diff mbox series

[072/126] x86_64: Fix svml_d_exp108_core_avx512.S code formatting

Message ID 20220307150201.10590-73-skpgkp2@gmail.com
State New
Headers show
Series x86_64: Fix libmvec assembly code formatting | expand

Commit Message

Sunil Pandey March 7, 2022, 3:01 p.m. UTC 
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.
---
 .../fpu/multiarch/svml_d_exp108_core_avx512.S | 457 +++++++++---------
 1 file changed, 228 insertions(+), 229 deletions(-)
diff mbox series

Patch

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_exp108_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_d_exp108_core_avx512.S
index bfd37be863..40b01c3cd0 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_d_exp108_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_d_exp108_core_avx512.S
@@ -30,258 +30,257 @@ 
 
 /* Offsets for data table __svml_dexp10_data_internal_avx512
  */
-#define Exp_tbl_H                     	0
-#define L2E                           	128
-#define Shifter                       	192
-#define L2H                           	256
-#define L2L                           	320
-#define EMask                         	384
-#define poly_coeff6                   	448
-#define poly_coeff5                   	512
-#define poly_coeff4                   	576
-#define poly_coeff3                   	640
-#define poly_coeff2                   	704
-#define poly_coeff1                   	768
-#define AbsMask                       	832
-#define Threshold                     	896
+#define Exp_tbl_H			0
+#define L2E				128
+#define Shifter				192
+#define L2H				256
+#define L2L				320
+#define EMask				384
+#define poly_coeff6			448
+#define poly_coeff5			512
+#define poly_coeff4			576
+#define poly_coeff3			640
+#define poly_coeff2			704
+#define poly_coeff1			768
+#define AbsMask				832
+#define Threshold			896
 
 #include <sysdep.h>
 
-        .text
-	.section .text.evex512,"ax",@progbits
+	.section .text.evex512, "ax", @progbits
 ENTRY(_ZGVeN8v_exp10_skx)
-        pushq     %rbp
-        cfi_def_cfa_offset(16)
-        movq      %rsp, %rbp
-        cfi_def_cfa(6, 16)
-        cfi_offset(6, -16)
-        andq      $-64, %rsp
-        subq      $192, %rsp
-        vmovups   L2E+__svml_dexp10_data_internal_avx512(%rip), %zmm4
-        vmovups   Shifter+__svml_dexp10_data_internal_avx512(%rip), %zmm2
-        vmovups   L2H+__svml_dexp10_data_internal_avx512(%rip), %zmm5
-        vmovups   L2L+__svml_dexp10_data_internal_avx512(%rip), %zmm3
-
-/* polynomial */
-        vmovups   poly_coeff6+__svml_dexp10_data_internal_avx512(%rip), %zmm6
-        vmovups   poly_coeff4+__svml_dexp10_data_internal_avx512(%rip), %zmm7
-        vmovups   poly_coeff3+__svml_dexp10_data_internal_avx512(%rip), %zmm9
-        vmovups   poly_coeff2+__svml_dexp10_data_internal_avx512(%rip), %zmm8
-        vmovups   poly_coeff1+__svml_dexp10_data_internal_avx512(%rip), %zmm11
-        vmovups   Threshold+__svml_dexp10_data_internal_avx512(%rip), %zmm14
-        vmovaps   %zmm0, %zmm1
-
-/* 2^(52-4)*1.5 + x * log2(e) */
-        vfmadd213pd {rz-sae}, %zmm2, %zmm1, %zmm4
-        vandpd    AbsMask+__svml_dexp10_data_internal_avx512(%rip), %zmm1, %zmm13
-
-/* Z0 ~ x*log2(e), rounded down to 4 fractional bits */
-        vsubpd    {rn-sae}, %zmm2, %zmm4, %zmm0
-
-/* Table lookup: Th */
-        vmovups   __svml_dexp10_data_internal_avx512(%rip), %zmm2
-        vcmppd    $29, {sae}, %zmm14, %zmm13, %k0
-
-/* R = x - Z0*log(2) */
-        vfnmadd213pd {rn-sae}, %zmm1, %zmm0, %zmm5
-        vpermt2pd Exp_tbl_H+64+__svml_dexp10_data_internal_avx512(%rip), %zmm4, %zmm2
-        kmovw     %k0, %edx
-        vfnmadd231pd {rn-sae}, %zmm0, %zmm3, %zmm5
-        vmovups   poly_coeff5+__svml_dexp10_data_internal_avx512(%rip), %zmm3
-
-/* ensure |R|<2 even for special cases */
-        vandpd    EMask+__svml_dexp10_data_internal_avx512(%rip), %zmm5, %zmm12
-        vmulpd    {rn-sae}, %zmm12, %zmm12, %zmm10
-        vmulpd    {rn-sae}, %zmm12, %zmm2, %zmm15
-        vfmadd231pd {rn-sae}, %zmm12, %zmm6, %zmm3
-        vfmadd231pd {rn-sae}, %zmm12, %zmm7, %zmm9
-        vfmadd231pd {rn-sae}, %zmm12, %zmm8, %zmm11
-        vfmadd213pd {rn-sae}, %zmm9, %zmm10, %zmm3
-        vfmadd213pd {rn-sae}, %zmm11, %zmm10, %zmm3
-        vfmadd213pd {rn-sae}, %zmm2, %zmm15, %zmm3
-        vscalefpd {rn-sae}, %zmm0, %zmm3, %zmm0
-        testl     %edx, %edx
-
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 edx zmm0 zmm1
-
-/* 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	$-64, %rsp
+	subq	$192, %rsp
+	vmovups	L2E+__svml_dexp10_data_internal_avx512(%rip), %zmm4
+	vmovups	Shifter+__svml_dexp10_data_internal_avx512(%rip), %zmm2
+	vmovups	L2H+__svml_dexp10_data_internal_avx512(%rip), %zmm5
+	vmovups	L2L+__svml_dexp10_data_internal_avx512(%rip), %zmm3
+
+	/* polynomial */
+	vmovups	poly_coeff6+__svml_dexp10_data_internal_avx512(%rip), %zmm6
+	vmovups	poly_coeff4+__svml_dexp10_data_internal_avx512(%rip), %zmm7
+	vmovups	poly_coeff3+__svml_dexp10_data_internal_avx512(%rip), %zmm9
+	vmovups	poly_coeff2+__svml_dexp10_data_internal_avx512(%rip), %zmm8
+	vmovups	poly_coeff1+__svml_dexp10_data_internal_avx512(%rip), %zmm11
+	vmovups	Threshold+__svml_dexp10_data_internal_avx512(%rip), %zmm14
+	vmovaps	%zmm0, %zmm1
+
+	/* 2^(52-4)*1.5 + x * log2(e) */
+	vfmadd213pd {rz-sae}, %zmm2, %zmm1, %zmm4
+	vandpd	AbsMask+__svml_dexp10_data_internal_avx512(%rip), %zmm1, %zmm13
+
+	/* Z0 ~ x*log2(e), rounded down to 4 fractional bits */
+	vsubpd	{rn-sae}, %zmm2, %zmm4, %zmm0
+
+	/* Table lookup: Th */
+	vmovups	__svml_dexp10_data_internal_avx512(%rip), %zmm2
+	vcmppd	$29, {sae}, %zmm14, %zmm13, %k0
+
+	/* R = x - Z0*log(2) */
+	vfnmadd213pd {rn-sae}, %zmm1, %zmm0, %zmm5
+	vpermt2pd Exp_tbl_H+64+__svml_dexp10_data_internal_avx512(%rip), %zmm4, %zmm2
+	kmovw	%k0, %edx
+	vfnmadd231pd {rn-sae}, %zmm0, %zmm3, %zmm5
+	vmovups	poly_coeff5+__svml_dexp10_data_internal_avx512(%rip), %zmm3
+
+	/* ensure |R|<2 even for special cases */
+	vandpd	EMask+__svml_dexp10_data_internal_avx512(%rip), %zmm5, %zmm12
+	vmulpd	{rn-sae}, %zmm12, %zmm12, %zmm10
+	vmulpd	{rn-sae}, %zmm12, %zmm2, %zmm15
+	vfmadd231pd {rn-sae}, %zmm12, %zmm6, %zmm3
+	vfmadd231pd {rn-sae}, %zmm12, %zmm7, %zmm9
+	vfmadd231pd {rn-sae}, %zmm12, %zmm8, %zmm11
+	vfmadd213pd {rn-sae}, %zmm9, %zmm10, %zmm3
+	vfmadd213pd {rn-sae}, %zmm11, %zmm10, %zmm3
+	vfmadd213pd {rn-sae}, %zmm2, %zmm15, %zmm3
+	vscalefpd {rn-sae}, %zmm0, %zmm3, %zmm0
+	testl	%edx, %edx
+
+	/* Go to special inputs processing branch */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	# LOE rbx r12 r13 r14 r15 edx zmm0 zmm1
+
+	/* 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   %zmm1, 64(%rsp)
-        vmovups   %zmm0, 128(%rsp)
-                                # LOE rbx r12 r13 r14 r15 edx zmm0
-
-        xorl      %eax, %eax
-                                # LOE rbx r12 r13 r14 r15 eax edx
-
-        vzeroupper
-        movq      %r12, 16(%rsp)
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
-        movl      %eax, %r12d
-        movq      %r13, 8(%rsp)
-        /*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
-        movl      %edx, %r13d
-        movq      %r14, (%rsp)
-        /*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r15 r12d r13d
-
-/* Range mask
- * bits check
- */
+	vmovups	%zmm1, 64(%rsp)
+	vmovups	%zmm0, 128(%rsp)
+	# LOE rbx r12 r13 r14 r15 edx zmm0
+
+	xorl	%eax, %eax
+	# LOE rbx r12 r13 r14 r15 eax edx
+
+	vzeroupper
+	movq	%r12, 16(%rsp)
+	/*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
+	movl	%eax, %r12d
+	movq	%r13, 8(%rsp)
+	/*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
+	movl	%edx, %r13d
+	movq	%r14, (%rsp)
+	/*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r15 r12d r13d
+
+	/* Range mask
+	 * bits check
+	 */
 
 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   128(%rsp), %zmm0
-
-/* Go to exit */
-        jmp       L(EXIT)
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
-        /*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
-        /*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r12 r13 r14 r15 zmm0
-
-/* 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	128(%rsp), %zmm0
+
+	/* Go to exit */
+	jmp	L(EXIT)
+	/*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
+	/*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
+	/*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r12 r13 r14 r15 zmm0
+
+	/* Scalar math fucntion call
+	 * to process special input
+	 */
 
 L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movsd     64(%rsp,%r14,8), %xmm0
-        call      exp10@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
+	movl	%r12d, %r14d
+	movsd	64(%rsp, %r14, 8), %xmm0
+	call	exp10@PLT
+	# LOE rbx r14 r15 r12d r13d xmm0
 
-        movsd     %xmm0, 128(%rsp,%r14,8)
+	movsd	%xmm0, 128(%rsp, %r14, 8)
 
-/* Process special inputs in loop */
-        jmp       L(SPECIAL_VALUES_LOOP)
-                                # LOE rbx r15 r12d r13d
+	/* Process special inputs in loop */
+	jmp	L(SPECIAL_VALUES_LOOP)
+	# LOE rbx r15 r12d r13d
 END(_ZGVeN8v_exp10_skx)
 
-        .section .rodata, "a"
-        .align 64
+	.section .rodata, "a"
+	.align	64
 
 #ifdef __svml_dexp10_data_internal_avx512_typedef
 typedef unsigned int VUINT32;
 typedef struct {
-        __declspec(align(64)) VUINT32 Exp_tbl_H[16][2];
-        __declspec(align(64)) VUINT32 L2E[8][2];
-        __declspec(align(64)) VUINT32 Shifter[8][2];
-        __declspec(align(64)) VUINT32 L2H[8][2];
-        __declspec(align(64)) VUINT32 L2L[8][2];
-        __declspec(align(64)) VUINT32 EMask[8][2];
-        __declspec(align(64)) VUINT32 poly_coeff6[8][2];
-        __declspec(align(64)) VUINT32 poly_coeff5[8][2];
-        __declspec(align(64)) VUINT32 poly_coeff4[8][2];
-        __declspec(align(64)) VUINT32 poly_coeff3[8][2];
-        __declspec(align(64)) VUINT32 poly_coeff2[8][2];
-        __declspec(align(64)) VUINT32 poly_coeff1[8][2];
-        __declspec(align(64)) VUINT32 AbsMask[8][2];
-        __declspec(align(64)) VUINT32 Threshold[8][2];
-    } __svml_dexp10_data_internal_avx512;
+	__declspec(align(64)) VUINT32 Exp_tbl_H[16][2];
+	__declspec(align(64)) VUINT32 L2E[8][2];
+	__declspec(align(64)) VUINT32 Shifter[8][2];
+	__declspec(align(64)) VUINT32 L2H[8][2];
+	__declspec(align(64)) VUINT32 L2L[8][2];
+	__declspec(align(64)) VUINT32 EMask[8][2];
+	__declspec(align(64)) VUINT32 poly_coeff6[8][2];
+	__declspec(align(64)) VUINT32 poly_coeff5[8][2];
+	__declspec(align(64)) VUINT32 poly_coeff4[8][2];
+	__declspec(align(64)) VUINT32 poly_coeff3[8][2];
+	__declspec(align(64)) VUINT32 poly_coeff2[8][2];
+	__declspec(align(64)) VUINT32 poly_coeff1[8][2];
+	__declspec(align(64)) VUINT32 AbsMask[8][2];
+	__declspec(align(64)) VUINT32 Threshold[8][2];
+} __svml_dexp10_data_internal_avx512;
 #endif
 __svml_dexp10_data_internal_avx512:
-        /*== Exp_tbl_H ==*/
-        .quad 0x3ff0000000000000
-        .quad 0x3ff0b5586cf9890f
-        .quad 0x3ff172b83c7d517b
-        .quad 0x3ff2387a6e756238
-        .quad 0x3ff306fe0a31b715
-        .quad 0x3ff3dea64c123422
-        .quad 0x3ff4bfdad5362a27
-        .quad 0x3ff5ab07dd485429
-        .quad 0x3ff6a09e667f3bcd
-        .quad 0x3ff7a11473eb0187
-        .quad 0x3ff8ace5422aa0db
-        .quad 0x3ff9c49182a3f090
-        .quad 0x3ffae89f995ad3ad
-        .quad 0x3ffc199bdd85529c
-        .quad 0x3ffd5818dcfba487
-        .quad 0x3ffea4afa2a490da
-        /*== log2(e) ==*/
-        .align 64
-        .quad 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371
-        /*== Shifter=2^(52-4)*1.5 ==*/
-        .align 64
-        .quad 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0
-        /*== L2H = log(2)_high ==*/
-        .align 64
-        .quad 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff
-        /*== L2L = log(2)_low ==*/
-        .align 64
-        .quad 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21
-        /*== EMask ==*/
-        .align 64
-        .quad 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff
-        /*== poly_coeff6 ==*/
-        .align 64
-        .quad 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020
-        /*== poly_coeff5 ==*/
-        .align 64
-        .quad 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424
-        /*== poly_coeff4 ==*/
-        .align 64
-        .quad 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d
-        /*== poly_coeff3 ==*/
-        .align 64
-        .quad 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8
-        /*== poly_coeff2 ==*/
-        .align 64
-        .quad 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25
-        /*== poly_coeff1 ==*/
-        .align 64
-        .quad 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2
-        /*== AbsMask ==*/
-        .align 64
-        .quad 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff
-        /*== Threshold ==*/
-        .align 64
-        .quad 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41
-        .align 64
-        .type	__svml_dexp10_data_internal_avx512,@object
-        .size	__svml_dexp10_data_internal_avx512,.-__svml_dexp10_data_internal_avx512
+	/* Exp_tbl_H */
+	.quad	0x3ff0000000000000
+	.quad	0x3ff0b5586cf9890f
+	.quad	0x3ff172b83c7d517b
+	.quad	0x3ff2387a6e756238
+	.quad	0x3ff306fe0a31b715
+	.quad	0x3ff3dea64c123422
+	.quad	0x3ff4bfdad5362a27
+	.quad	0x3ff5ab07dd485429
+	.quad	0x3ff6a09e667f3bcd
+	.quad	0x3ff7a11473eb0187
+	.quad	0x3ff8ace5422aa0db
+	.quad	0x3ff9c49182a3f090
+	.quad	0x3ffae89f995ad3ad
+	.quad	0x3ffc199bdd85529c
+	.quad	0x3ffd5818dcfba487
+	.quad	0x3ffea4afa2a490da
+	/* log2(e) */
+	.align	64
+	.quad	0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371, 0x400A934F0979A371
+	/* Shifter=2^(52-4)*1.5 */
+	.align	64
+	.quad	0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0, 0x42f8000000003ff0
+	/* L2H = log(2)_high */
+	.align	64
+	.quad	0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff, 0x3fd34413509f79ff
+	/* L2L = log(2)_low */
+	.align	64
+	.quad	0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21, 0xbc49dc1da994fd21
+	/* EMask */
+	.align	64
+	.quad	0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff, 0xbfffffffffffffff
+	/* poly_coeff6 */
+	.align	64
+	.quad	0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020, 0x3fcb137ed8ac2020
+	/* poly_coeff5 */
+	.align	64
+	.quad	0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424, 0x3fe141a8e24f9424
+	/* poly_coeff4 */
+	.align	64
+	.quad	0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d, 0x3ff2bd77a0926c9d
+	/* poly_coeff3 */
+	.align	64
+	.quad	0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8, 0x40004705908704c8
+	/* poly_coeff2 */
+	.align	64
+	.quad	0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25, 0x40053524c73dfe25
+	/* poly_coeff1 */
+	.align	64
+	.quad	0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2, 0x40026bb1bbb554c2
+	/* AbsMask */
+	.align	64
+	.quad	0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff, 0x7fffffffffffffff
+	/* Threshold */
+	.align	64
+	.quad	0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41, 0x40733A7146F72A41
+	.align	64
+	.type	__svml_dexp10_data_internal_avx512, @object
+	.size	__svml_dexp10_data_internal_avx512, .-__svml_dexp10_data_internal_avx512