x86_64: Fix svml_s_expm1f8_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, 293 insertions, 294 deletions

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f8_core_avx2.S
index 732cb4a..73f8625 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f8_core_avx2.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f8_core_avx2.S
@@ -28,324 +28,323 @@
 
 /* Offsets for data table __svml_sexpm1_data_internal
  */
-#define Expm1_HA_table                	0
-#define poly_coeff                    	512
-#define Log2e                         	640
-#define L2H                           	672
-#define L2L                           	704
-#define ExpAddConst                   	736
-#define IndexMask                     	768
-#define ExpMask                       	800
-#define MOne                          	832
-#define AbsMask                       	864
-#define Threshold                     	896
-#define L2                            	928
+#define Expm1_HA_table			0
+#define poly_coeff			512
+#define Log2e				640
+#define L2H				672
+#define L2L				704
+#define ExpAddConst			736
+#define IndexMask			768
+#define ExpMask				800
+#define MOne				832
+#define AbsMask				864
+#define Threshold			896
+#define L2				928
 
 #include <sysdep.h>
 
-        .text
-	.section .text.avx2,"ax",@progbits
+	.section .text.avx2, "ax", @progbits
 ENTRY(_ZGVdN8v_expm1f_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       __svml_sexpm1_data_internal(%rip), %rax
-        vmovaps   %ymm0, %ymm3
-        vmulps    Log2e+__svml_sexpm1_data_internal(%rip), %ymm3, %ymm4
-
-/* argument reduction */
-        vmovups   L2H+__svml_sexpm1_data_internal(%rip), %ymm2
-        vmovups   AbsMask+__svml_sexpm1_data_internal(%rip), %ymm5
-        vroundps  $0, %ymm4, %ymm8
-        vaddps    ExpAddConst+__svml_sexpm1_data_internal(%rip), %ymm8, %ymm0
-        vfnmadd213ps %ymm3, %ymm8, %ymm2
-
-/* table lookup */
-        vandps    IndexMask+__svml_sexpm1_data_internal(%rip), %ymm0, %ymm9
-        vandps    %ymm5, %ymm3, %ymm6
-        vcmpnle_uqps Threshold+__svml_sexpm1_data_internal(%rip), %ymm6, %ymm7
-        vfnmadd231ps L2L+__svml_sexpm1_data_internal(%rip), %ymm8, %ymm2
-        vandps    ExpMask+__svml_sexpm1_data_internal(%rip), %ymm0, %ymm0
-        vandnps   %ymm3, %ymm5, %ymm1
-        vpslld    $14, %ymm0, %ymm0
-        vmovmskps %ymm7, %edx
-        vmovd     %xmm9, %ecx
-        vextractf128 $1, %ymm9, %xmm10
-        movslq    %ecx, %rcx
-        vmovd     %xmm10, %r9d
-        vpextrd   $1, %xmm9, %esi
-        vpextrd   $2, %xmm9, %edi
-        vpextrd   $3, %xmm9, %r8d
-        vmovq     (%rax,%rcx), %xmm11
-        vpextrd   $1, %xmm10, %r10d
-        vpextrd   $2, %xmm10, %r11d
-        vpextrd   $3, %xmm10, %ecx
-        movslq    %esi, %rsi
-        movslq    %edi, %rdi
-        movslq    %r8d, %r8
-        movslq    %r9d, %r9
-        movslq    %r10d, %r10
-        movslq    %r11d, %r11
-        movslq    %ecx, %rcx
-        vmovq     (%rax,%rsi), %xmm13
-        vmovq     (%rax,%rdi), %xmm12
-        vmovq     (%rax,%r8), %xmm14
-        vmovq     (%rax,%r9), %xmm15
-        vmovq     (%rax,%r10), %xmm5
-        vmovq     (%rax,%r11), %xmm4
-        vmovq     (%rax,%rcx), %xmm6
-        vunpcklps %xmm12, %xmm11, %xmm7
-        vunpcklps %xmm14, %xmm13, %xmm8
-        vunpcklps %xmm4, %xmm15, %xmm15
-        vunpcklps %xmm6, %xmm5, %xmm9
-        vmulps    %ymm2, %ymm2, %ymm13
-        vinsertf128 $1, %xmm15, %ymm7, %ymm10
-        vinsertf128 $1, %xmm9, %ymm8, %ymm11
-        vunpcklps %ymm11, %ymm10, %ymm12
-        vorps     %ymm0, %ymm12, %ymm14
-
-/* polynomial */
-        vmovups   poly_coeff+__svml_sexpm1_data_internal(%rip), %ymm12
-        vfmadd213ps poly_coeff+32+__svml_sexpm1_data_internal(%rip), %ymm2, %ymm12
-        vfmadd213ps %ymm2, %ymm13, %ymm12
-
-/* T-1 */
-        vmovups   MOne+__svml_sexpm1_data_internal(%rip), %ymm13
-        vaddps    %ymm13, %ymm14, %ymm2
-        vunpckhps %ymm11, %ymm10, %ymm4
-        vfmadd213ps %ymm2, %ymm0, %ymm4
-        vsubps    %ymm13, %ymm4, %ymm0
-        vfmadd213ps %ymm4, %ymm12, %ymm0
-        vorps     %ymm1, %ymm0, %ymm0
-        testl     %edx, %edx
-
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 edx ymm0 ymm3
-
-/* 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	__svml_sexpm1_data_internal(%rip), %rax
+	vmovaps	%ymm0, %ymm3
+	vmulps	Log2e+__svml_sexpm1_data_internal(%rip), %ymm3, %ymm4
+
+	/* argument reduction */
+	vmovups	L2H+__svml_sexpm1_data_internal(%rip), %ymm2
+	vmovups	AbsMask+__svml_sexpm1_data_internal(%rip), %ymm5
+	vroundps $0, %ymm4, %ymm8
+	vaddps	ExpAddConst+__svml_sexpm1_data_internal(%rip), %ymm8, %ymm0
+	vfnmadd213ps %ymm3, %ymm8, %ymm2
+
+	/* table lookup */
+	vandps	IndexMask+__svml_sexpm1_data_internal(%rip), %ymm0, %ymm9
+	vandps	%ymm5, %ymm3, %ymm6
+	vcmpnle_uqps Threshold+__svml_sexpm1_data_internal(%rip), %ymm6, %ymm7
+	vfnmadd231ps L2L+__svml_sexpm1_data_internal(%rip), %ymm8, %ymm2
+	vandps	ExpMask+__svml_sexpm1_data_internal(%rip), %ymm0, %ymm0
+	vandnps	%ymm3, %ymm5, %ymm1
+	vpslld	$14, %ymm0, %ymm0
+	vmovmskps %ymm7, %edx
+	vmovd	%xmm9, %ecx
+	vextractf128 $1, %ymm9, %xmm10
+	movslq	%ecx, %rcx
+	vmovd	%xmm10, %r9d
+	vpextrd	$1, %xmm9, %esi
+	vpextrd	$2, %xmm9, %edi
+	vpextrd	$3, %xmm9, %r8d
+	vmovq	(%rax, %rcx), %xmm11
+	vpextrd	$1, %xmm10, %r10d
+	vpextrd	$2, %xmm10, %r11d
+	vpextrd	$3, %xmm10, %ecx
+	movslq	%esi, %rsi
+	movslq	%edi, %rdi
+	movslq	%r8d, %r8
+	movslq	%r9d, %r9
+	movslq	%r10d, %r10
+	movslq	%r11d, %r11
+	movslq	%ecx, %rcx
+	vmovq	(%rax, %rsi), %xmm13
+	vmovq	(%rax, %rdi), %xmm12
+	vmovq	(%rax, %r8), %xmm14
+	vmovq	(%rax, %r9), %xmm15
+	vmovq	(%rax, %r10), %xmm5
+	vmovq	(%rax, %r11), %xmm4
+	vmovq	(%rax, %rcx), %xmm6
+	vunpcklps %xmm12, %xmm11, %xmm7
+	vunpcklps %xmm14, %xmm13, %xmm8
+	vunpcklps %xmm4, %xmm15, %xmm15
+	vunpcklps %xmm6, %xmm5, %xmm9
+	vmulps	%ymm2, %ymm2, %ymm13
+	vinsertf128 $1, %xmm15, %ymm7, %ymm10
+	vinsertf128 $1, %xmm9, %ymm8, %ymm11
+	vunpcklps %ymm11, %ymm10, %ymm12
+	vorps	%ymm0, %ymm12, %ymm14
+
+	/* polynomial */
+	vmovups	poly_coeff+__svml_sexpm1_data_internal(%rip), %ymm12
+	vfmadd213ps poly_coeff+32+__svml_sexpm1_data_internal(%rip), %ymm2, %ymm12
+	vfmadd213ps %ymm2, %ymm13, %ymm12
+
+	/* T-1 */
+	vmovups	MOne+__svml_sexpm1_data_internal(%rip), %ymm13
+	vaddps	%ymm13, %ymm14, %ymm2
+	vunpckhps %ymm11, %ymm10, %ymm4
+	vfmadd213ps %ymm2, %ymm0, %ymm4
+	vsubps	%ymm13, %ymm4, %ymm0
+	vfmadd213ps %ymm4, %ymm12, %ymm0
+	vorps	%ymm1, %ymm0, %ymm0
+	testl	%edx, %edx
+
+	/* Go to special inputs processing branch */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	# LOE rbx r12 r13 r14 r15 edx ymm0 ymm3
+
+	/* 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   %ymm3, 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	%ymm3, 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      expm1f@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
+	movl	%r12d, %r14d
+	movss	32(%rsp, %r14, 4), %xmm0
+	call	expm1f@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_expm1f_avx2)
 
-        .section .rodata, "a"
-        .align 32
+	.section .rodata, "a"
+	.align	32
 
 #ifdef __svml_sexpm1_data_internal_typedef
 typedef unsigned int VUINT32;
 typedef struct {
-        __declspec(align(32)) VUINT32 Expm1_HA_table[(1<<7)][1];
-        __declspec(align(32)) VUINT32 poly_coeff[4][8][1];
-        __declspec(align(32)) VUINT32 Log2e[8][1];
-        __declspec(align(32)) VUINT32 L2H[8][1];
-        __declspec(align(32)) VUINT32 L2L[8][1];
-        __declspec(align(32)) VUINT32 ExpAddConst[8][1];
-        __declspec(align(32)) VUINT32 IndexMask[8][1];
-        __declspec(align(32)) VUINT32 ExpMask[8][1];
-        __declspec(align(32)) VUINT32 MOne[8][1];
-        __declspec(align(32)) VUINT32 AbsMask[8][1];
-        __declspec(align(32)) VUINT32 Threshold[8][1];
-        __declspec(align(32)) VUINT32 L2[8][1];
+	__declspec(align(32)) VUINT32 Expm1_HA_table[(1<<7)][1];
+	__declspec(align(32)) VUINT32 poly_coeff[4][8][1];
+	__declspec(align(32)) VUINT32 Log2e[8][1];
+	__declspec(align(32)) VUINT32 L2H[8][1];
+	__declspec(align(32)) VUINT32 L2L[8][1];
+	__declspec(align(32)) VUINT32 ExpAddConst[8][1];
+	__declspec(align(32)) VUINT32 IndexMask[8][1];
+	__declspec(align(32)) VUINT32 ExpMask[8][1];
+	__declspec(align(32)) VUINT32 MOne[8][1];
+	__declspec(align(32)) VUINT32 AbsMask[8][1];
+	__declspec(align(32)) VUINT32 Threshold[8][1];
+	__declspec(align(32)) VUINT32 L2[8][1];
 } __svml_sexpm1_data_internal;
 #endif
 __svml_sexpm1_data_internal:
-        /* Expm1_HA_table */
-        .long 0x00000000, 0x00000000
-        .long 0x00016000, 0x391a3e78
-        .long 0x0002d000, 0xb89e59d5
-        .long 0x00044000, 0xb93ae78a
-        .long 0x0005b000, 0xb9279306
-        .long 0x00072000, 0xb79e6961
-        .long 0x0008a000, 0xb97e2fee
-        .long 0x000a1000, 0x391aaea9
-        .long 0x000b9000, 0x39383c7d
-        .long 0x000d2000, 0xb9241490
-        .long 0x000ea000, 0x39073169
-        .long 0x00103000, 0x386e218a
-        .long 0x0011c000, 0x38f4dceb
-        .long 0x00136000, 0xb93a9a1e
-        .long 0x0014f000, 0x391df520
-        .long 0x00169000, 0x3905a6e4
-        .long 0x00183000, 0x397e0a32
-        .long 0x0019e000, 0x370b2641
-        .long 0x001b9000, 0xb8b1918b
-        .long 0x001d4000, 0xb8132c6a
-        .long 0x001ef000, 0x39264c12
-        .long 0x0020b000, 0x37221f73
-        .long 0x00227000, 0x37060619
-        .long 0x00243000, 0x3922b5c1
-        .long 0x00260000, 0xb814ab27
-        .long 0x0027d000, 0xb89b12c6
-        .long 0x0029a000, 0x382d5a75
-        .long 0x002b8000, 0xb938c94b
-        .long 0x002d6000, 0xb97822b8
-        .long 0x002f4000, 0xb910ea53
-        .long 0x00312000, 0x38fd6075
-        .long 0x00331000, 0x38620955
-        .long 0x00350000, 0x391e667f
-        .long 0x00370000, 0xb89b8736
-        .long 0x00390000, 0xb90a1714
-        .long 0x003b0000, 0xb7a54ded
-        .long 0x003d1000, 0xb96b8c15
-        .long 0x003f1000, 0x397336cf
-        .long 0x00413000, 0xb8eccd66
-        .long 0x00434000, 0x39599b45
-        .long 0x00456000, 0x3965422b
-        .long 0x00479000, 0xb8a2cdd5
-        .long 0x0049c000, 0xb9484f32
-        .long 0x004bf000, 0xb8fac043
-        .long 0x004e2000, 0x391182a4
-        .long 0x00506000, 0x38ccf6bc
-        .long 0x0052b000, 0xb97c4dc2
-        .long 0x0054f000, 0x38d6aaf4
-        .long 0x00574000, 0x391f995b
-        .long 0x0059a000, 0xb8ba8f62
-        .long 0x005c0000, 0xb9090d05
-        .long 0x005e6000, 0x37f4825e
-        .long 0x0060d000, 0xb8c844f5
-        .long 0x00634000, 0xb76d1a83
-        .long 0x0065c000, 0xb95f2310
-        .long 0x00684000, 0xb952b5f8
-        .long 0x006ac000, 0x37c6e7dd
-        .long 0x006d5000, 0xb7cfe126
-        .long 0x006fe000, 0x3917337c
-        .long 0x00728000, 0x383b9e2d
-        .long 0x00752000, 0x392fa2a5
-        .long 0x0077d000, 0x37df730b
-        .long 0x007a8000, 0x38ecb6dd
-        .long 0x007d4000, 0xb879f986
-        /*== poly_coeff[4] ==*/
-        .align 32
-        .long 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF /* coeff3 */
-        .long 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F /* coeff2 */
-        /* 64 Byte Padding */
-        .zero 64
-        /*== Log2e ==*/
-        .align 32
-        .long 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B
-        /*== L2H ==*/
-        .align 32
-        .long 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000
-        /*== L2L ==*/
-        .align 32
-        .long 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083
-        /*== ExpAddConst ==*/
-        .align 32
-        .long 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00
-        /*== IndexMask ==*/
-        .align 32
-        .long 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8
-        /*== ExpMask ==*/
-        .align 32
-        .long 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00
-        /*== MOne ==*/
-        .align 32
-        .long 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000
-        /*== AbsMask ==*/
-        .align 32
-        .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
-        /*== Threshold ==*/
-        .align 32
-        .long 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B // 86.643394
-        /*== L2 ==*/
-        .align 32
-        .long 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218
-        .align 32
-        .type	__svml_sexpm1_data_internal,@object
-        .size	__svml_sexpm1_data_internal,.-__svml_sexpm1_data_internal
+	/* Expm1_HA_table */
+	.long	0x00000000, 0x00000000
+	.long	0x00016000, 0x391a3e78
+	.long	0x0002d000, 0xb89e59d5
+	.long	0x00044000, 0xb93ae78a
+	.long	0x0005b000, 0xb9279306
+	.long	0x00072000, 0xb79e6961
+	.long	0x0008a000, 0xb97e2fee
+	.long	0x000a1000, 0x391aaea9
+	.long	0x000b9000, 0x39383c7d
+	.long	0x000d2000, 0xb9241490
+	.long	0x000ea000, 0x39073169
+	.long	0x00103000, 0x386e218a
+	.long	0x0011c000, 0x38f4dceb
+	.long	0x00136000, 0xb93a9a1e
+	.long	0x0014f000, 0x391df520
+	.long	0x00169000, 0x3905a6e4
+	.long	0x00183000, 0x397e0a32
+	.long	0x0019e000, 0x370b2641
+	.long	0x001b9000, 0xb8b1918b
+	.long	0x001d4000, 0xb8132c6a
+	.long	0x001ef000, 0x39264c12
+	.long	0x0020b000, 0x37221f73
+	.long	0x00227000, 0x37060619
+	.long	0x00243000, 0x3922b5c1
+	.long	0x00260000, 0xb814ab27
+	.long	0x0027d000, 0xb89b12c6
+	.long	0x0029a000, 0x382d5a75
+	.long	0x002b8000, 0xb938c94b
+	.long	0x002d6000, 0xb97822b8
+	.long	0x002f4000, 0xb910ea53
+	.long	0x00312000, 0x38fd6075
+	.long	0x00331000, 0x38620955
+	.long	0x00350000, 0x391e667f
+	.long	0x00370000, 0xb89b8736
+	.long	0x00390000, 0xb90a1714
+	.long	0x003b0000, 0xb7a54ded
+	.long	0x003d1000, 0xb96b8c15
+	.long	0x003f1000, 0x397336cf
+	.long	0x00413000, 0xb8eccd66
+	.long	0x00434000, 0x39599b45
+	.long	0x00456000, 0x3965422b
+	.long	0x00479000, 0xb8a2cdd5
+	.long	0x0049c000, 0xb9484f32
+	.long	0x004bf000, 0xb8fac043
+	.long	0x004e2000, 0x391182a4
+	.long	0x00506000, 0x38ccf6bc
+	.long	0x0052b000, 0xb97c4dc2
+	.long	0x0054f000, 0x38d6aaf4
+	.long	0x00574000, 0x391f995b
+	.long	0x0059a000, 0xb8ba8f62
+	.long	0x005c0000, 0xb9090d05
+	.long	0x005e6000, 0x37f4825e
+	.long	0x0060d000, 0xb8c844f5
+	.long	0x00634000, 0xb76d1a83
+	.long	0x0065c000, 0xb95f2310
+	.long	0x00684000, 0xb952b5f8
+	.long	0x006ac000, 0x37c6e7dd
+	.long	0x006d5000, 0xb7cfe126
+	.long	0x006fe000, 0x3917337c
+	.long	0x00728000, 0x383b9e2d
+	.long	0x00752000, 0x392fa2a5
+	.long	0x0077d000, 0x37df730b
+	.long	0x007a8000, 0x38ecb6dd
+	.long	0x007d4000, 0xb879f986
+	/* poly_coeff[4] */
+	.align	32
+	.long	0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF /* coeff3 */
+	.long	0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F /* coeff2 */
+	/* 64 Byte Padding */
+	.zero	64
+	/* Log2e */
+	.align	32
+	.long	0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B
+	/* L2H */
+	.align	32
+	.long	0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000
+	/* L2L */
+	.align	32
+	.long	0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083
+	/* ExpAddConst */
+	.align	32
+	.long	0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00
+	/* IndexMask */
+	.align	32
+	.long	0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8
+	/* ExpMask */
+	.align	32
+	.long	0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00
+	/* MOne */
+	.align	32
+	.long	0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000
+	/* AbsMask */
+	.align	32
+	.long	0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
+	/* Threshold */
+	.align	32
+	.long	0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B // 86.643394
+	/* L2 */
+	.align	32
+	.long	0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218
+	.align	32
+	.type	__svml_sexpm1_data_internal, @object
+	.size	__svml_sexpm1_data_internal, .-__svml_sexpm1_data_internal