From 35668c8d9475d7fe061978ce79a286ba972062cc Mon Sep 17 00:00:00 2001
From: Sunil K Pandey <skpgkp2@gmail.com>
Date: Mon, 7 Mar 2022 10:47:08 -0800
Subject: x86_64: Fix svml_s_acosf8_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>
---
 .../x86_64/fpu/multiarch/svml_s_acosf8_core_avx2.S | 411 ++++++++++-----------
 1 file changed, 205 insertions(+), 206 deletions(-)

(limited to 'sysdeps')

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_acosf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_acosf8_core_avx2.S
index 94402554ad..bf28a5dd00 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_acosf8_core_avx2.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_acosf8_core_avx2.S
@@ -29,236 +29,235 @@
 
 /* Offsets for data table __svml_sacos_data_internal
  */
-#define SgnBit                        	0
-#define OneHalf                       	32
-#define SmallNorm                     	64
-#define MOne                          	96
-#define Two                           	128
-#define sqrt_coeff                    	160
-#define poly_coeff                    	224
-#define Pi2H                          	384
-#define PiH                           	416
+#define SgnBit				0
+#define OneHalf				32
+#define SmallNorm			64
+#define MOne				96
+#define Two				128
+#define sqrt_coeff			160
+#define poly_coeff			224
+#define Pi2H				384
+#define PiH				416
 
 #include <sysdep.h>
 
-        .text
-	.section .text.avx2,"ax",@progbits
+	.section .text.avx2, "ax", @progbits
 ENTRY(_ZGVdN8v_acosf_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
-
-/*
- * 2*sqrt(X) ~ Sh - Sl  (to 24+ bits)
- * SQ ~ 2*sqrt(X)
- */
-        vmovups   __svml_sacos_data_internal(%rip), %ymm6
-        vmovups   OneHalf+__svml_sacos_data_internal(%rip), %ymm7
-        vmovaps   %ymm0, %ymm5
-
-/* x = -|arg| */
-        vorps     %ymm5, %ymm6, %ymm4
-
-/* Y = 0.5 + 0.5*(-x) */
-        vfmadd231ps %ymm4, %ymm7, %ymm7
-
-/* x^2 */
-        vmulps    %ymm4, %ymm4, %ymm8
-
-/* SQ ~ 2*sqrt(Y) */
-        vmovups   sqrt_coeff+__svml_sacos_data_internal(%rip), %ymm0
-        vcmpnge_uqps MOne+__svml_sacos_data_internal(%rip), %ymm4, %ymm9
-        vcmplt_oqps SmallNorm+__svml_sacos_data_internal(%rip), %ymm7, %ymm10
-        vminps    %ymm7, %ymm8, %ymm2
-        vaddps    %ymm7, %ymm7, %ymm14
-        vrsqrtps  %ymm7, %ymm11
-        vmovups   poly_coeff+64+__svml_sacos_data_internal(%rip), %ymm8
-        vcmpnlt_uqps %ymm7, %ymm2, %ymm1
-        vmulps    %ymm2, %ymm2, %ymm7
-        vfmadd213ps poly_coeff+96+__svml_sacos_data_internal(%rip), %ymm2, %ymm8
-        vmovmskps %ymm9, %edx
-
-/* polynomial */
-        vmovups   poly_coeff+__svml_sacos_data_internal(%rip), %ymm9
-        vandnps   %ymm11, %ymm10, %ymm12
-        vmulps    %ymm12, %ymm12, %ymm13
-        vfmadd213ps poly_coeff+32+__svml_sacos_data_internal(%rip), %ymm2, %ymm9
-
-/* X<X^2 iff X<0 */
-        vcmplt_oqps %ymm2, %ymm5, %ymm10
-        vfmadd213ps %ymm8, %ymm7, %ymm9
-        vandps    %ymm5, %ymm6, %ymm3
-        vmulps    %ymm14, %ymm12, %ymm6
-        vfmsub213ps Two+__svml_sacos_data_internal(%rip), %ymm13, %ymm14
-        vfmadd213ps poly_coeff+128+__svml_sacos_data_internal(%rip), %ymm2, %ymm9
-        vfmadd213ps sqrt_coeff+32+__svml_sacos_data_internal(%rip), %ymm14, %ymm0
-        vmulps    %ymm14, %ymm6, %ymm15
-        vmulps    %ymm9, %ymm2, %ymm14
-        vfnmadd213ps %ymm6, %ymm15, %ymm0
-        vblendvps %ymm1, %ymm0, %ymm4, %ymm0
-        vandps    PiH+__svml_sacos_data_internal(%rip), %ymm1, %ymm2
-        vandnps   Pi2H+__svml_sacos_data_internal(%rip), %ymm1, %ymm12
-        vxorps    %ymm3, %ymm0, %ymm1
-        vfmadd213ps %ymm1, %ymm1, %ymm14
-        vandps    %ymm10, %ymm2, %ymm11
-        vaddps    %ymm12, %ymm11, %ymm13
-        vaddps    %ymm14, %ymm13, %ymm0
-        testl     %edx, %edx
-
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 edx ymm0 ymm5
-
-/* 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
+
+	/*
+	 * 2*sqrt(X) ~ Sh - Sl  (to 24+ bits)
+	 * SQ ~ 2*sqrt(X)
+	 */
+	vmovups	__svml_sacos_data_internal(%rip), %ymm6
+	vmovups	OneHalf+__svml_sacos_data_internal(%rip), %ymm7
+	vmovaps	%ymm0, %ymm5
+
+	/* x = -|arg| */
+	vorps	%ymm5, %ymm6, %ymm4
+
+	/* Y = 0.5 + 0.5*(-x) */
+	vfmadd231ps %ymm4, %ymm7, %ymm7
+
+	/* x^2 */
+	vmulps	%ymm4, %ymm4, %ymm8
+
+	/* SQ ~ 2*sqrt(Y) */
+	vmovups	sqrt_coeff+__svml_sacos_data_internal(%rip), %ymm0
+	vcmpnge_uqps MOne+__svml_sacos_data_internal(%rip), %ymm4, %ymm9
+	vcmplt_oqps SmallNorm+__svml_sacos_data_internal(%rip), %ymm7, %ymm10
+	vminps	%ymm7, %ymm8, %ymm2
+	vaddps	%ymm7, %ymm7, %ymm14
+	vrsqrtps %ymm7, %ymm11
+	vmovups	poly_coeff+64+__svml_sacos_data_internal(%rip), %ymm8
+	vcmpnlt_uqps %ymm7, %ymm2, %ymm1
+	vmulps	%ymm2, %ymm2, %ymm7
+	vfmadd213ps poly_coeff+96+__svml_sacos_data_internal(%rip), %ymm2, %ymm8
+	vmovmskps %ymm9, %edx
+
+	/* polynomial */
+	vmovups	poly_coeff+__svml_sacos_data_internal(%rip), %ymm9
+	vandnps	%ymm11, %ymm10, %ymm12
+	vmulps	%ymm12, %ymm12, %ymm13
+	vfmadd213ps poly_coeff+32+__svml_sacos_data_internal(%rip), %ymm2, %ymm9
+
+	/* X<X^2 iff X<0 */
+	vcmplt_oqps %ymm2, %ymm5, %ymm10
+	vfmadd213ps %ymm8, %ymm7, %ymm9
+	vandps	%ymm5, %ymm6, %ymm3
+	vmulps	%ymm14, %ymm12, %ymm6
+	vfmsub213ps Two+__svml_sacos_data_internal(%rip), %ymm13, %ymm14
+	vfmadd213ps poly_coeff+128+__svml_sacos_data_internal(%rip), %ymm2, %ymm9
+	vfmadd213ps sqrt_coeff+32+__svml_sacos_data_internal(%rip), %ymm14, %ymm0
+	vmulps	%ymm14, %ymm6, %ymm15
+	vmulps	%ymm9, %ymm2, %ymm14
+	vfnmadd213ps %ymm6, %ymm15, %ymm0
+	vblendvps %ymm1, %ymm0, %ymm4, %ymm0
+	vandps	PiH+__svml_sacos_data_internal(%rip), %ymm1, %ymm2
+	vandnps	Pi2H+__svml_sacos_data_internal(%rip), %ymm1, %ymm12
+	vxorps	%ymm3, %ymm0, %ymm1
+	vfmadd213ps %ymm1, %ymm1, %ymm14
+	vandps	%ymm10, %ymm2, %ymm11
+	vaddps	%ymm12, %ymm11, %ymm13
+	vaddps	%ymm14, %ymm13, %ymm0
+	testl	%edx, %edx
+
+	/* Go to special inputs processing branch */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	# LOE rbx r12 r13 r14 r15 edx ymm0 ymm5
+
+	/* 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):
-        vmovups   %ymm5, 32(%rsp)
-        vmovups   %ymm0, 64(%rsp)
-                                # LOE rbx r12 r13 r14 r15 edx ymm0
-
-        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: -80; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 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: -88; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 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: -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
- */
+	vmovups	%ymm5, 32(%rsp)
+	vmovups	%ymm0, 64(%rsp)
+	# LOE rbx r12 r13 r14 r15 edx ymm0
+
+	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: -80; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 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: -88; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 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: -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      $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   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	$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	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
-        movss     32(%rsp,%r14,4), %xmm0
-        call      acosf@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
+	movl	%r12d, %r14d
+	movss	32(%rsp, %r14, 4), %xmm0
+	call	acosf@PLT
+	# LOE rbx r14 r15 r12d r13d xmm0
 
-        movss     %xmm0, 64(%rsp,%r14,4)
+	movss	%xmm0, 64(%rsp, %r14, 4)
 
-/* 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(_ZGVdN8v_acosf_avx2)
 
-        .section .rodata, "a"
-        .align 32
+	.section .rodata, "a"
+	.align	32
 
 #ifdef __svml_sacos_data_internal_typedef
 typedef unsigned int VUINT32;
 typedef struct {
-        __declspec(align(32)) VUINT32 SgnBit[8][1];
-        __declspec(align(32)) VUINT32 OneHalf[8][1];
-        __declspec(align(32)) VUINT32 SmallNorm[8][1];
-        __declspec(align(32)) VUINT32 MOne[8][1];
-        __declspec(align(32)) VUINT32 Two[8][1];
-        __declspec(align(32)) VUINT32 sqrt_coeff[2][8][1];
-        __declspec(align(32)) VUINT32 poly_coeff[5][8][1];
-        __declspec(align(32)) VUINT32 Pi2H[8][1];
-        __declspec(align(32)) VUINT32 PiH[8][1];
+	__declspec(align(32)) VUINT32 SgnBit[8][1];
+	__declspec(align(32)) VUINT32 OneHalf[8][1];
+	__declspec(align(32)) VUINT32 SmallNorm[8][1];
+	__declspec(align(32)) VUINT32 MOne[8][1];
+	__declspec(align(32)) VUINT32 Two[8][1];
+	__declspec(align(32)) VUINT32 sqrt_coeff[2][8][1];
+	__declspec(align(32)) VUINT32 poly_coeff[5][8][1];
+	__declspec(align(32)) VUINT32 Pi2H[8][1];
+	__declspec(align(32)) VUINT32 PiH[8][1];
 } __svml_sacos_data_internal;
 #endif
 __svml_sacos_data_internal:
-        /*== SgnBit ==*/
-        .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000
-        /*== OneHalf ==*/
-        .align 32
-        .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000
-        /*== SmallNorm ==*/
-        .align 32
-        .long 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000
-        /*== MOne ==*/
-        .align 32
-        .long 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000
-        /*== Two ==*/
-        .align 32
-        .long 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000
-        /*== sqrt_coeff[2] ==*/
-        .align 32
-        .long 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004 /* sqrt_coeff2 */
-        .long 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001 /* sqrt_coeff1 */
-        /*== poly_coeff[5] ==*/
-        .align 32
-        .long 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07 /* poly_coeff5 */
-        .long 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B /* poly_coeff4 */
-        .long 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4 /* poly_coeff3 */
-        .long 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12 /* poly_coeff2 */
-        .long 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF /* poly_coeff1 */
-        /*== Pi2H ==*/
-        .align 32
-        .long 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB
-        /*== PiH ==*/
-        .align 32
-        .long 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB
-        .align 32
-        .type	__svml_sacos_data_internal,@object
-        .size	__svml_sacos_data_internal,.-__svml_sacos_data_internal
+	/* SgnBit */
+	.long	0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000
+	/* OneHalf */
+	.align	32
+	.long	0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000
+	/* SmallNorm */
+	.align	32
+	.long	0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000
+	/* MOne */
+	.align	32
+	.long	0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000
+	/* Two */
+	.align	32
+	.long	0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000
+	/* sqrt_coeff[2] */
+	.align	32
+	.long	0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004 /* sqrt_coeff2 */
+	.long	0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001 /* sqrt_coeff1 */
+	/* poly_coeff[5] */
+	.align	32
+	.long	0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07 /* poly_coeff5 */
+	.long	0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B /* poly_coeff4 */
+	.long	0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4 /* poly_coeff3 */
+	.long	0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12 /* poly_coeff2 */
+	.long	0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF /* poly_coeff1 */
+	/* Pi2H */
+	.align	32
+	.long	0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB
+	/* PiH */
+	.align	32
+	.long	0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB
+	.align	32
+	.type	__svml_sacos_data_internal, @object
+	.size	__svml_sacos_data_internal, .-__svml_sacos_data_internal
-- 
cgit v1.2.3