymm9
+
+	/* Scalar math fucntion call
+	 * to process special input
+	 */
 
 L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movss     32(%rsp,%r14,4), %xmm0
-        movss     64(%rsp,%r14,4), %xmm1
-        call      atan2f@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
-
-        movss     %xmm0, 96(%rsp,%r14,4)
-
-/* Process special inputs in loop */
-        jmp       L(SPECIAL_VALUES_LOOP)
-        cfi_restore(12)
-        cfi_restore(13)
-        cfi_restore(14)
-                                # LOE rbx r15 r12d r13d
-
-/* Auxilary branch
- * for out of main path inputs
- */
-
-L(AUX_BRANCH):
-/* Check if at least on of Y or Y is zero: iAXAYZERO */
-        vpcmpeqd  %ymm5, %ymm13, %ymm13
-        vpcmpeqd  %ymm5, %ymm12, %ymm12
-
-/* Check if both X & Y are not NaNs:  iXYnotNAN */
-        vcmpordps %ymm7, %ymm7, %ymm11
-        vcmpordps %ymm0, %ymm0, %ymm14
-
-/*
- *  Path for zero arguments (at least one of both)
- * Check if both args are zeros (den. is zero)
- */
-        vcmpeqps  %ymm5, %ymm3, %ymm3
-        vpor      %ymm12, %ymm13, %ymm15
-
-/* Set sPIO2 to zero if den. is zero */
-        vblendvps %ymm3, %ymm5, %ymm4, %ymm4
-        vandps    %ymm14, %ymm11, %ymm8
+	movl	%r12d, %r14d
+	movss	32(%rsp, %r14, 4), %xmm0
+	movss	64(%rsp, %r14, 4), %xmm1
+	call	atan2f@PLT
+	# LOE rbx r14 r15 r12d r13d xmm0
 
-/* Check if at least on of Y or Y is zero and not NaN: iAXAYZEROnotNAN */
-        vpand     %ymm8, %ymm15, %ymm8
+	movss	%xmm0, 96(%rsp, %r14, 4)
 
-/* Res = sign(Y)*(X<0)?(PIO2+PI):PIO2 */
-        vpcmpgtd  %ymm7, %ymm5, %ymm5
-        vorps     %ymm1, %ymm4, %ymm1
-        vandps    %ymm6, %ymm5, %ymm6
-        vaddps    %ymm6, %ymm1, %ymm1
+	/* Process special inputs in loop */
+	jmp	L(SPECIAL_VALUES_LOOP)
+	cfi_restore(12)
+	cfi_restore(13)
+	cfi_restore(14)
+	# LOE rbx r15 r12d r13d
 
-/* Exclude from previous callout mask zero (and not NaN) arguments */
-        vpandn    %ymm10, %ymm8, %ymm10
-        vorps     %ymm2, %ymm1, %ymm2
+	/* Auxilary branch
+	 * for out of main path inputs
+	 */
 
-/* Go to callout */
-        vmovmskps %ymm10, %edx
-
-/* Merge results from main and spec path */
-        vblendvps %ymm8, %ymm2, %ymm9, %ymm9
-
-/* Return to main vector processing path */
-        jmp       L(AUX_BRANCH_RETURN)
-                                # LOE rbx r12 r13 r14 r15 edx ymm0 ymm7 ymm9
+L(AUX_BRANCH):
+	/* Check if at least on of Y or Y is zero: iAXAYZERO */
+	vpcmpeqd %ymm5, %ymm13, %ymm13
+	vpcmpeqd %ymm5, %ymm12, %ymm12
+
+	/* Check if both X & Y are not NaNs:  iXYnotNAN */
+	vcmpordps %ymm7, %ymm7, %ymm11
+	vcmpordps %ymm0, %ymm0, %ymm14
+
+	/*
+	 *  Path for zero arguments (at least one of both)
+	 * Check if both args are zeros (den. is zero)
+	 */
+	vcmpeqps %ymm5, %ymm3, %ymm3
+	vpor	%ymm12, %ymm13, %ymm15
+
+	/* Set sPIO2 to zero if den. is zero */
+	vblendvps %ymm3, %ymm5, %ymm4, %ymm4
+	vandps	%ymm14, %ymm11, %ymm8
+
+	/* Check if at least on of Y or Y is zero and not NaN: iAXAYZEROnotNAN */
+	vpand	%ymm8, %ymm15, %ymm8
+
+	/* Res = sign(Y)*(X<0)?(PIO2+PI):PIO2 */
+	vpcmpgtd %ymm7, %ymm5, %ymm5
+	vorps	%ymm1, %ymm4, %ymm1
+	vandps	%ymm6, %ymm5, %ymm6
+	vaddps	%ymm6, %ymm1, %ymm1
+
+	/* Exclude from previous callout mask zero (and not NaN) arguments */
+	vpandn	%ymm10, %ymm8, %ymm10
+	vorps	%ymm2, %ymm1, %ymm2
+
+	/* Go to callout */
+	vmovmskps %ymm10, %edx
+
+	/* Merge results from main and spec path */
+	vblendvps %ymm8, %ymm2, %ymm9, %ymm9
+
+	/* Return to main vector processing path */
+	jmp	L(AUX_BRANCH_RETURN)
+	# LOE rbx r12 r13 r14 r15 edx ymm0 ymm7 ymm9
 END(_ZGVdN8vv_atan2f_avx2)
 
-        .section .rodata, "a"
-        .align 32
+	.section .rodata, "a"
+	.align	32
 
 #ifdef __svml_satan2_data_internal_typedef
 typedef unsigned int VUINT32;
 typedef struct {
-        __declspec(align(32)) VUINT32 sZERO[8][1];
-        __declspec(align(32)) VUINT32 sSIGN_MASK[8][1];
-        __declspec(align(32)) VUINT32 sABS_MASK[8][1];
-        __declspec(align(32)) VUINT32 sPIO2[8][1];
-        __declspec(align(32)) VUINT32 sPI[8][1];
-        __declspec(align(32)) VUINT32 sPC8[8][1];
-        __declspec(align(32)) VUINT32 sPC7[8][1];
-        __declspec(align(32)) VUINT32 sPC6[8][1];
-        __declspec(align(32)) VUINT32 sPC5[8][1];
-        __declspec(align(32)) VUINT32 sPC4[8][1];
-        __declspec(align(32)) VUINT32 sPC3[8][1];
-        __declspec(align(32)) VUINT32 sPC2[8][1];
-        __declspec(align(32)) VUINT32 sPC1[8][1];
-        __declspec(align(32)) VUINT32 sPC0[8][1];
-        __declspec(align(32)) VUINT32 iCHK_WORK_SUB[8][1];
-        __declspec(align(32)) VUINT32 iCHK_WORK_CMP[8][1];
+	__declspec(align(32)) VUINT32 sZERO[8][1];
+	__declspec(align(32)) VUINT32 sSIGN_MASK[8][1];
+	__declspec(align(32)) VUINT32 sABS_MASK[8][1];
+	__declspec(align(32)) VUINT32 sPIO2[8][1];
+	__declspec(align(32)) VUINT32 sPI[8][1];
+	__declspec(align(32)) VUINT32 sPC8[8][1];
+	__declspec(align(32)) VUINT32 sPC7[8][1];
+	__declspec(align(32)) VUINT32 sPC6[8][1];
+	__declspec(align(32)) VUINT32 sPC5[8][1];
+	__declspec(align(32)) VUINT32 sPC4[8][1];
+	__declspec(align(32)) VUINT32 sPC3[8][1];
+	__declspec(align(32)) VUINT32 sPC2[8][1];
+	__declspec(align(32)) VUINT32 sPC1[8][1];
+	__declspec(align(32)) VUINT32 sPC0[8][1];
+	__declspec(align(32)) VUINT32 iCHK_WORK_SUB[8][1];
+	__declspec(align(32)) VUINT32 iCHK_WORK_CMP[8][1];
 } __svml_satan2_data_internal;
 #endif
 __svml_satan2_data_internal:
-        .long 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000 // sZERO
-        .align 32
-        .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000 // sSIGN_MASK
-        .align 32
-        .long 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF // sABS_MASK
-        .align 32
-        .long 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB // sPIO2
-        .align 32
-        .long 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB // sPI
-        .align 32
-        .long 0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0 // sA08
-        .align 32
-        .long 0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631 // sA07
-        .align 32
-        .long 0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384 // sA06
-        .align 32
-        .long 0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629 // sA05
-        .align 32
-        .long 0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474 // sA04
-        .align 32
-        .long 0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8 // sA03
-        .align 32
-        .long 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F // sA02
-        .align 32
-        .long 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49 // sA01
-        .align 32
-        .long 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000 // sA00
-        .align 32
-        .long 0x81000000, 0x81000000, 0x81000000, 0x81000000, 0x81000000, 0x81000000, 0x81000000, 0x81000000 //iCHK_WORK_SUB
-        .align 32
-        .long 0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000 //iCHK_WORK_CMP
-        .align 32
-        .type	__svml_satan2_data_internal,@object
-        .size	__svml_satan2_data_internal,.-__svml_satan2_data_internal
+	.long	0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000 // sZERO
+	.align	32
+	.long	0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000 // sSIGN_MASK
+	.align	32
+	.long	0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF, 0x7FFFFFFF // sABS_MASK
+	.align	32
+	.long	0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB, 0x3FC90FDB // sPIO2
+	.align	32
+	.long	0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB // sPI
+	.align	32
+	.long	0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0, 0x3B322CC0 // sA08
+	.align	32
+	.long	0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631, 0xBC7F2631 // sA07
+	.align	32
+	.long	0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384, 0x3D2BC384 // sA06
+	.align	32
+	.long	0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629, 0xBD987629 // sA05
+	.align	32
+	.long	0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474, 0x3DD96474 // sA04
+	.align	32
+	.long	0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8, 0xBE1161F8 // sA03
+	.align	32
+	.long	0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F, 0x3E4CB79F // sA02
+	.align	32
+	.long	0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49, 0xBEAAAA49 // sA01
+	.align	32
+	.long	0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000 // sA00
+	.align	32
+	.long	0x81000000, 0x81000000, 0x81000000, 0x81000000, 0x81000000, 0x81000000, 0x81000000, 0x81000000 // iCHK_WORK_SUB
+	.align	32
+	.long	0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000, 0xFC000000 // iCHK_WORK_CMP
+	.align	32
+	.type	__svml_satan2_data_internal, @object
+	.size	__svml_satan2_data_internal, .-__svml_satan2_data_internal