public inbox for libc-alpha@sourceware.org
 help / color / mirror / Atom feed
* [PATCH v1] x86: Optimize svml_s_tanhf_core_{sse4|avx2|avx512}.S
@ 2022-01-30  4:36 Noah Goldstein
  2022-02-01 20:02 ` Sunil Pandey
  0 siblings, 1 reply; 9+ messages in thread
From: Noah Goldstein @ 2022-01-30  4:36 UTC (permalink / raw)
  To: libc-alpha

No bug.

Optimizations are:
    1. Reduce code size
        avx512: -56 bytes
        avx2:   -70 bytes
        sse4:   -106 bytes
    2. Reduce rodata size
        avx512: -448 bytes
        avx2:   -32 bytes
        sse4:   -4k+ (shares rodata with avx2)
    3. Remove register save/restores and stack adjustment from the
       fast path.
    4. Slightly better instruction selection where possible.

This results in roughly a 15% performance improvement for all
functions.

Results from geomean of 40 benchtest runs:
       Function, New Time, Old Time, New / Old
 _ZGVbN4v_tanhf,     3.28,    3.852,     0.852
 _ZGVcN8v_tanhf,    3.556,    4.192,     0.848
 _ZGVdN8v_tanhf,     2.13,    2.486,     0.857
_ZGVeN16v_tanhf,    0.658,    0.762,     0.864
---
 .../multiarch/svml_s_tanhf16_core_avx512.S    | 585 +++++------
 .../fpu/multiarch/svml_s_tanhf4_core_sse4.S   | 871 +++--------------
 .../fpu/multiarch/svml_s_tanhf8_core_avx2.S   | 908 +++---------------
 3 files changed, 581 insertions(+), 1783 deletions(-)

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf16_core_avx512.S
index 8954a5f658..6a2f0c1392 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf16_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf16_core_avx512.S
@@ -70,312 +70,323 @@
  *
  */
 
-/* Offsets for data table __svml_stanh_data_internal
- */
-#define _sC                           	0
-#define _sP0                          	128
-#define _sP2                          	256
-#define _sP3                          	384
-#define _sP4                          	512
-#define _sP5                          	640
-#define _sP6                          	768
-#define _sP7                          	896
-#define _iExpMantMask_UISA            	1024
-#define _iMinIdxOfsMask_UISA          	1088
-#define _iMaxIdxMask_UISA             	1152
-#define _sSignMask                    	1216
-#define _sAbsMask                     	1280
-#define _iExpMantMask                 	1344
-#define _iExpMask                     	1408
-#define _iMinIdxOfsMask               	1472
-#define _iMaxIdxMask                  	1536
-
 #include <sysdep.h>
 
+#define TANHF_DATA(offset)	((offset) + __svml_stanh_data_internal)
+
+/* Offsets for data table __svml_stanh_data_internal.  */
+#define _iExpMantMask_UISA	0
+#define _iMinIdxOfsMask_UISA	4
+#define _iMaxIdxMask_UISA	8
+#define _iExpMask	12
+#define _sSignMask	64
+#define _sC_lo	128
+#define _sC_hi	192
+#define _sP7_lo	256
+#define _sP7_hi	320
+#define _sP6_lo	384
+#define _sP6_hi	448
+#define _sP5_lo	512
+#define _sP5_hi	576
+#define _sP4_lo	640
+#define _sP4_hi	704
+#define _sP3_lo	768
+#define _sP3_hi	832
+#define _sP2_lo	896
+#define _sP2_hi	960
+#define _sP0_lo	1024
+#define _sP0_hi	1088
+
         .text
 	.section .text.exex512,"ax",@progbits
 ENTRY(_ZGVeN16v_tanhf_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
-        vmovaps   %zmm0, %zmm1
-        vmovups   __svml_stanh_data_internal(%rip), %zmm9
-        vmovups   _sP6+__svml_stanh_data_internal(%rip), %zmm11
-        vmovups   _sP5+__svml_stanh_data_internal(%rip), %zmm12
-        vmovups   _sP4+__svml_stanh_data_internal(%rip), %zmm13
-        vmovups   _sP3+__svml_stanh_data_internal(%rip), %zmm14
-        vmovups   _sP2+__svml_stanh_data_internal(%rip), %zmm15
-        vpternlogd $255, %zmm2, %zmm2, %zmm2
-        vandps    _sAbsMask+__svml_stanh_data_internal(%rip), %zmm1, %zmm8
-        vandps    _sSignMask+__svml_stanh_data_internal(%rip), %zmm1, %zmm0
-
-/* Here huge arguments, INF and NaNs are filtered out to callout. */
-        vpandd    _iExpMantMask_UISA+__svml_stanh_data_internal(%rip), %zmm1, %zmm3
-        vpsubd    _iMinIdxOfsMask_UISA+__svml_stanh_data_internal(%rip), %zmm3, %zmm4
-        vpcmpd    $2, _iExpMask+__svml_stanh_data_internal(%rip), %zmm3, %k1
+	/* Here huge arguments, INF and NaNs are filtered out to callout.  */
+	vpandd	TANHF_DATA(_iExpMantMask_UISA)(%rip) {1to16}, %zmm0, %zmm1
+	vpsubd	TANHF_DATA(_iMinIdxOfsMask_UISA)(%rip) {1to16}, %zmm1, %zmm2
 
-/*
- *  small table specific variables *
- *  Constant loading
- */
-        vpxord    %zmm5, %zmm5, %zmm5
-
-/* if VMIN, VMAX is defined for I type */
-        vpmaxsd   %zmm5, %zmm4, %zmm6
-        vpminsd   _iMaxIdxMask_UISA+__svml_stanh_data_internal(%rip), %zmm6, %zmm7
-        vpsrld    $21, %zmm7, %zmm10
-        vmovups   _sP7+__svml_stanh_data_internal(%rip), %zmm4
-        vpermt2ps _sC+64+__svml_stanh_data_internal(%rip), %zmm10, %zmm9
-        vpermt2ps _sP6+64+__svml_stanh_data_internal(%rip), %zmm10, %zmm11
-        vpermt2ps _sP7+64+__svml_stanh_data_internal(%rip), %zmm10, %zmm4
-        vpermt2ps _sP5+64+__svml_stanh_data_internal(%rip), %zmm10, %zmm12
-        vpermt2ps _sP4+64+__svml_stanh_data_internal(%rip), %zmm10, %zmm13
-        vpermt2ps _sP3+64+__svml_stanh_data_internal(%rip), %zmm10, %zmm14
-        vpermt2ps _sP2+64+__svml_stanh_data_internal(%rip), %zmm10, %zmm15
-        vpandnd   %zmm3, %zmm3, %zmm2{%k1}
-        vptestmd  %zmm2, %zmm2, %k0
-        vmovups   _sP0+__svml_stanh_data_internal(%rip), %zmm3
-        vsubps    {rn-sae}, %zmm9, %zmm8, %zmm2
-        kmovw     %k0, %edx
-        vfmadd213ps {rn-sae}, %zmm11, %zmm2, %zmm4
-        vpermt2ps _sP0+64+__svml_stanh_data_internal(%rip), %zmm10, %zmm3
-        vfmadd213ps {rn-sae}, %zmm12, %zmm2, %zmm4
-        vfmadd213ps {rn-sae}, %zmm13, %zmm2, %zmm4
-        vfmadd213ps {rn-sae}, %zmm14, %zmm2, %zmm4
-        vfmadd213ps {rn-sae}, %zmm15, %zmm2, %zmm4
-        vfmadd213ps {rn-sae}, %zmm3, %zmm2, %zmm4
-        vorps     %zmm0, %zmm4, %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
- */
+	/* Selection arguments between [0, 0x03e00000] into zmm3.  */
+	vpxord	%zmm3, %zmm3, %zmm3
+	vpmaxsd	%zmm3, %zmm2, %zmm3
+	vpminsd	TANHF_DATA(_iMaxIdxMask_UISA)(%rip) {1to16}, %zmm3, %zmm3
 
-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
- */
+	/* Setup permute indices in zmm3.  */
+	vpsrld	$21, %zmm3, %zmm3
+
+	/* Store if there are any special cases in k1.  */
+	vpcmpd	$6, TANHF_DATA(_iExpMask)(%rip) {1to16}, %zmm1, %k1
+
+
+	/* Store absolute values of inputs in zmm1.  */
+	vmovaps	TANHF_DATA(_sSignMask)(%rip), %zmm4
+	vandnps	%zmm0, %zmm4, %zmm1
+
+	vmovaps	TANHF_DATA(_sC_lo)(%rip), %zmm5
+	vpermt2ps TANHF_DATA(_sC_hi)(%rip), %zmm3, %zmm5
+	vsubps	{rn-sae}, %zmm5, %zmm1, %zmm1
+
+	vmovaps	TANHF_DATA(_sP7_lo)(%rip), %zmm2
+	vpermt2ps TANHF_DATA(_sP7_hi)(%rip), %zmm3, %zmm2
 
+	vmovaps	TANHF_DATA(_sP6_lo)(%rip), %zmm5
+	vpermt2ps TANHF_DATA(_sP6_hi)(%rip), %zmm3, %zmm5
+
+	vmovaps	TANHF_DATA(_sP5_lo)(%rip), %zmm6
+	vpermt2ps TANHF_DATA(_sP5_hi)(%rip), %zmm3, %zmm6
+
+	vfmadd213ps {rn-sae}, %zmm5, %zmm1, %zmm2
+	vfmadd213ps {rn-sae}, %zmm6, %zmm1, %zmm2
+
+	vmovaps	TANHF_DATA(_sP4_lo)(%rip), %zmm7
+	vpermt2ps TANHF_DATA(_sP4_hi)(%rip), %zmm3, %zmm7
+
+	vmovaps	TANHF_DATA(_sP3_lo)(%rip), %zmm8
+	vpermt2ps TANHF_DATA(_sP3_hi)(%rip), %zmm3, %zmm8
+
+	vfmadd213ps {rn-sae}, %zmm7, %zmm1, %zmm2
+	vfmadd213ps {rn-sae}, %zmm8, %zmm1, %zmm2
+
+	vmovaps	TANHF_DATA(_sP2_lo)(%rip), %zmm9
+	vpermt2ps TANHF_DATA(_sP2_hi)(%rip), %zmm3, %zmm9
+
+	vmovaps	TANHF_DATA(_sP0_lo)(%rip), %zmm10
+	vpermt2ps TANHF_DATA(_sP0_hi)(%rip), %zmm3, %zmm10
+
+	vfmadd213ps {rn-sae}, %zmm9, %zmm1, %zmm2
+	vfmadd213ps {rn-sae}, %zmm10, %zmm1, %zmm2
+
+	kmovw	%k1, %edx
+	testl	%edx, %edx
+
+	/* Go to special inputs processing branch.  */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	/* Wait until after branch of write over zmm0.  */
+	vpternlogd $0xec, %zmm4, %zmm2, %zmm0
+
+	/* No stack restoration on the fastpath.  */
+	ret
+
+	/* 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
- */
+	pushq	%rbp
+	/* Need to callee save registers to preserve state across tanhf calls.
+	 */
+	pushq	%r13
+	pushq	%r12
+	movq	%rsp, %rbp
 
-L(RANGEMASK_CHECK):
-        btl       %r12d, %r13d
+	/* Align stack and make room for 2x zmm vectors.  */
+	andq	$-64, %rsp
+	addq	$-128, %rsp
 
-/* Call scalar math function */
-        jc        L(SCALAR_MATH_CALL)
-                                # LOE rbx r15 r12d r13d
+	/* Save all already computed inputs.  */
+	vpternlogd $0xec, %zmm4, %zmm2, %zmm2
+	vmovaps	%zmm2, (%rsp)
+	/* Save origional input (zmm0 unchanged up to this point).  */
+	vmovaps	%zmm0, 64(%rsp)
 
-/* Special inputs
- * processing loop
- */
+	vzeroupper
 
+	/* edx has 1s where there was a special value that needs to be handled
+	   by a tanhf call.  */
+	movl	%edx, %r13d
 L(SPECIAL_VALUES_LOOP):
-        incl      %r12d
-        cmpl      $16, %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
- */
+	/* use r12 as index for special value that is saved across calls to
+	   tanhf. We technically don't need a callee save register here as offset
+	   to rsp is always [0, 56] so we can restore rsp by realigning to 64.
+	   Essentially the tradeoff is 1 extra save/restore vs 2 extra instructions
+	   in the loop.  */
+	xorl	%r12d, %r12d
+	tzcntl	%r13d, %r12d
 
-L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movss     64(%rsp,%r14,4), %xmm0
-        call      tanhf@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
+	/* Scalar math fucntion call to process special input.  */
+	movss	64(%rsp, %r12, 4), %xmm0
+	call	tanhf@PLT
 
-        movss     %xmm0, 128(%rsp,%r14,4)
+	/* No good way to avoid the store-forwarding fault this will cause on
+	   return. `lfence` avoids the SF fault but at greater cost as it
+	   serialized stack/callee save restoration.  */
+	movss	%xmm0, (%rsp, %r12, 4)
 
-/* Process special inputs in loop */
-        jmp       L(SPECIAL_VALUES_LOOP)
-                                # LOE rbx r15 r12d r13d
-END(_ZGVeN16v_tanhf_skx)
+	blsr	%r13d, %r13d
+	jnz	L(SPECIAL_VALUES_LOOP)
 
-        .section .rodata, "a"
-        .align 64
+	/* All results have been written to 64(%rsp).  */
+	vmovaps	(%rsp), %zmm0
+	/* Restore rsp.  */
+	movq	%rbp, %rsp
+	/* Restore callee save registers.  */
+	popq	%r12
+	popq	%r13
+	popq	%rbp
+	ret
+END(_ZGVeN16v_tanhf_skx)
 
+	.section .rodata, "a"
+	.align	16
 #ifdef __svml_stanh_data_internal_typedef
-typedef unsigned int VUINT32;
-typedef struct
-{
-        __declspec(align(64)) VUINT32 _sC[32][1];
-        __declspec(align(64)) VUINT32 _sP0[32][1];
-        __declspec(align(64)) VUINT32 _sP2[32][1];
-        __declspec(align(64)) VUINT32 _sP3[32][1];
-        __declspec(align(64)) VUINT32 _sP4[32][1];
-        __declspec(align(64)) VUINT32 _sP5[32][1];
-        __declspec(align(64)) VUINT32 _sP6[32][1];
-        __declspec(align(64)) VUINT32 _sP7[32][1];
-        __declspec(align(64)) VUINT32 _iExpMantMask_UISA[16][1];
-        __declspec(align(64)) VUINT32 _iMinIdxOfsMask_UISA[16][1];
-        __declspec(align(64)) VUINT32 _iMaxIdxMask_UISA[16][1];
-        __declspec(align(64)) VUINT32 _sSignMask[16][1];
-        __declspec(align(64)) VUINT32 _sAbsMask[16][1];
-        __declspec(align(64)) VUINT32 _iExpMantMask[16][1];
-        __declspec(align(64)) VUINT32 _iExpMask[16][1];
-        __declspec(align(64)) VUINT32 _iMinIdxOfsMask[16][1];
-        __declspec(align(64)) VUINT32 _iMaxIdxMask[16][1];
-} __svml_stanh_data_internal;
+	typedef	unsigned int VUINT32;
+	typedef	struct
+	{
+	__declspec (align(4))VUINT32 _iExpMantMask_UISA[1][1];
+	__declspec (align(4))VUINT32 _iMinIdxOfsMask_UISA[1][1];
+	__declspec (align(4))VUINT32 _iMaxIdxMask_UISA[1][1];
+	__declspec (align(4))VUINT32 _iExpMask[1][1];
+	__declspec (align(64))VUINT32 _sSignMask[16][1];
+	__declspec (align(64))VUINT32 _sC_lo[16][1];
+	__declspec (align(64))VUINT32 _sC_hi[16][1];
+	__declspec (align(64))VUINT32 _sP7_lo[16][1];
+	__declspec (align(64))VUINT32 _sP7_hi[16][1];
+	__declspec (align(64))VUINT32 _sP6_lo[16][1];
+	__declspec (align(64))VUINT32 _sP6_hi[16][1];
+	__declspec (align(64))VUINT32 _sP5_lo[16][1];
+	__declspec (align(64))VUINT32 _sP5_hi[16][1];
+	__declspec (align(64))VUINT32 _sP4_lo[16][1];
+	__declspec (align(64))VUINT32 _sP4_hi[16][1];
+	__declspec (align(64))VUINT32 _sP3_lo[16][1];
+	__declspec (align(64))VUINT32 _sP3_hi[16][1];
+	__declspec (align(64))VUINT32 _sP2_lo[16][1];
+	__declspec (align(64))VUINT32 _sP2_hi[16][1];
+	__declspec (align(64))VUINT32 _sP0_lo[16][1];
+	__declspec (align(64))VUINT32 _sP0_hi[16][1];
+	}__svml_stanh_data_internal;
 #endif
+
 __svml_stanh_data_internal:
-        /*== _sC ==*/
-        .long 0x00000000, 0x3d700000, 0x3d900000, 0x3db00000
-        .long 0x3dd00000, 0x3df00000, 0x3e100000, 0x3e300000
-        .long 0x3e500000, 0x3e700000, 0x3e900000, 0x3eb00000
-        .long 0x3ed00000, 0x3ef00000, 0x3f100000, 0x3f300000
-        .long 0x3f500000, 0x3f700000, 0x3f900000, 0x3fb00000
-        .long 0x3fd00000, 0x3ff00000, 0x40100000, 0x40300000
-        .long 0x40500000, 0x40700000, 0x40900000, 0x40b00000
-        .long 0x40d00000, 0x40f00000, 0x41100000, 0x00000000
-        /*== p0 ==*/
-        .align 64
-        .long 0x00000000, 0x3d6fb9c9, 0x3d8fc35f, 0x3daf9169
-        .long 0x3dcf49ab, 0x3deee849, 0x3e0f0ee8, 0x3e2e4984
-        .long 0x3e4d2f8e, 0x3e6bb32e, 0x3e8c51cd, 0x3ea96163
-        .long 0x3ec543f1, 0x3edfd735, 0x3f028438, 0x3f18abf0
-        .long 0x3f2bc480, 0x3f3bec1c, 0x3f4f2e5b, 0x3f613c53
-        .long 0x3f6ce37d, 0x3f743c4f, 0x3f7a5feb, 0x3f7dea85
-        .long 0x3f7f3b3d, 0x3f7fb78c, 0x3f7fefd4, 0x3f7ffdd0
-        .long 0x3f7fffb4, 0x3f7ffff6, 0x3f7fffff, 0x3f800000
-        /*== p2 ==*/
-        .align 64
-        .long 0x3f800000, 0x3f7f1f84, 0x3f7ebd11, 0x3f7e1e5f
-        .long 0x3f7d609f, 0x3f7c842d, 0x3f7b00e5, 0x3f789580
-        .long 0x3f75b8ad, 0x3f726fd9, 0x3f6cc59b, 0x3f63fb92
-        .long 0x3f59ff97, 0x3f4f11d7, 0x3f3d7573, 0x3f24f360
-        .long 0x3f0cbfe7, 0x3eec1a69, 0x3eb0a801, 0x3e6753a2
-        .long 0x3e132f1a, 0x3db7e7d3, 0x3d320845, 0x3c84d3d4
-        .long 0x3bc477b7, 0x3b10d3da, 0x3a01601e, 0x388c1a3b
-        .long 0x3717b0da, 0x35a43bce, 0x338306c6, 0x00000000
-        /*== p3 ==*/
-        .align 64
-        .long 0xb0343c7b, 0xbd6ee69d, 0xbd8f0da7, 0xbdae477d
-        .long 0xbdcd2a1f, 0xbdeba80d, 0xbe0c443b, 0xbe293cf3
-        .long 0xbe44f282, 0xbe5f3651, 0xbe81c7c0, 0xbe96d7ca
-        .long 0xbea7fb8e, 0xbeb50e9e, 0xbec12efe, 0xbec4be92
-        .long 0xbebce070, 0xbead510e, 0xbe8ef7d6, 0xbe4b8704
-        .long 0xbe083237, 0xbdaf7449, 0xbd2e1ec4, 0xbc83bf06
-        .long 0xbbc3e0b5, 0xbb10aadc, 0xba0157db, 0xb88c18f2
-        .long 0xb717b096, 0xb5a43bae, 0xb383012c, 0x00000000
-        /*== p4 ==*/
-        .align 64
-        .long 0xbeaaaaa5, 0xbeab0612, 0xbea7f01f, 0xbea4e120
-        .long 0xbea387b7, 0xbea15962, 0xbe9d57f7, 0xbe976b5a
-        .long 0xbe90230d, 0xbe880dff, 0xbe7479b3, 0xbe4c3d88
-        .long 0xbe212482, 0xbdeb8cba, 0xbd5e78ad, 0x3c6b5e6e
-        .long 0x3d839143, 0x3dc21ee1, 0x3de347af, 0x3dcbec96
-        .long 0x3d99ef2d, 0x3d542ea1, 0x3cdde701, 0x3c2cca67
-        .long 0x3b81cb27, 0x3ac073a1, 0x39ac3032, 0x383a94d9
-        .long 0x36ca081d, 0x355abd4c, 0x332b3cb6, 0x00000000
-        /*== p5 ==*/
-        .align 64
-        .long 0xb76dd6b9, 0xbe1c276d, 0x3c1dcf2f, 0x3dc1a78d
-        .long 0x3d96f985, 0x3da2b61b, 0x3dc13397, 0x3dd2f670
-        .long 0x3df48a0a, 0x3e06c5a8, 0x3e1a3aba, 0x3e27c405
-        .long 0x3e2e78d0, 0x3e2c3e44, 0x3e1d3097, 0x3df4a8f4
-        .long 0x3da38508, 0x3d31416a, 0x3b562657, 0xbcaeeac9
-        .long 0xbcce9419, 0xbcaaeac4, 0xbc49e7d0, 0xbba71ddd
-        .long 0xbb003b0e, 0xba3f9a05, 0xb92c08a7, 0xb7ba9232
-        .long 0xb64a0b0f, 0xb4dac169, 0xb2ab78ac, 0x00000000
-        /*== p6 ==*/
-        .align 64
-        .long 0x3e0910e9, 0x43761143, 0x4165ecdc, 0xc190f756
-        .long 0xc08c097d, 0xc02ba813, 0xbf7f6bda, 0x3f2b1dc0
-        .long 0x3ece105d, 0x3f426a94, 0xbadb0dc4, 0x3da43b17
-        .long 0xbd51ab88, 0xbcaea23d, 0xbd3b6d8d, 0xbd6caaad
-        .long 0xbd795bed, 0xbd5fddda, 0xbd038f3b, 0xbc1cad63
-        .long 0x3abb4766, 0x3b95f10b, 0x3b825873, 0x3afaea66
-        .long 0x3a49f878, 0x39996bf3, 0x388f3e6c, 0x371bb0e3
-        .long 0x35a8a5e6, 0x34369b17, 0x322487b0, 0x00000000
-        /*== p7 ==*/
-        .align 64
-        .long 0xbc0e2f66, 0x460bda12, 0x43d638ef, 0xc3e11c3e
-        .long 0xc2baa4e9, 0xc249da2d, 0xc1859b82, 0x40dd5b57
-        .long 0x40494640, 0x40c730a8, 0xbf0f160e, 0x3e30e76f
-        .long 0xbea81387, 0xbdb26a1c, 0xbd351e57, 0xbb4c01a0
-        .long 0x3c1d7bfb, 0x3c722cd1, 0x3c973f1c, 0x3c33a31b
-        .long 0x3b862ef4, 0x3a27b3d0, 0xba3b5907, 0xba0efc22
-        .long 0xb97f9f0f, 0xb8c8af50, 0xb7bdddfb, 0xb64f2950
-        .long 0xb4e085b1, 0xb3731dfa, 0xb15a1f04, 0x00000000
-        .align 64
-        .long 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000, 0x7fe00000           /* _iExpMantMask_UISA     */
-        .align 64
-        .long 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000, 0x3d400000           /* _iMinIdxOfsMask_UISA   */
-        .align 64
-        .long 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000, 0x03e00000           /* _iMaxIdxMask_UISA      */
-        .align 64
-        .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000           /* _sSignMask        */
-        .align 64
-        .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff           /* _sAbsMask         */
-        .align 64
-        .long 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000           /* _iExpMantMask     */
-        .align 64
-        .long 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000           /* _iExpMask         */
-        .align 64
-        .long 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000           /* _iMinIdxOfsMask   */
-        .align 64
-        .long 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000           /* _iMaxIdxMask      */
-        .align 64
-        .type	__svml_stanh_data_internal,@object
-        .size	__svml_stanh_data_internal,.-__svml_stanh_data_internal
+	.align	4
+	/* _iExpMantMask_UISA.  */
+	.long	0x7fe00000
+
+	.align	4
+	/* _iMinIdxOfsMask_UISA.  */
+	.long	0x3d400000
+
+	.align	4
+	/* _iMaxIdxMask_UISA.  */
+	.long	0x03e00000
+
+	.align	4
+	/* _iExpMask.  */
+	.long	0x7f000000
+
+	.align	64
+	/* _sSignMask.  */
+	.long	0x80000000, 0x80000000, 0x80000000, 0x80000000
+	.long	0x80000000, 0x80000000, 0x80000000, 0x80000000
+	.long	0x80000000, 0x80000000, 0x80000000, 0x80000000
+	.long	0x80000000, 0x80000000, 0x80000000, 0x80000000
+
+	.align	64
+	/* _sC_lo.  */
+	.long	0x00000000, 0x3d700000, 0x3d900000, 0x3db00000
+	.long	0x3dd00000, 0x3df00000, 0x3e100000, 0x3e300000
+	.long	0x3e500000, 0x3e700000, 0x3e900000, 0x3eb00000
+	.long	0x3ed00000, 0x3ef00000, 0x3f100000, 0x3f300000
+
+	.align	64
+	/* _sC_hi.  */
+	.long	0x3f500000, 0x3f700000, 0x3f900000, 0x3fb00000
+	.long	0x3fd00000, 0x3ff00000, 0x40100000, 0x40300000
+	.long	0x40500000, 0x40700000, 0x40900000, 0x40b00000
+	.long	0x40d00000, 0x40f00000, 0x41100000, 0x00000000
+
+	.align	64
+	/* _sP7_lo.  */
+	.long	0xbc0e2f66, 0x460bda12, 0x43d638ef, 0xc3e11c3e
+	.long	0xc2baa4e9, 0xc249da2d, 0xc1859b82, 0x40dd5b57
+	.long	0x40494640, 0x40c730a8, 0xbf0f160e, 0x3e30e76f
+	.long	0xbea81387, 0xbdb26a1c, 0xbd351e57, 0xbb4c01a0
+
+	.align	64
+	/* _sP7_hi.  */
+	.long	0x3c1d7bfb, 0x3c722cd1, 0x3c973f1c, 0x3c33a31b
+	.long	0x3b862ef4, 0x3a27b3d0, 0xba3b5907, 0xba0efc22
+	.long	0xb97f9f0f, 0xb8c8af50, 0xb7bdddfb, 0xb64f2950
+	.long	0xb4e085b1, 0xb3731dfa, 0xb15a1f04, 0x00000000
+
+	.align	64
+	/* _sP6_lo.  */
+	.long	0x3e0910e9, 0x43761143, 0x4165ecdc, 0xc190f756
+	.long	0xc08c097d, 0xc02ba813, 0xbf7f6bda, 0x3f2b1dc0
+	.long	0x3ece105d, 0x3f426a94, 0xbadb0dc4, 0x3da43b17
+	.long	0xbd51ab88, 0xbcaea23d, 0xbd3b6d8d, 0xbd6caaad
+
+	.align	64
+	/* _sP6_hi.  */
+	.long	0xbd795bed, 0xbd5fddda, 0xbd038f3b, 0xbc1cad63
+	.long	0x3abb4766, 0x3b95f10b, 0x3b825873, 0x3afaea66
+	.long	0x3a49f878, 0x39996bf3, 0x388f3e6c, 0x371bb0e3
+	.long	0x35a8a5e6, 0x34369b17, 0x322487b0, 0x00000000
+
+	.align	64
+	/* _sP5_lo.  */
+	.long	0xb76dd6b9, 0xbe1c276d, 0x3c1dcf2f, 0x3dc1a78d
+	.long	0x3d96f985, 0x3da2b61b, 0x3dc13397, 0x3dd2f670
+	.long	0x3df48a0a, 0x3e06c5a8, 0x3e1a3aba, 0x3e27c405
+	.long	0x3e2e78d0, 0x3e2c3e44, 0x3e1d3097, 0x3df4a8f4
+
+	.align	64
+	/* _sP5_hi.  */
+	.long	0x3da38508, 0x3d31416a, 0x3b562657, 0xbcaeeac9
+	.long	0xbcce9419, 0xbcaaeac4, 0xbc49e7d0, 0xbba71ddd
+	.long	0xbb003b0e, 0xba3f9a05, 0xb92c08a7, 0xb7ba9232
+	.long	0xb64a0b0f, 0xb4dac169, 0xb2ab78ac, 0x00000000
+
+	.align	64
+	/* _sP4_lo.  */
+	.long	0xbeaaaaa5, 0xbeab0612, 0xbea7f01f, 0xbea4e120
+	.long	0xbea387b7, 0xbea15962, 0xbe9d57f7, 0xbe976b5a
+	.long	0xbe90230d, 0xbe880dff, 0xbe7479b3, 0xbe4c3d88
+	.long	0xbe212482, 0xbdeb8cba, 0xbd5e78ad, 0x3c6b5e6e
+
+	.align	64
+	/* _sP4_hi.  */
+	.long	0x3d839143, 0x3dc21ee1, 0x3de347af, 0x3dcbec96
+	.long	0x3d99ef2d, 0x3d542ea1, 0x3cdde701, 0x3c2cca67
+	.long	0x3b81cb27, 0x3ac073a1, 0x39ac3032, 0x383a94d9
+	.long	0x36ca081d, 0x355abd4c, 0x332b3cb6, 0x00000000
+
+	.align	64
+	/* _sP3_lo.  */
+	.long	0xb0343c7b, 0xbd6ee69d, 0xbd8f0da7, 0xbdae477d
+	.long	0xbdcd2a1f, 0xbdeba80d, 0xbe0c443b, 0xbe293cf3
+	.long	0xbe44f282, 0xbe5f3651, 0xbe81c7c0, 0xbe96d7ca
+	.long	0xbea7fb8e, 0xbeb50e9e, 0xbec12efe, 0xbec4be92
+
+	.align	64
+	/* _sP3_hi.  */
+	.long	0xbebce070, 0xbead510e, 0xbe8ef7d6, 0xbe4b8704
+	.long	0xbe083237, 0xbdaf7449, 0xbd2e1ec4, 0xbc83bf06
+	.long	0xbbc3e0b5, 0xbb10aadc, 0xba0157db, 0xb88c18f2
+	.long	0xb717b096, 0xb5a43bae, 0xb383012c, 0x00000000
+
+	.align	64
+	/* _sP2_lo.  */
+	.long	0x3f800000, 0x3f7f1f84, 0x3f7ebd11, 0x3f7e1e5f
+	.long	0x3f7d609f, 0x3f7c842d, 0x3f7b00e5, 0x3f789580
+	.long	0x3f75b8ad, 0x3f726fd9, 0x3f6cc59b, 0x3f63fb92
+	.long	0x3f59ff97, 0x3f4f11d7, 0x3f3d7573, 0x3f24f360
+
+	.align	64
+	/* _sP2_hi.  */
+	.long	0x3f0cbfe7, 0x3eec1a69, 0x3eb0a801, 0x3e6753a2
+	.long	0x3e132f1a, 0x3db7e7d3, 0x3d320845, 0x3c84d3d4
+	.long	0x3bc477b7, 0x3b10d3da, 0x3a01601e, 0x388c1a3b
+	.long	0x3717b0da, 0x35a43bce, 0x338306c6, 0x00000000
+
+	.align	64
+	/* _sP0_lo.  */
+	.long	0x00000000, 0x3d6fb9c9, 0x3d8fc35f, 0x3daf9169
+	.long	0x3dcf49ab, 0x3deee849, 0x3e0f0ee8, 0x3e2e4984
+	.long	0x3e4d2f8e, 0x3e6bb32e, 0x3e8c51cd, 0x3ea96163
+	.long	0x3ec543f1, 0x3edfd735, 0x3f028438, 0x3f18abf0
+
+	.align	64
+	/* _sP0_hi.  */
+	.long	0x3f2bc480, 0x3f3bec1c, 0x3f4f2e5b, 0x3f613c53
+	.long	0x3f6ce37d, 0x3f743c4f, 0x3f7a5feb, 0x3f7dea85
+	.long	0x3f7f3b3d, 0x3f7fb78c, 0x3f7fefd4, 0x3f7ffdd0
+	.long	0x3f7fffb4, 0x3f7ffff6, 0x3f7fffff, 0x3f800000
+
+	.align	64
+	.type	__svml_stanh_data_internal, @object
+	.size	__svml_stanh_data_internal, .-__svml_stanh_data_internal
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf4_core_sse4.S b/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf4_core_sse4.S
index 50f753ffb3..716b06d640 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf4_core_sse4.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf4_core_sse4.S
@@ -70,763 +70,154 @@
  *
  */
 
-/* Offsets for data table __svml_stanh_data_internal
- */
-#define _dbP                          	0
-#define _sSignMask                    	4288
-#define _sAbsMask                     	4304
-#define _iExpMantMask                 	4320
-#define _iExpMask                     	4336
-#define _iMinIdxOfsMask               	4352
-#define _iMaxIdxMask                  	4368
 
 #include <sysdep.h>
 
+#define ONLY_DECL_OFFSET
+#include "svml_s_tanhf_rodata.S"
+
         .text
 	.section .text.sse4,"ax",@progbits
 ENTRY(_ZGVbN4v_tanhf_sse4)
-        subq      $72, %rsp
-        cfi_def_cfa_offset(80)
-        movaps    %xmm0, %xmm5
+	/* Save copy of input in xmm12.  */
+	movaps	%xmm0, %xmm12
 
-/* Here huge arguments, INF and NaNs are filtered out to callout. */
-        movdqu    _iExpMantMask+__svml_stanh_data_internal(%rip), %xmm9
-        lea       _dbP+16+__svml_stanh_data_internal(%rip), %r8
-        pand      %xmm5, %xmm9
+	/* Here huge arguments, INF and NaNs are filtered out to callout.  */
+	movdqu	TANHF_DATA(_iExpMantMask)(%rip), %xmm3
+	pand	%xmm0, %xmm3
 
-/* if VMIN, VMAX is defined for I type */
-        pxor      %xmm7, %xmm7
-        movdqa    %xmm9, %xmm6
-        psubd     _iMinIdxOfsMask+__svml_stanh_data_internal(%rip), %xmm9
 
-/*
- *  small table specific variables *
- *  Constant loading
- */
-        movdqu    _iMaxIdxMask+__svml_stanh_data_internal(%rip), %xmm10
-        movdqa    %xmm9, %xmm11
-        movdqa    %xmm9, %xmm8
-        pcmpgtd   %xmm10, %xmm11
-        pcmpgtd   %xmm7, %xmm8
-        movdqa    %xmm11, %xmm14
-        pand      %xmm8, %xmm9
-        andps     %xmm11, %xmm10
-        andnps    %xmm9, %xmm14
-        orps      %xmm10, %xmm14
-        psrld     $14, %xmm14
-        movd      %xmm14, %edx
-        pshufd    $1, %xmm14, %xmm12
-        pshufd    $2, %xmm14, %xmm13
-        movd      %xmm12, %ecx
-        pshufd    $3, %xmm14, %xmm15
-        movups    _sAbsMask+__svml_stanh_data_internal(%rip), %xmm3
-        movslq    %edx, %rdx
-        andps     %xmm5, %xmm3
-        movslq    %ecx, %rcx
-        pcmpgtd   _iExpMask+__svml_stanh_data_internal(%rip), %xmm6
-        movd      %xmm13, %esi
-        movups    -16(%rdx,%r8), %xmm2
-        movaps    %xmm2, %xmm0
-        movd      %xmm15, %edi
-        movmskps  %xmm6, %eax
-        movups    -16(%rcx,%r8), %xmm6
-        unpcklpd  %xmm6, %xmm0
-        unpckhpd  %xmm6, %xmm2
-        cvtps2pd  %xmm3, %xmm6
-        movhlps   %xmm3, %xmm3
-        cvtps2pd  %xmm3, %xmm3
-        movslq    %esi, %rsi
-        movslq    %edi, %rdi
-        movups    (%rcx,%r8), %xmm8
-        movups    (%rdx,%r8), %xmm12
-        movups    (%rsi,%r8), %xmm13
-        movaps    %xmm12, %xmm10
-        movups    (%rdi,%r8), %xmm9
-        movaps    %xmm13, %xmm11
-        unpckhpd  %xmm8, %xmm12
-        unpckhpd  %xmm9, %xmm13
-        mulpd     %xmm6, %xmm12
-        mulpd     %xmm3, %xmm13
-        unpcklpd  %xmm8, %xmm10
-        unpcklpd  %xmm9, %xmm11
-        addpd     %xmm10, %xmm12
-        addpd     %xmm11, %xmm13
-        mulpd     %xmm6, %xmm12
-        mulpd     %xmm3, %xmm13
-        addpd     %xmm2, %xmm12
-        movups    -16(%rsi,%r8), %xmm1
-        movups    -16(%rdi,%r8), %xmm7
-        movaps    %xmm1, %xmm14
-        unpckhpd  %xmm7, %xmm1
-        addpd     %xmm1, %xmm13
-        mulpd     %xmm12, %xmm6
-        mulpd     %xmm13, %xmm3
-        addpd     %xmm0, %xmm6
-        unpcklpd  %xmm7, %xmm14
-        addpd     %xmm14, %xmm3
-        cvtpd2ps  %xmm6, %xmm0
-        cvtpd2ps  %xmm3, %xmm1
-        movups    _sSignMask+__svml_stanh_data_internal(%rip), %xmm4
-        movlhps   %xmm1, %xmm0
-        andps     %xmm5, %xmm4
-        orps      %xmm4, %xmm0
-        testl     %eax, %eax
-
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx rbp r12 r13 r14 r15 eax xmm0 xmm5
-
-/* Restore registers
- * and exit the function
- */
+	/* Selection of arguments between [0, 0x04280000] into xmm3.  */
+	pxor	%xmm7, %xmm7
+	/* Save xmm3 for special values check at end.  */
+	movdqa	%xmm3, %xmm8
+	psubd	TANHF_DATA(_iMinIdxOfsMask)(%rip), %xmm3
+	pmaxsd	%xmm7, %xmm3
+	pminsd	TANHF_DATA(_iMaxIdxMask)(%rip), %xmm3
+	psrld	$14, %xmm3
 
-L(EXIT):
-        addq      $72, %rsp
-        cfi_def_cfa_offset(8)
-        ret
-        cfi_def_cfa_offset(80)
+	movq	%xmm3, %rcx
+	movl	%ecx, %edx
+	shrq	$32, %rcx
 
-/* Branch to process
- * special inputs
- */
+	/* xmm8 contains mask of special values.  */
+	pcmpgtd	TANHF_DATA(_iExpMask)(%rip), %xmm8
 
-L(SPECIAL_VALUES_BRANCH):
-        movups    %xmm5, 32(%rsp)
-        movups    %xmm0, 48(%rsp)
-                                # LOE rbx rbp r12 r13 r14 r15 eax
-
-        xorl      %edx, %edx
-        movq      %r12, 16(%rsp)
-        cfi_offset(12, -64)
-        movl      %edx, %r12d
-        movq      %r13, 8(%rsp)
-        cfi_offset(13, -72)
-        movl      %eax, %r13d
-        movq      %r14, (%rsp)
-        cfi_offset(14, -80)
-                                # LOE rbx rbp r15 r12d r13d
-
-/* Range mask
- * bits check
- */
+	pshufd	$0x0e, %xmm3, %xmm3
+	movq	%xmm3, %rdi
+	movl	%edi, %esi
+	shrq	$32, %rdi
 
-L(RANGEMASK_CHECK):
-        btl       %r12d, %r13d
+	movaps	TANHF_DATA(_sAbsMask)(%rip), %xmm1
+	andps	%xmm1, %xmm0
 
-/* Call scalar math function */
-        jc        L(SCALAR_MATH_CALL)
-                                # LOE rbx rbp r15 r12d r13d
+	leaq	TANHF_DATA(_lookupTable)(%rip), %rax
+	movups	(%rdx, %rax), %xmm2
+	movups	(%rcx, %rax), %xmm6
 
-/* Special inputs
- * processing loop
- */
+	movaps	%xmm2, %xmm4
+	movlhps	%xmm6, %xmm4
+	unpckhpd %xmm6, %xmm2
 
-L(SPECIAL_VALUES_LOOP):
-        incl      %r12d
-        cmpl      $4, %r12d
-
-/* Check bits in range mask */
-        jl        L(RANGEMASK_CHECK)
-                                # LOE rbx rbp r15 r12d r13d
-
-        movq      16(%rsp), %r12
-        cfi_restore(12)
-        movq      8(%rsp), %r13
-        cfi_restore(13)
-        movq      (%rsp), %r14
-        cfi_restore(14)
-        movups    48(%rsp), %xmm0
-
-/* Go to exit */
-        jmp       L(EXIT)
-        cfi_offset(12, -64)
-        cfi_offset(13, -72)
-        cfi_offset(14, -80)
-                                # LOE rbx rbp r12 r13 r14 r15 xmm0
-
-/* Scalar math fucntion call
- * to process special input
- */
+	cvtps2pd %xmm0, %xmm6
+	movhlps	%xmm0, %xmm0
+	cvtps2pd %xmm0, %xmm0
 
-L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movss     32(%rsp,%r14,4), %xmm0
-        call      tanhf@PLT
-                                # LOE rbx rbp r14 r15 r12d r13d xmm0
+	movups	16(%rdx, %rax), %xmm5
+	movups	16(%rsi, %rax), %xmm13
 
-        movss     %xmm0, 48(%rsp,%r14,4)
+	movaps	%xmm5, %xmm10
+	movaps	%xmm13, %xmm11
 
-/* Process special inputs in loop */
-        jmp       L(SPECIAL_VALUES_LOOP)
-                                # LOE rbx rbp r15 r12d r13d
-END(_ZGVbN4v_tanhf_sse4)
+	movups	16(%rcx, %rax), %xmm7
+	movups	16(%rdi, %rax), %xmm3
+
+	unpckhpd %xmm7, %xmm5
+	unpckhpd %xmm3, %xmm13
+
+	mulpd	%xmm6, %xmm5
+	mulpd	%xmm0, %xmm13
+
+	movlhps	%xmm7, %xmm10
+	movlhps	%xmm3, %xmm11
+
+	addpd	%xmm10, %xmm5
+	addpd	%xmm11, %xmm13
+
+	mulpd	%xmm6, %xmm5
+	mulpd	%xmm0, %xmm13
+
+	addpd	%xmm2, %xmm5
 
-        .section .rodata, "a"
-        .align 16
-
-#ifdef __svml_stanh_data_internal_typedef
-typedef unsigned int VUINT32;
-typedef struct
-{
-        __declspec(align(16)) VUINT32 _dbP[(134*4)][2];
-        __declspec(align(16)) VUINT32 _sSignMask[4][1];
-        __declspec(align(16)) VUINT32 _sAbsMask[4][1];
-        __declspec(align(16)) VUINT32 _iExpMantMask[4][1];
-        __declspec(align(16)) VUINT32 _iExpMask[4][1];
-        __declspec(align(16)) VUINT32 _iMinIdxOfsMask[4][1];
-        __declspec(align(16)) VUINT32 _iMaxIdxMask[4][1];
-} __svml_stanh_data_internal;
-#endif
-__svml_stanh_data_internal:
-        /* Pol_000:  err=7.93e-09, x in [0.0000000; 0.0312500]. */
-        .quad 0x0000000000000000  /* A00 = +0.000000000000000000000e-01 */
-        .quad 0x3FF00000022C70EB  /* A01 = +1.000000008097283510367e+00 */
-        .quad 0xBED00E878CFFA194  /* A02 = -3.828228912518614443549e-06 */
-        .quad 0xBFD551766D0607A9  /* A03 = -3.330970825846813476723e-01 */
-        .quad 0xBE53D60CE3E4C297  /* A00 = -1.847383956330407336230e-08 */
-        .quad 0x3FF000024177CF5C  /* A01 = +1.000002151235967140508e+00 */
-        .quad 0xBF1758BC94A51A25  /* A02 = -8.906031613262943753568e-05 */
-        .quad 0xBFD53EAE67E0D4F0  /* A03 = -3.319507612644221339337e-01 */
-        .quad 0xBE5A9E47EF32D6FE  /* A00 = -2.479020984039698285657e-08 */
-        .quad 0x3FF00002DA983057  /* A01 = +1.000002721676556793895e+00 */
-        .quad 0xBF1BD953509E94AA  /* A02 = -1.062352277175377670507e-04 */
-        .quad 0xBFD53BDB562EEDD5  /* A03 = -3.317783681520414806876e-01 */
-        .quad 0xBE6191BBE496D294  /* A00 = -3.272532162914017685901e-08 */
-        .quad 0x3FF0000390492017  /* A01 = +1.000003398528866105366e+00 */
-        .quad 0xBF20727E814A57CE  /* A02 = -1.254825043772153972919e-04 */
-        .quad 0xBFD538DE060A6F22  /* A03 = -3.315959033004550748913e-01 */
-        .quad 0xBE66DAFA2A893A25  /* A00 = -4.257146219278012568149e-08 */
-        .quad 0x3FF0000465E08CD1  /* A01 = +1.000004194219219266770e+00 */
-        .quad 0xBF2341C765EF91B6  /* A02 = -1.469188600530365522261e-04 */
-        .quad 0xBFD535B6841FAF9E  /* A03 = -3.314033785124993469751e-01 */
-        .quad 0xBE6D5794E361E964  /* A00 = -5.465394929765249413434e-08 */
-        .quad 0x3FF000055EE2A0CB  /* A01 = +1.000005121846742950353e+00 */
-        .quad 0xBF265E6C77E66C8B  /* A02 = -1.706607253709506650304e-04 */
-        .quad 0xBFD53264DDCCEDA6  /* A03 = -3.312008062382240103361e-01 */
-        .quad 0xBE729C844D374A6E  /* A00 = -6.933284462462096107184e-08 */
-        .quad 0x3FF000067F019093  /* A01 = +1.000006195180536350264e+00 */
-        .quad 0xBF29CC5348D6DCE5  /* A02 = -1.968242326435338705130e-04 */
-        .quad 0xBFD52EE92121ED35  /* A03 = -3.309881995734998416658e-01 */
-        .quad 0xBE775AEA17EAA872  /* A00 = -8.700465590574974405858e-08 */
-        .quad 0x3FF00007CA1D66B8  /* A01 = +1.000007428656699559610e+00 */
-        .quad 0xBF2D8F5EB98A2637  /* A02 = -2.255252009216044881395e-04 */
-        .quad 0xBFD52B435CDF9128  /* A03 = -3.307655722585587376727e-01 */
-        .quad 0xBE7D04DA28C343F0  /* A00 = -1.081040272327705484794e-07 */
-        .quad 0x3FF000094443CCF5  /* A01 = +1.000008837375216730337e+00 */
-        .quad 0xBF30D5B76C947AE5  /* A02 = -2.568791210978817814332e-04 */
-        .quad 0xBFD52773A0776FAD  /* A03 = -3.305329386764651045105e-01 */
-        .quad 0xBE81DD77A12C51C7  /* A00 = -1.331054169875768625701e-07 */
-        .quad 0x3FF0000AF1AFD2DA  /* A01 = +1.000010437096696680470e+00 */
-        .quad 0xBF331230624C1680  /* A02 = -2.910011410651516805537e-04 */
-        .quad 0xBFD52379FC0B61DF  /* A03 = -3.302903138515186909352e-01 */
-        .quad 0xBE85D04EEEB3C435  /* A00 = -1.625247628488202841012e-07 */
-        .quad 0x3FF0000CD6C9B1F2  /* A01 = +1.000012244238970726684e+00 */
-        .quad 0xBF357F0742FADDD4  /* A02 = -3.280060509313874068243e-04 */
-        .quad 0xBFD51F56806D0E81  /* A03 = -3.300377134475880880338e-01 */
-        .quad 0xBE8A6E289B59681B  /* A00 = -1.969211333326924655065e-07 */
-        .quad 0x3FF0000EF8268F72  /* A01 = +1.000014275873550406715e+00 */
-        .quad 0xBF381E277A1B747A  /* A02 = -3.680082682942575423093e-04 */
-        .quad 0xBFD51B093F1D6FD4  /* A03 = -3.297751537663746734808e-01 */
-        .quad 0xBE8FCBC40EE9ABD5  /* A00 = -2.368983653301529373887e-07 */
-        .quad 0x3FF000115A883B6C  /* A01 = +1.000016549721943981410e+00 */
-        .quad 0xBF3AF17AC974B3D9  /* A02 = -4.111218235774406434303e-04 */
-        .quad 0xBFD516924A4C549C  /* A03 = -3.295026517456081105450e-01 */
-        .quad 0xBE92FFBC60A3F956  /* A00 = -2.831066871072026054144e-07 */
-        .quad 0x3FF0001402DCED8A  /* A01 = +1.000019084151832604590e+00 */
-        .quad 0xBF3DFAE9390C4801  /* A02 = -4.574603454311488280083e-04 */
-        .quad 0xBFD511F1B4D7DC3A  /* A03 = -3.292202249571719585575e-01 */
-        .quad 0xBE9690A22F96D5AD  /* A00 = -3.362443262393081632612e-07 */
-        .quad 0x3FF00016F63EFF5D  /* A01 = +1.000021898173108825247e+00 */
-        .quad 0xBF409E2C839605BB  /* A02 = -5.071370461992499986334e-04 */
-        .quad 0xBFD50D27924BEE00  /* A03 = -3.289278916051614487515e-01 */
-        .quad 0xBE9AA56C65E72A73  /* A00 = -3.970591019557469835586e-07 */
-        .quad 0x3FF0001A39F4A43E  /* A01 = +1.000025011433776978009e+00 */
-        .quad 0xBF425BD74C3D6667  /* A02 = -5.602647074553602319844e-04 */
-        .quad 0xBFD50833F6E1ABA2  /* A03 = -3.286256705238718156536e-01 */
-        .quad 0xBE9F4BD4FF1A83B0  /* A00 = -4.663500013744687071912e-07 */
-        .quad 0x3FF0001DD36F9EC2  /* A01 = +1.000028444215715683896e+00 */
-        .quad 0xBF44376634149405  /* A02 = -6.169556656102642569831e-04 */
-        .quad 0xBFD50316F77EDEE5  /* A03 = -3.283135811757190158922e-01 */
-        .quad 0xBEA3B625387BB079  /* A00 = -5.874486399249461304297e-07 */
-        .quad 0x3FF00023E14CFBA9  /* A01 = +1.000034217911642153709e+00 */
-        .quad 0xBF47392F923218D2  /* A02 = -7.087213783883111826306e-04 */
-        .quad 0xBFD4FB1FACDEB938  /* A03 = -3.278273761924483942209e-01 */
-        .quad 0xBEAA6E24F543500A  /* A00 = -7.876828740601738750574e-07 */
-        .quad 0x3FF0002D5C6E8412  /* A01 = +1.000043259679163742959e+00 */
-        .quad 0xBF4BAF02BD7FDD70  /* A02 = -8.448375110664940040861e-04 */
-        .quad 0xBFD4EFEE6527A7DE  /* A03 = -3.271442401734229177279e-01 */
-        .quad 0xBEB16E3EBE2157D0  /* A00 = -1.038947396133402500647e-06 */
-        .quad 0x3FF00038990FEE2F  /* A01 = +1.000053975962952312884e+00 */
-        .quad 0xBF50569481C574CB  /* A02 = -9.972048056490652716971e-04 */
-        .quad 0xBFD4E419278DA2B4  /* A03 = -3.264220129263251113372e-01 */
-        .quad 0xBEB6A7B6723165D4  /* A00 = -1.350350836279403750524e-06 */
-        .quad 0x3FF00045CAB4158E  /* A01 = +1.000066558657042303793e+00 */
-        .quad 0xBF531D7C9C849108  /* A02 = -1.166698160951775212202e-03 */
-        .quad 0xBFD4D7A0BB33B152  /* A03 = -3.256608799117844954552e-01 */
-        .quad 0xBEBD0EE2A8654AFD  /* A00 = -1.732000471561702711532e-06 */
-        .quad 0x3FF00055276F18D6  /* A01 = +1.000081209219890521211e+00 */
-        .quad 0xBF562FDBA3FB6C6C  /* A02 = -1.354183666925102939860e-03 */
-        .quad 0xBFD4CA85F1B93DB2  /* A03 = -3.248610363561638125773e-01 */
-        .quad 0xBEC269D4036A207E  /* A00 = -2.195047297096822741730e-06 */
-        .quad 0x3FF00066E7DA6E4E  /* A01 = +1.000098138500919997540e+00 */
-        .quad 0xBF5991499FC36B3A  /* A02 = -1.560518167983372759405e-03 */
-        .quad 0xBFD4BCC9A72283D6  /* A03 = -3.240226871658341556426e-01 */
-        .quad 0xBEC7154B6C09CFE1  /* A00 = -2.751729738565190291276e-06 */
-        .quad 0x3FF0007B47086B80  /* A01 = +1.000117566559055148900e+00 */
-        .quad 0xBF5D455433B4F8F4  /* A02 = -1.786548832412968197680e-03 */
-        .quad 0xBFD4AE6CC1BFE145  /* A03 = -3.231460468373550942722e-01 */
-        .quad 0xBECCA68CC64A0F8A  /* A00 = -3.415415948561670285790e-06 */
-        .quad 0x3FF00092827742F7  /* A01 = +1.000139722473418535387e+00 */
-        .quad 0xBF60A7BF15A527AF  /* A02 = -2.033112728132522705610e-03 */
-        .quad 0xBFD49F703214084C  /* A03 = -3.222313393636155876010e-01 */
-        .quad 0xBED19E68676B241B  /* A00 = -4.200644630977303616698e-06 */
-        .quad 0x3FF000ACDA037B26  /* A01 = +1.000164844146362863597e+00 */
-        .quad 0xBF62D99F836A02F8  /* A02 = -2.301036405072284102280e-03 */
-        .quad 0xBFD48FD4F2B91B28  /* A03 = -3.212787981359945810311e-01 */
-        .quad 0xBED57CF4B0C7AA54  /* A00 = -5.123164339408145209103e-06 */
-        .quad 0x3FF000CA8FD9E1A1  /* A01 = +1.000193178099017865534e+00 */
-        .quad 0xBF653A014548E686  /* A02 = -2.591135484433962181405e-03 */
-        .quad 0xBFD47F9C0844B38F  /* A03 = -3.202886658426046806447e-01 */
-        .quad 0xBEDA012B1B1A41E2  /* A00 = -6.199971197454598722328e-06 */
-        .quad 0x3FF000EBE868FDF4  /* A01 = +1.000224979259539459520e+00 */
-        .quad 0xBF67CA9427E0A544  /* A02 = -2.904214255086275467410e-03 */
-        .quad 0xBFD46EC6812ADB37  /* A03 = -3.192611943626845749655e-01 */
-        .quad 0xBEDF3EAC5BF12194  /* A00 = -7.449344990702664567927e-06 */
-        .quad 0x3FF001112A520784  /* A01 = +1.000260510744255704196e+00 */
-        .quad 0xBF6A8D01ABDA4DC4  /* A02 = -3.241065277345108255891e-03 */
-        .quad 0xBFD45D55759FFA4A  /* A03 = -3.181966446572103146551e-01 */
-        .quad 0xBEE2A541BC274267  /* A00 = -8.890883582164319970972e-06 */
-        .quad 0x3FF0013A9E5961F2  /* A01 = +1.000300043631906721231e+00 */
-        .quad 0xBF6D82ECD080C540  /* A02 = -3.602468994380686462264e-03 */
-        .quad 0xBFD44B4A0779C0AD  /* A03 = -3.170952866557950611259e-01 */
-        .quad 0xBEE61D97609A27F4  /* A00 = -1.054553560499505625520e-05 */
-        .quad 0x3FF001688F56A3AF  /* A01 = +1.000343856731187974773e+00 */
-        .quad 0xBF7056F8EFB683EC  /* A02 = -3.989193351487490407647e-03 */
-        .quad 0xBFD438A5620F0F74  /* A03 = -3.159573991399533543500e-01 */
-        .quad 0xBEEA145429EDD370  /* A00 = -1.243563138839952927732e-05 */
-        .quad 0x3FF0019B4A242A67  /* A01 = +1.000392236341804297339e+00 */
-        .quad 0xBF7207D31CA78D9B  /* A02 = -4.401993423445739288258e-03 */
-        .quad 0xBFD42568BA16E7CD  /* A03 = -3.147832696228050619602e-01 */
-        .quad 0xBEEE96370D52680F  /* A00 = -1.458491207477835326165e-05 */
-        .quad 0x3FF001D31D8E4115  /* A01 = +1.000445476009251821736e+00 */
-        .quad 0xBF73D4CC11EDC094  /* A02 = -4.841611050196221316400e-03 */
-        .quad 0xBFD411954D8664E7  /* A03 = -3.135731942252974469021e-01 */
-        .quad 0xBEF338C046215EF8  /* A00 = -1.833122622260562810219e-05 */
-        .quad 0x3FF00230C32C2EC1  /* A01 = +1.000534784691737621998e+00 */
-        .quad 0xBF76BD019BCC5DAF  /* A02 = -5.551344188254799492943e-03 */
-        .quad 0xBFD3F2C7156DC21E  /* A03 = -3.116929730668135389848e-01 */
-        .quad 0xBEF9B15EAE411EAE  /* A00 = -2.450261207822986676092e-05 */
-        .quad 0x3FF002C2DF057A4D  /* A01 = +1.000674124886830940184e+00 */
-        .quad 0xBF7B08CCD9AC1E30  /* A02 = -6.600189396301511801646e-03 */
-        .quad 0xBFD3C7A7A114FED8  /* A03 = -3.090609620157755976777e-01 */
-        .quad 0xBF00E36483C373B3  /* A00 = -3.221178528332122595812e-05 */
-        .quad 0x3FF0036F419480D7  /* A01 = +1.000838524028997644777e+00 */
-        .quad 0xBF7FD255D1777007  /* A02 = -7.768950679260206403087e-03 */
-        .quad 0xBFD39A453911D6CE  /* A03 = -3.062909180947429588215e-01 */
-        .quad 0xBF05DFA04DD12059  /* A00 = -4.172046622180685472624e-05 */
-        .quad 0x3FF00438B2A03D8D  /* A01 = +1.001030633695197069599e+00 */
-        .quad 0xBF828F8DBB4A9D10  /* A02 = -9.062869337255224921890e-03 */
-        .quad 0xBFD36AAB704697D9  /* A03 = -3.033856007044711255993e-01 */
-        .quad 0xBF0BF3E0C647DEFB  /* A00 = -5.331544597092331081714e-05 */
-        .quad 0x3FF005221063D36D  /* A01 = +1.001253189109060359741e+00 */
-        .quad 0xBF857A2CB3C96102  /* A02 = -1.048693584122917590862e-02 */
-        .quad 0xBFD338E65BBB4FEC  /* A03 = -3.003478904549854444639e-01 */
-        .quad 0xBF11A506ED7C9D31  /* A00 = -6.730894835681591541979e-05 */
-        .quad 0x3FF0062E4D0EA92A  /* A01 = +1.001508999829250345925e+00 */
-        .quad 0xBF88AB82C2761AF3  /* A02 = -1.204588085125866091241e-02 */
-        .quad 0xBFD305028D6BD206  /* A03 = -2.971807843271395688234e-01 */
-        .quad 0xBF1607C0922D9BF1  /* A00 = -8.403885708006799337092e-05 */
-        .quad 0x3FF007606C341961  /* A01 = +1.001800940198869449560e+00 */
-        .quad 0xBF8C25E6DA487BCF  /* A02 = -1.374416688582682892494e-02 */
-        .quad 0xBFD2CF0D0EE8F7B5  /* A03 = -2.938873906713255768075e-01 */
-        .quad 0xBF1B3A8480A0A16D  /* A00 = -1.038688061788578038307e-04 */
-        .quad 0x3FF008BB802D02D6  /* A01 = +1.002131939589323561535e+00 */
-        .quad 0xBF8FEB8AE99FD100  /* A02 = -1.558598065819483124983e-02 */
-        .quad 0xBFD297135BD0911B  /* A03 = -2.904709240558688843059e-01 */
-        .quad 0xBF20ABB9BDB75C65  /* A00 = -1.271881327357976163798e-04 */
-        .quad 0x3FF00A42A76D8CD1  /* A01 = +1.002504972472525901495e+00 */
-        .quad 0xBF91FF3D752BB9E6  /* A02 = -1.757522609380570560722e-02 */
-        .quad 0xBFD25D235C1F88B4  /* A03 = -2.869346999779154305799e-01 */
-        .quad 0xBF243D3254425461  /* A00 = -1.544116913733432829448e-04 */
-        .quad 0x3FF00BF909D1795E  /* A01 = +1.002923048355647051011e+00 */
-        .quad 0xBF94304E04D44942  /* A02 = -1.971551804042204897316e-02 */
-        .quad 0xBFD2214B5E61CFA6  /* A03 = -2.832821294498394371075e-01 */
-        .quad 0xBF286070011B61CE  /* A00 = -1.859795307186510085994e-04 */
-        .quad 0x3FF00DE1D5E1627E  /* A01 = +1.003389201612804537689e+00 */
-        .quad 0xBF9689D5F4163F59  /* A02 = -2.201017668045266231780e-02 */
-        .quad 0xBFD1E39A11C3B42C  /* A03 = -2.795167134743816728104e-01 */
-        .quad 0xBF2D250B366A79E8  /* A00 = -2.223564326486314902259e-04 */
-        .quad 0x3FF010003E134001  /* A01 = +1.003906481248123094829e+00 */
-        .quad 0xBF990C9FF91F6F81  /* A02 = -2.446222265267250853271e-02 */
-        .quad 0xBFD1A41E80084CDC  /* A03 = -2.756420374218586655246e-01 */
-        .quad 0xBF314DB5DDC2A30E  /* A00 = -2.640313157465248123865e-04 */
-        .quad 0x3FF012577608921B  /* A01 = +1.004477940624503018441e+00 */
-        .quad 0xBF9BB9626875B0C9  /* A02 = -2.707437288829409385849e-02 */
-        .quad 0xBFD162E80768A9D0  /* A03 = -2.716617653228725615122e-01 */
-        .quad 0xBF346A6133808864  /* A00 = -3.115165050094957730625e-04 */
-        .quad 0x3FF014EAAFCC88A3  /* A01 = +1.005106627192198898157e+00 */
-        .quad 0xBF9E90BEF9BF7419  /* A02 = -2.984903716411588595059e-02 */
-        .quad 0xBFD12006545F7FAD  /* A03 = -2.675796340899932457269e-01 */
-        .quad 0xBF37F180DC3848EA  /* A00 = -3.653468704395550778821e-04 */
-        .quad 0x3FF017BD19147861  /* A01 = +1.005795572250939295955e+00 */
-        .quad 0xBFA0C9A14C702E07  /* A02 = -3.278831537326359207851e-02 */
-        .quad 0xBFD0DB895B650092  /* A03 = -2.633994476818851682154e-01 */
-        .quad 0xBF3BEC6AAC6D7635  /* A00 = -4.260788377246944457107e-04 */
-        .quad 0x3FF01AD1D884E719  /* A01 = +1.006547780778822565040e+00 */
-        .quad 0xBFA260B2A1B1434A  /* A02 = -3.589399551186163439542e-02 */
-        .quad 0xBFD09581529E93D6  /* A03 = -2.591250712233067465817e-01 */
-        .quad 0xBF4164E26167882B  /* A00 = -5.308251737086202562063e-04 */
-        .quad 0x3FF01FEF14B62B81  /* A01 = +1.007796364693348545316e+00 */
-        .quad 0xBFA4EB014538AA42  /* A02 = -4.085544557559163403315e-02 */
-        .quad 0xBFD029D36FEAF41F  /* A03 = -2.525528519580024222613e-01 */
-        .quad 0xBF46F6FFF4E53DC8  /* A00 = -7.008313930700277652464e-04 */
-        .quad 0x3FF027CBB51CBBA0  /* A01 = +1.009715754956893363214e+00 */
-        .quad 0xBFA89DEC9FEC112E  /* A02 = -4.807986690687680864098e-02 */
-        .quad 0xBFCF2A99464D0DB4  /* A03 = -2.434875100390009317053e-01 */
-        .quad 0xBF4DCC9C4F66A4D9  /* A00 = -9.094012482836712945103e-04 */
-        .quad 0x3FF030E7CFCCD583  /* A01 = +1.011939822882909068014e+00 */
-        .quad 0xBFACAA3B95814081  /* A02 = -5.598627281199331645611e-02 */
-        .quad 0xBFCDF78F156BE7CF  /* A03 = -2.341173987004467604844e-01 */
-        .quad 0xBF5308ED74E5C7A6  /* A00 = -1.161796466103906435435e-03 */
-        .quad 0x3FF03B5986412ECB  /* A01 = +1.014489674026594512313e+00 */
-        .quad 0xBFB087EBA88DCC3F  /* A02 = -6.457398285947223148806e-02 */
-        .quad 0xBFCCBB9BD134862F  /* A03 = -2.244753619680052991736e-01 */
-        .quad 0xBF57FA23C00DF4B5  /* A00 = -1.463446533505758208674e-03 */
-        .quad 0x3FF0473558A1BCC0  /* A01 = +1.017384859292903342975e+00 */
-        .quad 0xBFB2E702BC6360EF  /* A02 = -7.383744334527241048871e-02 */
-        .quad 0xBFCB77D546379288  /* A03 = -2.145945160729250122955e-01 */
-        .quad 0xBF5DD12971557F71  /* A00 = -1.819887610814388068450e-03 */
-        .quad 0x3FF0548DDF5000A8  /* A01 = +1.020643112482540360020e+00 */
-        .quad 0xBFB571B63DA186E1  /* A02 = -8.376635555898871710045e-02 */
-        .quad 0xBFCA2D5202605148  /* A03 = -2.045080672838912594358e-01 */
-        .quad 0xBF6252B1AD5D4F17  /* A00 = -2.236697221556737096709e-03 */
-        .quad 0x3FF063738A910BF7  /* A01 = +1.024280110622155737232e+00 */
-        .quad 0xBFB8270C8E6B601B  /* A02 = -9.434584118878357184013e-02 */
-        .quad 0xBFC8DD27D950A07E  /* A03 = -1.942491351230763441116e-01 */
-        .quad 0xBF66470C91730CFC  /* A00 = -2.719425723258004842786e-03 */
-        .quad 0x3FF073F468FCF331  /* A01 = +1.028309259519300633556e+00 */
-        .quad 0xBFBB05C2952191E4  /* A02 = -1.055566419686964629854e-01 */
-        .quad 0xBFC7886A770DE2BD  /* A03 = -1.838505822486435070662e-01 */
-        .quad 0xBF6AD114AC8E98EC  /* A00 = -3.273525599485007861467e-03 */
-        .quad 0x3FF0861BF53E5226  /* A01 = +1.032741506559554434119e+00 */
-        .quad 0xBFBE0C4F9B461507  /* A02 = -1.173753503881763554650e-01 */
-        .quad 0xBFC6302A037CDE3A  /* A03 = -1.733448521642786954722e-01 */
-        .quad 0xBF6FFBDE2A6C2AF8  /* A00 = -3.904279630096648551207e-03 */
-        .quad 0x3FF099F2EB8E7DA3  /* A01 = +1.037585182326304034106e+00 */
-        .quad 0xBFC09C74D192DDF0  /* A02 = -1.297746680554463516444e-01 */
-        .quad 0xBFC4D571D8E3079F  /* A03 = -1.627638157861470424859e-01 */
-        .quad 0xBF72E8FDC0B952AA  /* A00 = -4.616728994353872309042e-03 */
-        .quad 0x3FF0AF7F273C9533  /* A01 = +1.042845872181101141152e+00 */
-        .quad 0xBFC244C512736F10  /* A02 = -1.427236881344176033792e-01 */
-        .quad 0xBFC379474F58B902  /* A03 = -1.521386277613104298645e-01 */
-        .quad 0xBF762EABAF17395B  /* A00 = -5.415602341101023557701e-03 */
-        .quad 0x3FF0C6C3886F63FB  /* A01 = +1.048526318502125631582e+00 */
-        .quad 0xBFC3FDF9918EA12A  /* A02 = -1.561881981590514389957e-01 */
-        .quad 0xBFC21CA89ECAB895  /* A03 = -1.414995932913753196036e-01 */
-        .quad 0xBF79D387CE5B2BAE  /* A00 = -6.305246822828998107258e-03 */
-        .quad 0x3FF0DFBFE2346376  /* A01 = +1.054626353847394337748e+00 */
-        .quad 0xBFC5C6DA43602620  /* A02 = -1.701309994680721970894e-01 */
-        .quad 0xBFC0C08BD8DB6631  /* A03 = -1.308760460731704100557e-01 */
-        .quad 0xBF7DDBA8E8DA9060  /* A00 = -7.289562037531366334164e-03 */
-        .quad 0x3FF0FA70F0D1B464  /* A01 = +1.061142864894713433443e+00 */
-        .quad 0xBFC79E18D92BAA7C  /* A02 = -1.845122394946264732241e-01 */
-        .quad 0xBFBECBBBF74C2669  /* A03 = -1.202962378266875381749e-01 */
-        .quad 0xBF81254E76EA25DA  /* A00 = -8.371937755572145950511e-03 */
-        .quad 0x3FF116D05835EBD0  /* A01 = +1.068069786618014660462e+00 */
-        .quad 0xBFC982539E2ED224  /* A02 = -1.992897531869327609755e-01 */
-        .quad 0xBFBC1B043C350159  /* A03 = -1.097872397413132278254e-01 */
-        .quad 0xBF8391ACBA863403  /* A00 = -9.555196230190082448686e-03 */
-        .quad 0x3FF134D4AA477FE2  /* A01 = +1.075398125794884141015e+00 */
-        .quad 0xBFCB7218609FEAFB  /* A02 = -2.144194099235717521079e-01 */
-        .quad 0xBFB970A16CB88329  /* A03 = -9.937485603633135211599e-02 */
-        .quad 0xBF87935088E48E8B  /* A00 = -1.151144902957603431692e-02 */
-        .quad 0x3FF1649892AD7DD3  /* A01 = +1.087059567413110938716e+00 */
-        .quad 0xBFCE6971DDE75409  /* A02 = -2.375929196847723912089e-01 */
-        .quad 0xBFB58291E88CB251  /* A03 = -8.402358939628952472223e-02 */
-        .quad 0xBF8DB3A62C325325  /* A00 = -1.450280973794233242702e-02 */
-        .quad 0x3FF1A9C900C6DEEA  /* A01 = +1.103951457056548068891e+00 */
-        .quad 0xBFD13DBC65B0E08E  /* A02 = -2.693930619311765140012e-01 */
-        .quad 0xBFB06696F62696D1  /* A03 = -6.406539449252625362252e-02 */
-        .quad 0xBF92583699F2E27A  /* A00 = -1.791463198307716858659e-02 */
-        .quad 0x3FF1F451B85AA9F0  /* A01 = +1.122148246892376022288e+00 */
-        .quad 0xBFD34FD5F8288180  /* A02 = -3.017477916164565954205e-01 */
-        .quad 0xBFA6FB692825B683  /* A03 = -4.488686194495718900788e-02 */
-        .quad 0xBF9641C26E673D6F  /* A00 = -2.173522757385398448959e-02 */
-        .quad 0x3FF24364DA5E2B07  /* A01 = +1.141453602790251542487e+00 */
-        .quad 0xBFD564A5A5EF5890  /* A02 = -3.342680092295120530821e-01 */
-        .quad 0xBF9B43712011A982  /* A03 = -2.662445791467283467968e-02 */
-        .quad 0xBF9A901038EC2F39  /* A00 = -2.594018313816024226548e-02 */
-        .quad 0x3FF2961356DFFEBA  /* A01 = +1.161639537196534011088e+00 */
-        .quad 0xBFD775EBB17198C7  /* A02 = -3.665723069046972759644e-01 */
-        .quad 0xBF833B1A926CD462  /* A03 = -9.390075295963199591975e-03 */
-        .quad 0xBF9F396A6A461B91  /* A00 = -3.049246095317987084727e-02 */
-        .quad 0x3FF2EB53BAEF534B  /* A01 = +1.182452898229899629357e+00 */
-        .quad 0xBFD97DABF8AD8BBD  /* A02 = -3.982953957076310058660e-01 */
-        .quad 0x3F7B8F6A3E0F8837  /* A03 = +6.728568086119371925713e-03 */
-        .quad 0xBFA21878590F8BAA  /* A00 = -3.534294211546946951064e-02 */
-        .quad 0x3FF34209790236E1  /* A01 = +1.203622315111197105253e+00 */
-        .quad 0xBFDB764C0E71BECB  /* A02 = -4.290952817018306997277e-01 */
-        .quad 0x3F962FE0C03F84C0  /* A03 = +2.166701482190513949888e-02 */
-        .quad 0xBFA4B36B9AD27ECC  /* A00 = -4.043136849327097492868e-02 */
-        .quad 0x3FF3990C5B12FC16  /* A01 = +1.224865298994477935679e+00 */
-        .quad 0xBFDD5AABB0D01390  /* A02 = -4.586590983092770912322e-01 */
-        .quad 0x3FA21DAF5CA162DB  /* A03 = +3.538272863142363083844e-02 */
-        .quad 0xBFA7645E4D7BF28B  /* A00 = -4.568762489177399105378e-02 */
-        .quad 0x3FF3EF2FD51C0D9F  /* A01 = +1.245895225962932562069e+00 */
-        .quad 0xBFDF26377E1B686E  /* A02 = -4.867075664057044503963e-01 */
-        .quad 0x3FA8803E756EE812  /* A03 = +4.785342391501513914509e-02 */
-        .quad 0xBFAA210925C64413  /* A00 = -5.103329263796054643398e-02 */
-        .quad 0x3FF44349F897D8E7  /* A01 = +1.266427966181760345066e+00 */
-        .quad 0xBFE06A7B02C6D8E2  /* A02 = -5.129981092675530707226e-01 */
-        .quad 0x3FAE3F194734F5D0  /* A03 = +5.907515520309980505687e-02 */
-        .quad 0xBFACDE48F8A19BBB  /* A00 = -5.638340029764018351832e-02 */
-        .quad 0x3FF49439D5466582  /* A01 = +1.286187966447272845727e+00 */
-        .quad 0xBFE131C7C1063DDC  /* A02 = -5.373266954429101183166e-01 */
-        .quad 0x3FB1ADEEC36AD805  /* A03 = +6.906025191241844940482e-02 */
-        .quad 0xBFAF905D8F585680  /* A00 = -6.164829611604449866036e-02 */
-        .quad 0x3FF4E0ED1FD27F99  /* A01 = +1.304913639360142818546e+00 */
-        .quad 0xBFE1E7A859DC1D3D  /* A02 = -5.595285182070380836095e-01 */
-        .quad 0x3FB3ED018E4642A1  /* A03 = +7.783517573831001679086e-02 */
-        .quad 0xBFB11595104160BA  /* A00 = -6.673556944713512906198e-02 */
-        .quad 0x3FF528650340490B  /* A01 = +1.322361958217302513319e+00 */
-        .quad 0xBFE28B14B40BC974  /* A02 = -5.794776455425521000109e-01 */
-        .quad 0x3FB5DF49F5BAF6D7  /* A03 = +8.543836831355676453281e-02 */
-        .quad 0xBFB2513A97344BA4  /* A00 = -7.155195418844911836587e-02 */
-        .quad 0x3FF569BA0DB5EE14  /* A01 = +1.338312200124055273420e+00 */
-        .quad 0xBFE31B53A8B67B20  /* A02 = -5.970857901737396389308e-01 */
-        .quad 0x3FB787F297BB0544  /* A03 = +9.191814617499455275507e-02 */
-        .quad 0xBFB37512E848FAFA  /* A00 = -7.600515528700305112331e-02 */
-        .quad 0x3FF5A41F33B403C8  /* A01 = +1.352568819013173495591e+00 */
-        .quad 0xBFE397F6EA9A58A5  /* A02 = -6.123003561103997904880e-01 */
-        .quad 0x3FB8EAA9FF25CA06  /* A03 = +9.733068923177520814782e-02 */
-        .quad 0xBFB47B3E603AFC5D  /* A00 = -8.000554894805263217439e-02 */
-        .quad 0x3FF5D6E3EDE40487  /* A01 = +1.364963464031718975988e+00 */
-        .quad 0xBFE400D5BCA6D631  /* A02 = -6.251019177058819709103e-01 */
-        .quad 0x3FBA0B830ED567FE  /* A03 = +1.017381583418739132707e-01 */
-        .quad 0xBFB5BBFE8AC90496  /* A00 = -8.489981544791400103200e-02 */
-        .quad 0x3FF612BA70107E95  /* A01 = +1.379572332145390989311e+00 */
-        .quad 0xBFE477EAF1FA7693  /* A02 = -6.396383978023599814478e-01 */
-        .quad 0x3FBB4784B7C08A95  /* A03 = +1.065600346196709652391e-01 */
-        .quad 0xBFB6D5D940743939  /* A00 = -8.920057128509463473254e-02 */
-        .quad 0x3FF644A8748F70CE  /* A01 = +1.391762214006166953340e+00 */
-        .quad 0xBFE4D646AB07EA37  /* A02 = -6.511567440459832267763e-01 */
-        .quad 0x3FBC354F4E1D5292  /* A03 = +1.101884427747086558913e-01 */
-        .quad 0xBFB7223D19E4F3D1  /* A00 = -9.036619074045339206069e-02 */
-        .quad 0x3FF6518FEB42B7FA  /* A01 = +1.394912642466350494175e+00 */
-        .quad 0xBFE4ED86CB87498C  /* A02 = -6.539949393430091184598e-01 */
-        .quad 0x3FBC6D29F28CCA9B  /* A03 = +1.110407082713131127205e-01 */
-        .quad 0xBFB6878652FF6312  /* A00 = -8.800544287022329936754e-02 */
-        .quad 0x3FF63948C302D040  /* A01 = +1.388985406648330922508e+00 */
-        .quad 0xBFE4C4E2E7904E17  /* A02 = -6.490339777687407218920e-01 */
-        .quad 0x3FBC127356CA1ABE  /* A03 = +1.096565329445224612481e-01 */
-        .quad 0xBFB4F5D18B0C91D6  /* A00 = -8.187589306596207427980e-02 */
-        .quad 0x3FF5FD27EB7DD0B8  /* A01 = +1.374305648697413673176e+00 */
-        .quad 0xBFE464E01A2B2FC6  /* A02 = -6.373138915164353601739e-01 */
-        .quad 0x3FBB460547674A30  /* A03 = +1.065371798825160976065e-01 */
-        .quad 0xBFB26642FA16A685  /* A00 = -7.187288861919156890412e-02 */
-        .quad 0x3FF59F9BEDE1C95A  /* A01 = +1.351467065073470141812e+00 */
-        .quad 0xBFE3D67920C8FBEA  /* A02 = -6.199308052381387046381e-01 */
-        .quad 0x3FBA24F6A8D3CBC1  /* A03 = +1.021265184570401413078e-01 */
-        .quad 0xBFADB5294794F097  /* A00 = -5.802277563859197656582e-02 */
-        .quad 0x3FF523EA7B9CF453  /* A01 = +1.321268542159732772845e+00 */
-        .quad 0xBFE322A8B55E35DB  /* A02 = -5.979808370918208160205e-01 */
-        .quad 0x3FB8C8673B1B3E37  /* A03 = +9.680791085269722928697e-02 */
-        .quad 0xBFA4B7D661965C6A  /* A00 = -4.046506825687219699450e-02 */
-        .quad 0x3FF48DE3E2CE3122  /* A01 = +1.284641157110919085227e+00 */
-        .quad 0xBFE251FED1A7F445  /* A02 = -5.725092024655472622285e-01 */
-        .quad 0x3FB745699FCABDB9  /* A03 = +9.090290213747821701507e-02 */
-        .quad 0xBF93E60456E4EE1D  /* A00 = -1.943213253365004902773e-02 */
-        .quad 0x3FF3E1A14E628A59  /* A01 = +1.242585474196536532432e+00 */
-        .quad 0xBFE16C5AB660E876  /* A02 = -5.444768488007543094653e-01 */
-        .quad 0x3FB5AD33AA8C188F  /* A03 = +8.467410005332197397987e-02 */
-        .quad 0x3F738C17C47C7961  /* A00 = +4.772274820224659853951e-03 */
-        .quad 0x3FF3234DDE3BD146  /* A01 = +1.196119182682268355933e+00 */
-        .quad 0xBFE078C0D77A9D3B  /* A02 = -5.147403915952176722826e-01 */
-        .quad 0x3FB40D74B3E276B8  /* A03 = +7.833032027925923568290e-02 */
-        .quad 0x3FA0474BECC689C7  /* A00 = +3.179394975019849550746e-02 */
-        .quad 0x3FF256FB4FA7D18A  /* A01 = +1.146235762743432307076e+00 */
-        .quad 0xBFDEFA8E3FB285E2  /* A02 = -4.840427038235174395098e-01 */
-        .quad 0x3FB270C007493D59  /* A03 = +7.203293016322244446403e-02 */
-        .quad 0x3FAF5BD51E479BDC  /* A00 = +6.124750132203590768931e-02 */
-        .quad 0x3FF18081D0B53BC5  /* A01 = +1.093873801484492647162e+00 */
-        .quad 0xBFDCFE2439BD0C03  /* A02 = -4.530115665294831006626e-01 */
-        .quad 0x3FB0DEFE5A45AFDD  /* A03 = +6.590261176978580437424e-02 */
-        .quad 0x3FB7BD5D2806EA26  /* A00 = +9.273321368429118805032e-02 */
-        .quad 0x3FF0A369E35B4440  /* A01 = +1.039895904647224256223e+00 */
-        .quad 0xBFDB04BC5C9951E7  /* A02 = -4.221640495573226181669e-01 */
-        .quad 0x3FAEBBBAA9D6DEEF  /* A03 = +6.002600978120919278380e-02 */
-        .quad 0x3FC01BE411098DBC  /* A00 = +1.258511622610124502941e-01 */
-        .quad 0x3FEF85BDABC031C1  /* A01 = +9.850757936961188621083e-01 */
-        .quad 0xBFD91521375097C2  /* A02 = -3.919146576102968682065e-01 */
-        .quad 0x3FABE26F0086D982  /* A03 = +5.446192628317005068883e-02 */
-        .quad 0x3FC481D7FF5776B9  /* A00 = +1.602125164781023347604e-01 */
-        .quad 0x3FEDC3506C1E7218  /* A01 = +9.300920592973538347792e-01 */
-        .quad 0xBFD7349A88DA7D4F  /* A02 = -3.625856720409119104964e-01 */
-        .quad 0x3FA936E2DFF8E2AE  /* A03 = +4.924687370334389358018e-02 */
-        .quad 0x3FC90471F96FA27A  /* A00 = +1.954481571149420671141e-01 */
-        .quad 0x3FEC0451601987A2  /* A01 = +8.755270840595026360376e-01 */
-        .quad 0xBFD5671CD4B898DC  /* A02 = -3.344184949259110251063e-01 */
-        .quad 0x3FA6BB9594603B67  /* A03 = +4.439990459660841243261e-02 */
-        .quad 0x3FCFD8ADB9ED944C  /* A00 = +2.488000066615846384011e-01 */
-        .quad 0x3FE978C073F6809A  /* A01 = +7.959902062321078108909e-01 */
-        .quad 0xBFD2DF7E00BCD5A9  /* A02 = -2.948908812716931060471e-01 */
-        .quad 0x3FA3614033D490B2  /* A03 = +3.785133965200894456959e-02 */
-        .quad 0x3FD4846A12AFE5A0  /* A00 = +3.205819303981005674586e-01 */
-        .quad 0x3FE63A1147D40472  /* A01 = +6.945883181471244061100e-01 */
-        .quad 0xBFCFA2268AD34450  /* A02 = -2.471359422548027318101e-01 */
-        .quad 0x3F9F150201D9FFE0  /* A03 = +3.035357605267552383310e-02 */
-        .quad 0x3FD9018641F82BEB  /* A00 = +3.907180446846598154131e-01 */
-        .quad 0x3FE33B7C220FFBDC  /* A01 = +6.010113396913498995389e-01 */
-        .quad 0xBFCA4E4187E29C86  /* A02 = -2.055131829740483584423e-01 */
-        .quad 0x3F98C30CED19F8F4  /* A03 = +2.418155858185229434287e-02 */
-        .quad 0x3FDD4B8255BEB078  /* A00 = +4.577337109901757905561e-01 */
-        .quad 0x3FE0858B19D3A49B  /* A01 = +5.163016800335243905451e-01 */
-        .quad 0xBFC5BC929EACE564  /* A02 = -1.698172831327539045176e-01 */
-        .quad 0x3F93A083CE57DE2B  /* A03 = +1.916700312537337677621e-02 */
-        .quad 0x3FE0A8E5E039295C  /* A00 = +5.206174258576470315063e-01 */
-        .quad 0x3FDC35E1234583FE  /* A01 = +4.407885403107342225937e-01 */
-        .quad 0xBFC1DE034E31AEB9  /* A02 = -1.395877963835710222629e-01 */
-        .quad 0x3F8EFDEBB3471BDC  /* A03 = +1.513275280821162888101e-02 */
-        .quad 0x3FE2851B603CB2A5  /* A00 = +5.787484054213406503564e-01 */
-        .quad 0x3FD7F4A44ABBB286  /* A01 = +3.743067483726821853551e-01 */
-        .quad 0xBFBD3EEB67087DE7  /* A02 = -1.142413260026767657385e-01 */
-        .quad 0x3F8864F38329E8BD  /* A03 = +1.191129917173260922836e-02 */
-        .quad 0x3FE437DBE3C34AC1  /* A00 = +6.318187187665317283702e-01 */
-        .quad 0x3FD43F6F789441B5  /* A01 = +3.163717916040938438194e-01 */
-        .quad 0xBFB7D92E7901B9A4  /* A02 = -9.315767721429907277653e-02 */
-        .quad 0x3F8327ED342308E1  /* A03 = +9.353497651663324544136e-03 */
-        .quad 0x3FE5C0977766D55C  /* A00 = +6.797597248138731451661e-01 */
-        .quad 0x3FD10B42A764D8F9  /* A01 = +2.663122782427219115142e-01 */
-        .quad 0xBFB3633351D3D70F  /* A02 = -7.573242900602060456716e-02 */
-        .quad 0x3F7E079E30FF899C  /* A03 = +7.331483779099558922843e-03 */
-        .quad 0x3FE7202CE08A88C4  /* A00 = +7.226776490754436288455e-01 */
-        .quad 0x3FCC973EB5662B01  /* A01 = +2.233656297433626314319e-01 */
-        .quad 0xBFAF70A455F9920B  /* A02 = -6.140626477716545211782e-02 */
-        .quad 0x3F77812411CE99B6  /* A03 = +5.738392731393584730859e-03 */
-        .quad 0x3FE85879424095B1  /* A00 = +7.608000082006382003286e-01 */
-        .quad 0x3FC7E73BD1674D84  /* A01 = +1.867441914060742336190e-01 */
-        .quad 0xBFA96F84E4BF333B  /* A02 = -4.967894832916504993525e-02 */
-        .quad 0x3F72606DDCA6E117  /* A03 = +4.486493251924870105662e-03 */
-        .quad 0x3FE96BFE4957F4DD  /* A00 = +7.944327766887472330737e-01 */
-        .quad 0x3FC3ED4780D25478  /* A01 = +1.556786898624158421711e-01 */
-        .quad 0xBFA489C5F9A56B58  /* A02 = -4.011362717093075458408e-02 */
-        .quad 0x3F6CB5DC17E9AD2A  /* A03 = +3.504686231556104931972e-03 */
-        .quad 0x3FEA5D9CB2F41234  /* A00 = +8.239272589858672724006e-01 */
-        .quad 0x3FC091A758374DCF  /* A01 = +1.294449978582705440555e-01 */
-        .quad 0xBFA08E436D4B5CE0  /* A02 = -3.233538350257858517978e-02 */
-        .quad 0x3F666997AD53E6B7  /* A03 = +2.735897297154145629133e-03 */
-        .quad 0x3FEB3060342CB850  /* A00 = +8.496552485501158713532e-01 */
-        .quad 0x3FBB7D30BBC7DC1B  /* A01 = +1.073790033768634993860e-01 */
-        .quad 0xBF9AA6BA3443D9E3  /* A02 = -2.602663940430173170060e-02 */
-        .quad 0x3F617CA764B7850B  /* A03 = +2.134634914668814050648e-03 */
-        .quad 0x3FEBE759A6A0C7B8  /* A00 = +8.719909910635044170135e-01 */
-        .quad 0x3FB6C10DE6A703FF  /* A01 = +8.888327485239243264115e-02 */
-        .quad 0xBF956C566D8BE1F6  /* A02 = -2.092108768099084498138e-02 */
-        .quad 0x3F5B46D1A4A59CF8  /* A03 = +1.664833764687232917079e-03 */
-        .quad 0x3FEC858494887A04  /* A00 = +8.912985707318630268503e-01 */
-        .quad 0x3FB2CC31F543394D  /* A01 = +7.342827070099140762682e-02 */
-        .quad 0xBF9133477FF69137  /* A02 = -1.679717749142747504343e-02 */
-        .quad 0x3F5544482FBB4DA5  /* A03 = +1.298017973501022466823e-03 */
-        .quad 0x3FED0DB59D0E32E9  /* A00 = +9.079235141267335551518e-01 */
-        .quad 0x3FAF006BAFFC6EF4  /* A01 = +6.055008433597022787787e-02 */
-        .quad 0xBF8B97146FA2B97A  /* A02 = -1.347175565419144252499e-02 */
-        .quad 0x3F5093B01F4CDC69  /* A03 = +1.011774057770665211434e-03 */
-        .quad 0x3FEDB487C3EC457C  /* A00 = +9.282873942012623835751e-01 */
-        .quad 0x3FA7390C09D0BD1D  /* A01 = +4.535710925881118044112e-02 */
-        .quad 0xBF83D9F7C3181106  /* A02 = -9.693084374710735778846e-03 */
-        .quad 0x3F46E34A0A3C0E64  /* A03 = +6.984817050299072134500e-04 */
-        .quad 0x3FEE5FFCB4E6EB00  /* A00 = +9.492171796076434020506e-01 */
-        .quad 0x3F9F4913ED00AADF  /* A01 = +3.055220731782070861526e-02 */
-        .quad 0xBF79670BD0E59B5C  /* A02 = -6.201788097633133961528e-03 */
-        .quad 0x3F3BC998EBCAF96D  /* A03 = +4.240034429975534616304e-04 */
-        .quad 0x3FEEDBA41E9542FE  /* A00 = +9.643116566968215064293e-01 */
-        .quad 0x3F94F5DD18D9C24D  /* A01 = +2.046914543319848858727e-02 */
-        .quad 0xBF7034896AA122B9  /* A02 = -3.956352980886528904192e-03 */
-        .quad 0x3F30DCCB47810B39  /* A03 = +2.573009765038273091199e-04 */
-        .quad 0x3FEF33F2882520ED  /* A00 = +9.750912341196716903724e-01 */
-        .quad 0x3F8BF37F2CF553FF  /* A01 = +1.364802699996836392315e-02 */
-        .quad 0xBF649F6F05A69619  /* A02 = -2.517430152880317534986e-03 */
-        .quad 0x3F247623C950AAC9  /* A03 = +1.561087307505231250044e-04 */
-        .quad 0x3FEF727757751741  /* A00 = +9.827229221489021115943e-01 */
-        .quad 0x3F828E67912C4400  /* A01 = +9.060677640748693306705e-03 */
-        .quad 0xBF5A2F51A806CC2C  /* A02 = -1.598195784123355826789e-03 */
-        .quad 0x3F18D35D7687E613  /* A03 = +9.470231965016282719549e-05 */
-        .quad 0x3FEF9E6325C5942A  /* A00 = +9.880843866091073568469e-01 */
-        .quad 0x3F788AB117618F76  /* A01 = +5.991641772286606867914e-03 */
-        .quad 0xBF5096EAB0B1EA89  /* A02 = -1.012543859160305046233e-03 */
-        .quad 0x3F0E1E50EC4435AB  /* A03 = +5.744633156910412119652e-05 */
-        .quad 0x3FEFBD0784049369  /* A00 = +9.918248728250605994461e-01 */
-        .quad 0x3F702BBD8294035F  /* A01 = +3.947963975634432264028e-03 */
-        .quad 0xBF44FB55E0F00593  /* A02 = -6.403130845457509273330e-04 */
-        .quad 0x3F0244DCD723230A  /* A03 = +3.484534217219031730379e-05 */
-        .quad 0x3FEFD245E2366A43  /* A00 = +9.944180887426415926811e-01 */
-        .quad 0x3F653D82EC088433  /* A01 = +2.592807490387838333795e-03 */
-        .quad 0xBF3A7DF75E013CB8  /* A02 = -4.042366908878036561859e-04 */
-        .quad 0x3EF6298E69F991CD  /* A03 = +2.113564425911141559972e-05 */
-        .quad 0x3FEFE0EAA508BC69  /* A00 = +9.962056372950317539861e-01 */
-        .quad 0x3F5BD0771AF3FDDA  /* A01 = +1.697651208644282514598e-03 */
-        .quad 0xBF30B2E1254DE571  /* A02 = -2.548026725928887099328e-04 */
-        .quad 0x3EEAE28B70EC0256  /* A03 = +1.281973848454955042307e-05 */
-        .quad 0x3FEFEAF5303D7F96  /* A00 = +9.974313680831865536192e-01 */
-        .quad 0x3F5229111365657E  /* A01 = +1.108423877289460134782e-03 */
-        .quad 0xBF250572D04DFE66  /* A02 = -1.603796628408704519168e-04 */
-        .quad 0x3EE04E89BB57C981  /* A03 = +7.775682983689149966743e-06 */
-        .quad 0x3FEFF1CF52F1CF44  /* A00 = +9.982678051005469122003e-01 */
-        .quad 0x3F47A71316147CEB  /* A01 = +7.218211359577819110842e-04 */
-        .quad 0xBF1A6D7604055719  /* A02 = -1.008132248946049582547e-04 */
-        .quad 0x3ED3C8047586A85C  /* A03 = +4.716233739913014633626e-06 */
-        .quad 0x3FEFF6770369EF69  /* A00 = +9.988360468555416149528e-01 */
-        .quad 0x3F3EBB261180FBF0  /* A01 = +4.689186039321105101130e-04 */
-        .quad 0xBF1097754FE19D7F  /* A02 = -6.329206004950480057066e-05 */
-        .quad 0x3EC7FEFF83BCA0A7  /* A03 = +2.860556404988488738366e-06 */
-        .quad 0x3FEFF99D42371AC4  /* A00 = +9.992204945818561334647e-01 */
-        .quad 0x3F33EB2AEC271F59  /* A01 = +3.039340773764907474054e-04 */
-        .quad 0xBF04CF18E0FC0D79  /* A02 = -3.968996690952969588805e-05 */
-        .quad 0x3EBD1BDBD6019BE9  /* A03 = +1.735021065507727833886e-06 */
-        .quad 0x3FEFFBBCA32B0D91  /* A00 = +9.994795977476532700123e-01 */
-        .quad 0x3F29C41E1615110A  /* A01 = +1.965796209707565346710e-04 */
-        .quad 0xBEFA11F93D9DCB5A  /* A02 = -2.486248909101414873235e-05 */
-        .quad 0x3EB1A7CA4546F7A7  /* A03 = +1.052345642723709228769e-06 */
-        .quad 0x3FEFFD298B8E8DE2  /* A00 = +9.996535993308806045121e-01 */
-        .quad 0x3F20A1C42D523C5B  /* A01 = +1.268913244172078754520e-04 */
-        .quad 0xBEF0507A364AFAE4  /* A02 = -1.555859070622834605755e-05 */
-        .quad 0x3EA56ACA17E7CDF4  /* A03 = +6.382806956848098872313e-07 */
-        .quad 0x3FEFFE1DC82BA5A3  /* A00 = +9.997700604991915929176e-01 */
-        .quad 0x3F156E73B90F1769  /* A01 = +8.175450626798714452801e-05 */
-        .quad 0xBEE4663579D0A09F  /* A02 = -9.727122057226747625365e-06 */
-        .quad 0x3E99FAF6FEC5D4C1  /* A03 = +3.871371052824002996020e-07 */
-        .quad 0x3FEFFEF8D0BB5E81  /* A00 = +9.998745037837154514548e-01 */
-        .quad 0x3F06686DA18D39C3  /* A01 = +4.273972098777251447726e-05 */
-        .quad 0xBED46BC298073E90  /* A02 = -4.868731025855742842491e-06 */
-        .quad 0x3E88E42286B9D0FD  /* A03 = +1.854535328530838170114e-07 */
-        .quad 0x3FEFFF8DBC68DDC7  /* A00 = +9.999455146670975791423e-01 */
-        .quad 0x3EF26B2953A80AF0  /* A01 = +1.756534514108903368909e-05 */
-        .quad 0xBEBFC4472D580F83  /* A02 = -1.893443529411295465239e-06 */
-        .quad 0x3E72505B4553D19F  /* A03 = +6.822456673547912277047e-08 */
-        .quad 0x3FEFFFCED1276609  /* A00 = +9.999765477215883935358e-01 */
-        .quad 0x3EDE1A94C7CC58F5  /* A01 = +7.177313020153979672606e-06 */
-        .quad 0xBEA8A2C988744E57  /* A02 = -7.342066660497443762363e-07 */
-        .quad 0x3E5AF30036BBBAF4  /* A03 = +2.509841882843541084885e-08 */
-        .quad 0x3FEFFFEAFE70FCFC  /* A00 = +9.999899835164849370983e-01 */
-        .quad 0x3EC879175E3549F5  /* A01 = +2.917410471128503564412e-06 */
-        .quad 0xBE930E36677D1813  /* A02 = -2.839493400307523115929e-07 */
-        .quad 0x3E43D4005B42D48F  /* A03 = +9.233192745401904898013e-09 */
-        .quad 0x3ff0000000000000
-        .quad 0x0000000000000000
-        .quad 0x0000000000000000
-        .quad 0x0000000000000000
-        .align 16
-        .long 0x80000000, 0x80000000, 0x80000000, 0x80000000           /* _sSignMask        */
-        .align 16
-        .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff           /* _sAbsMask         */
-        .align 16
-        .long 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000           /* _iExpMantMask     */
-        .align 16
-        .long 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000           /* _iExpMask         */
-        .align 16
-        .long 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000           /* _iMinIdxOfsMask   */
-        .align 16
-        .long 0x04280000, 0x04280000, 0x04280000, 0x04280000           /* _iMaxIdxMask      */
-        .align 16
-        .type	__svml_stanh_data_internal,@object
-        .size	__svml_stanh_data_internal,.-__svml_stanh_data_internal
+	movups	(%rsi, %rax), %xmm2
+	movups	(%rdi, %rax), %xmm7
+
+	movaps	%xmm2, %xmm3
+
+	unpckhpd %xmm7, %xmm2
+	movlhps	%xmm7, %xmm3
+
+	addpd	%xmm13, %xmm2
+
+	mulpd	%xmm5, %xmm6
+	addpd	%xmm4, %xmm6
+
+	mulpd	%xmm2, %xmm0
+	addpd	%xmm3, %xmm0
+
+	cvtpd2ps %xmm0, %xmm2
+	cvtpd2ps %xmm6, %xmm0
+
+	movlhps	%xmm2, %xmm0
+	andnps	%xmm12, %xmm1
+	orps	%xmm1, %xmm0
+
+	movmskps %xmm8, %edx
+	testl	%edx, %edx
+
+	/* Go to special inputs processing branch.  */
+	jne	L(SPECIAL_VALUES_BRANCH)
+
+	/* No stack restoration on the fastpath.  */
+	ret
+
+L(SPECIAL_VALUES_BRANCH):
+	subq	$48, %rsp
+
+	movups	%xmm0, (%rsp)
+	movups	%xmm12, 16(%rsp)
+
+	movq	%r12, 32(%rsp)
+	movq	%r13, 40(%rsp)
+
+	/* edx has 1s where there was a special value that needs to be handled
+	   by a tanhf call.  */
+	movl	%edx, %r13d
+L(SPECIAL_VALUES_LOOP):
+	/* use r12 as index for special value that is saved across calls to
+	   tanhf. We technically don't need a callee save register here as offset
+	   to rsp is always [0, 12] so we can restore rsp by realigning to 64.
+	   Essentially the tradeoff is 1 extra save/restore vs 2 extra instructions
+	   in the loop.  */
+	xorl	%r12d, %r12d
+	bsfl	%r13d, %r12d
+
+	/* Scalar math fucntion call to process special input.  */
+	movss	16(%rsp, %r12, 4), %xmm0
+	call	tanhf@PLT
+	/* No good way to avoid the store-forwarding fault this will cause on
+	   return. `lfence` avoids the SF fault but at greater cost as it
+	   serialized stack/callee save restoration.  */
+	movss	%xmm0, (%rsp, %r12, 4)
+
+	leal	-1(%r13), %eax
+	andl	%eax, %r13d
+	jnz	L(SPECIAL_VALUES_LOOP)
+
+	/* All results have been written to 16(%rsp).  */
+	movups	(%rsp), %xmm0
+	movq	32(%rsp), %r12
+	movq	40(%rsp), %r13
+	addq	$48, %rsp
+	ret
+END(_ZGVbN4v_tanhf_sse4)
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf8_core_avx2.S
index 3745db5aa4..90c3ea4cc6 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf8_core_avx2.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_tanhf8_core_avx2.S
@@ -70,775 +70,171 @@
  *
  */
 
-/* Offsets for data table __svml_stanh_data_internal
- */
-#define _dbP                          	0
-#define _sSignMask                    	4288
-#define _sAbsMask                     	4320
-#define _iExpMantMask                 	4352
-#define _iExpMask                     	4384
-#define _iMinIdxOfsMask               	4416
-#define _iMaxIdxMask                  	4448
-
 #include <sysdep.h>
+#include "svml_s_tanhf_rodata.S"
 
         .text
 	.section .text.avx2,"ax",@progbits
 ENTRY(_ZGVdN8v_tanhf_avx2)
-        pushq     %rbp
-        cfi_def_cfa_offset(16)
-        movq      %rsp, %rbp
-        cfi_def_cfa(6, 16)
-        cfi_offset(6, -16)
-        andq      $-32, %rsp
-        pushq     %r12
-        subq      $120, %rsp
-        lea       _dbP+16+__svml_stanh_data_internal(%rip), %r10
-        vmovaps   %ymm0, %ymm12
-
-/* Here huge arguments, INF and NaNs are filtered out to callout. */
-        vpand     _iExpMantMask+__svml_stanh_data_internal(%rip), %ymm12, %ymm14
+	/* Here huge arguments, INF and NaNs are filtered out to callout.  */
+	vpand	TANHF_DATA(_iExpMantMask)(%rip), %ymm0, %ymm4
+	vpsubd	TANHF_DATA(_iMinIdxOfsMask)(%rip), %ymm4, %ymm2
 
-/*
- *  small table specific variables *
- *  Constant loading
- */
-        vmovups   _iMaxIdxMask+__svml_stanh_data_internal(%rip), %ymm8
-        vpsubd    _iMinIdxOfsMask+__svml_stanh_data_internal(%rip), %ymm14, %ymm9
-
-/* if VMIN, VMAX is defined for I type */
-        vxorps    %ymm15, %ymm15, %ymm15
-        vpcmpgtd  %ymm15, %ymm9, %ymm0
-        vpand     %ymm0, %ymm9, %ymm7
-        vpcmpgtd  %ymm8, %ymm9, %ymm6
-        vblendvps %ymm6, %ymm8, %ymm7, %ymm3
-        vpsrld    $14, %ymm3, %ymm1
-        vpcmpgtd  _iExpMask+__svml_stanh_data_internal(%rip), %ymm14, %ymm13
-        vmovmskps %ymm13, %r11d
-        vandps    _sAbsMask+__svml_stanh_data_internal(%rip), %ymm12, %ymm10
-        vandps    _sSignMask+__svml_stanh_data_internal(%rip), %ymm12, %ymm11
-        vextractf128 $1, %ymm1, %xmm2
-        vmovd     %xmm1, %r9d
-        vmovd     %xmm2, %ecx
-        vpextrd   $1, %xmm2, %edx
-        vpextrd   $1, %xmm1, %r8d
-        movslq    %r9d, %r9
-        movslq    %edx, %rdx
-        movslq    %r8d, %r8
-        vpextrd   $2, %xmm1, %edi
-        movslq    %ecx, %rcx
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -8; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xf8, 0xff, 0xff, 0xff, 0x22
-        vpextrd   $3, %xmm2, %r12d
-        vpextrd   $3, %xmm1, %esi
-        vpextrd   $2, %xmm2, %eax
-        movslq    %edi, %rdi
-        movslq    %r12d, %r12
-        movslq    %esi, %rsi
-        movslq    %eax, %rax
-        vmovupd   -16(%r9,%r10), %xmm5
-        vmovupd   -16(%rdx,%r10), %xmm14
-        vmovupd   -16(%rcx,%r10), %xmm13
-        vmovupd   (%r9,%r10), %xmm1
-        vmovupd   (%r8,%r10), %xmm2
-        vmovupd   -16(%r8,%r10), %xmm4
-        vinsertf128 $1, -16(%rdi,%r10), %ymm5, %ymm15
-        vinsertf128 $1, -16(%r12,%r10), %ymm14, %ymm3
-        vinsertf128 $1, -16(%rax,%r10), %ymm13, %ymm6
-        vinsertf128 $1, (%rdi,%r10), %ymm1, %ymm5
-        vinsertf128 $1, (%rsi,%r10), %ymm2, %ymm14
-        vunpcklpd %ymm3, %ymm6, %ymm8
-        vunpckhpd %ymm3, %ymm6, %ymm6
-        vunpcklpd %ymm14, %ymm5, %ymm3
-        vunpckhpd %ymm14, %ymm5, %ymm2
-        vmovupd   (%rcx,%r10), %xmm13
-        vcvtps2pd %xmm10, %ymm5
-        vextractf128 $1, %ymm10, %xmm10
-        vfmadd213pd %ymm3, %ymm5, %ymm2
-        vinsertf128 $1, -16(%rsi,%r10), %ymm4, %ymm0
-        vmovupd   (%rdx,%r10), %xmm4
-        vunpcklpd %ymm0, %ymm15, %ymm9
-        vunpckhpd %ymm0, %ymm15, %ymm7
-        vfmadd213pd %ymm7, %ymm5, %ymm2
-        vfmadd213pd %ymm9, %ymm5, %ymm2
-        vinsertf128 $1, (%r12,%r10), %ymm4, %ymm0
-        vcvtps2pd %xmm10, %ymm4
-        vinsertf128 $1, (%rax,%r10), %ymm13, %ymm15
-        vunpcklpd %ymm0, %ymm15, %ymm1
-        vunpckhpd %ymm0, %ymm15, %ymm0
-        vfmadd213pd %ymm1, %ymm4, %ymm0
-        vcvtpd2ps %ymm2, %xmm1
-        vfmadd213pd %ymm6, %ymm4, %ymm0
-        vfmadd213pd %ymm8, %ymm4, %ymm0
-        vcvtpd2ps %ymm0, %xmm0
-        vinsertf128 $1, %xmm0, %ymm1, %ymm2
-        vorps     %ymm11, %ymm2, %ymm0
-        testl     %r11d, %r11d
-
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx r13 r14 r15 r11d ymm0 ymm12
-
-/* Restore registers
- * and exit the function
- */
+	/* Selection of arguments between [0, 0x04280000] into ymm2.  */
+	vpxor	%ymm3, %ymm3, %ymm3
+	vpmaxsd	%ymm3, %ymm2, %ymm2
+	vpminsd	TANHF_DATA(_iMaxIdxMask)(%rip), %ymm2, %ymm2
 
-L(EXIT):
-        addq      $120, %rsp
-        cfi_restore(12)
-        popq      %r12
-        movq      %rbp, %rsp
-        popq      %rbp
-        cfi_def_cfa(7, 8)
-        cfi_restore(6)
-        ret
-        cfi_def_cfa(6, 16)
-        cfi_offset(6, -16)
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -8; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xf8, 0xff, 0xff, 0xff, 0x22
-
-/* Branch to process
- * special inputs
- */
+	vpsrld	$14, %ymm2, %ymm1
 
-L(SPECIAL_VALUES_BRANCH):
-        vmovups   %ymm12, 32(%rsp)
-        vmovups   %ymm0, 64(%rsp)
-                                # LOE rbx r13 r14 r15 r11d ymm0
-
-        xorl      %r12d, %r12d
-                                # LOE rbx r13 r14 r15 r11d r12d
-
-        vzeroupper
-        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      %r11d, %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
- */
+	/* Store special cases in ymm15.  */
+	vpcmpgtd TANHF_DATA(_iExpMask)(%rip), %ymm4, %ymm15
 
-L(RANGEMASK_CHECK):
-        btl       %r12d, %r13d
 
-/* Call scalar math function */
-        jc        L(SCALAR_MATH_CALL)
-                                # LOE rbx r15 r12d r13d
+	/* Store base of lookup table in rax.  */
+	leaq	TANHF_DATA(_lookupTable)(%rip), %rax
 
-/* Special inputs
- * processing loop
- */
+	/* We are splitting xmm1 into 8 GPRs. This may be faster to do with
+	   store/load as we can take advantage of store-forwarding.  */
+	vmovq	%xmm1, %r8
+	/* We have eliminated all negative values for ymm1 so no need to sign
+	   extend.  */
+	movl	%r8d, %r9d
+	shrq	$32, %r8
 
-L(SPECIAL_VALUES_LOOP):
-        incl      %r12d
-        cmpl      $8, %r12d
-
-/* Check bits in range mask */
-        jl        L(RANGEMASK_CHECK)
-                                # LOE rbx r15 r12d r13d
-
-        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: 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 r13 r14 r15 ymm0
-
-/* Scalar math fucntion call
- * to process special input
- */
+	/* Instead of using cross-lane permutes on ymm vectors, use vpinsertf128
+	   with memory operand. This helps alleviate bottleneck on p5.  */
+	vmovdqu	16(%r9, %rax), %xmm5
 
-L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movss     32(%rsp,%r14,4), %xmm0
-        call      tanhf@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
+	vpextrq	$1, %xmm1, %rsi
+	movl	%esi, %edi
+	shrq	$32, %rsi
 
-        movss     %xmm0, 64(%rsp,%r14,4)
+	vinsertf128 $1, 16(%rdi, %rax), %ymm5, %ymm5
 
-/* Process special inputs in loop */
-        jmp       L(SPECIAL_VALUES_LOOP)
-                                # LOE rbx r15 r12d r13d
-END(_ZGVdN8v_tanhf_avx2)
+	vextracti128 $1, %ymm1, %xmm2
+	vmovq	%xmm2, %rdx
+	movl	%edx, %ecx
+	shrq	$32, %rdx
+
+	vmovdqu	(%rcx, %rax), %xmm6
+
+	vpextrq	$1, %xmm2, %r10
+	movl	%r10d, %r11d
+	shrq	$32, %r10
+
+	vinsertf128 $1, (%r11, %rax), %ymm6, %ymm6
+
+	vmovupd	16(%r8, %rax), %xmm1
+	vinsertf128 $1, 16(%rsi, %rax), %ymm1, %ymm1
+	vmovupd	(%rdx, %rax), %xmm3
+	vinsertf128 $1, (%r10, %rax), %ymm3, %ymm3
+
+	vunpcklpd %ymm3, %ymm6, %ymm7
+	vunpckhpd %ymm3, %ymm6, %ymm6
+
+	vunpcklpd %ymm1, %ymm5, %ymm3
+	vunpckhpd %ymm1, %ymm5, %ymm1
+
+	vmovaps	TANHF_DATA(_sAbsMask)(%rip), %ymm11
+	vandps	%ymm11, %ymm0, %ymm4
 
-        .section .rodata, "a"
-        .align 32
-
-#ifdef __svml_stanh_data_internal_typedef
-typedef unsigned int VUINT32;
-typedef struct
-{
-        __declspec(align(32)) VUINT32 _dbP[(134*4)][2];
-        __declspec(align(32)) VUINT32 _sSignMask[8][1];
-        __declspec(align(32)) VUINT32 _sAbsMask[8][1];
-        __declspec(align(32)) VUINT32 _iExpMantMask[8][1];
-        __declspec(align(32)) VUINT32 _iExpMask[8][1];
-        __declspec(align(32)) VUINT32 _iMinIdxOfsMask[8][1];
-        __declspec(align(32)) VUINT32 _iMaxIdxMask[8][1];
-} __svml_stanh_data_internal;
-#endif
-__svml_stanh_data_internal:
-        /* Pol_000:  err=7.93e-09, x in [0.0000000; 0.0312500]. */
-        .quad 0x0000000000000000  /* A00 = +0.000000000000000000000e-01 */
-        .quad 0x3FF00000022C70EB  /* A01 = +1.000000008097283510367e+00 */
-        .quad 0xBED00E878CFFA194  /* A02 = -3.828228912518614443549e-06 */
-        .quad 0xBFD551766D0607A9  /* A03 = -3.330970825846813476723e-01 */
-        .quad 0xBE53D60CE3E4C297  /* A00 = -1.847383956330407336230e-08 */
-        .quad 0x3FF000024177CF5C  /* A01 = +1.000002151235967140508e+00 */
-        .quad 0xBF1758BC94A51A25  /* A02 = -8.906031613262943753568e-05 */
-        .quad 0xBFD53EAE67E0D4F0  /* A03 = -3.319507612644221339337e-01 */
-        .quad 0xBE5A9E47EF32D6FE  /* A00 = -2.479020984039698285657e-08 */
-        .quad 0x3FF00002DA983057  /* A01 = +1.000002721676556793895e+00 */
-        .quad 0xBF1BD953509E94AA  /* A02 = -1.062352277175377670507e-04 */
-        .quad 0xBFD53BDB562EEDD5  /* A03 = -3.317783681520414806876e-01 */
-        .quad 0xBE6191BBE496D294  /* A00 = -3.272532162914017685901e-08 */
-        .quad 0x3FF0000390492017  /* A01 = +1.000003398528866105366e+00 */
-        .quad 0xBF20727E814A57CE  /* A02 = -1.254825043772153972919e-04 */
-        .quad 0xBFD538DE060A6F22  /* A03 = -3.315959033004550748913e-01 */
-        .quad 0xBE66DAFA2A893A25  /* A00 = -4.257146219278012568149e-08 */
-        .quad 0x3FF0000465E08CD1  /* A01 = +1.000004194219219266770e+00 */
-        .quad 0xBF2341C765EF91B6  /* A02 = -1.469188600530365522261e-04 */
-        .quad 0xBFD535B6841FAF9E  /* A03 = -3.314033785124993469751e-01 */
-        .quad 0xBE6D5794E361E964  /* A00 = -5.465394929765249413434e-08 */
-        .quad 0x3FF000055EE2A0CB  /* A01 = +1.000005121846742950353e+00 */
-        .quad 0xBF265E6C77E66C8B  /* A02 = -1.706607253709506650304e-04 */
-        .quad 0xBFD53264DDCCEDA6  /* A03 = -3.312008062382240103361e-01 */
-        .quad 0xBE729C844D374A6E  /* A00 = -6.933284462462096107184e-08 */
-        .quad 0x3FF000067F019093  /* A01 = +1.000006195180536350264e+00 */
-        .quad 0xBF29CC5348D6DCE5  /* A02 = -1.968242326435338705130e-04 */
-        .quad 0xBFD52EE92121ED35  /* A03 = -3.309881995734998416658e-01 */
-        .quad 0xBE775AEA17EAA872  /* A00 = -8.700465590574974405858e-08 */
-        .quad 0x3FF00007CA1D66B8  /* A01 = +1.000007428656699559610e+00 */
-        .quad 0xBF2D8F5EB98A2637  /* A02 = -2.255252009216044881395e-04 */
-        .quad 0xBFD52B435CDF9128  /* A03 = -3.307655722585587376727e-01 */
-        .quad 0xBE7D04DA28C343F0  /* A00 = -1.081040272327705484794e-07 */
-        .quad 0x3FF000094443CCF5  /* A01 = +1.000008837375216730337e+00 */
-        .quad 0xBF30D5B76C947AE5  /* A02 = -2.568791210978817814332e-04 */
-        .quad 0xBFD52773A0776FAD  /* A03 = -3.305329386764651045105e-01 */
-        .quad 0xBE81DD77A12C51C7  /* A00 = -1.331054169875768625701e-07 */
-        .quad 0x3FF0000AF1AFD2DA  /* A01 = +1.000010437096696680470e+00 */
-        .quad 0xBF331230624C1680  /* A02 = -2.910011410651516805537e-04 */
-        .quad 0xBFD52379FC0B61DF  /* A03 = -3.302903138515186909352e-01 */
-        .quad 0xBE85D04EEEB3C435  /* A00 = -1.625247628488202841012e-07 */
-        .quad 0x3FF0000CD6C9B1F2  /* A01 = +1.000012244238970726684e+00 */
-        .quad 0xBF357F0742FADDD4  /* A02 = -3.280060509313874068243e-04 */
-        .quad 0xBFD51F56806D0E81  /* A03 = -3.300377134475880880338e-01 */
-        .quad 0xBE8A6E289B59681B  /* A00 = -1.969211333326924655065e-07 */
-        .quad 0x3FF0000EF8268F72  /* A01 = +1.000014275873550406715e+00 */
-        .quad 0xBF381E277A1B747A  /* A02 = -3.680082682942575423093e-04 */
-        .quad 0xBFD51B093F1D6FD4  /* A03 = -3.297751537663746734808e-01 */
-        .quad 0xBE8FCBC40EE9ABD5  /* A00 = -2.368983653301529373887e-07 */
-        .quad 0x3FF000115A883B6C  /* A01 = +1.000016549721943981410e+00 */
-        .quad 0xBF3AF17AC974B3D9  /* A02 = -4.111218235774406434303e-04 */
-        .quad 0xBFD516924A4C549C  /* A03 = -3.295026517456081105450e-01 */
-        .quad 0xBE92FFBC60A3F956  /* A00 = -2.831066871072026054144e-07 */
-        .quad 0x3FF0001402DCED8A  /* A01 = +1.000019084151832604590e+00 */
-        .quad 0xBF3DFAE9390C4801  /* A02 = -4.574603454311488280083e-04 */
-        .quad 0xBFD511F1B4D7DC3A  /* A03 = -3.292202249571719585575e-01 */
-        .quad 0xBE9690A22F96D5AD  /* A00 = -3.362443262393081632612e-07 */
-        .quad 0x3FF00016F63EFF5D  /* A01 = +1.000021898173108825247e+00 */
-        .quad 0xBF409E2C839605BB  /* A02 = -5.071370461992499986334e-04 */
-        .quad 0xBFD50D27924BEE00  /* A03 = -3.289278916051614487515e-01 */
-        .quad 0xBE9AA56C65E72A73  /* A00 = -3.970591019557469835586e-07 */
-        .quad 0x3FF0001A39F4A43E  /* A01 = +1.000025011433776978009e+00 */
-        .quad 0xBF425BD74C3D6667  /* A02 = -5.602647074553602319844e-04 */
-        .quad 0xBFD50833F6E1ABA2  /* A03 = -3.286256705238718156536e-01 */
-        .quad 0xBE9F4BD4FF1A83B0  /* A00 = -4.663500013744687071912e-07 */
-        .quad 0x3FF0001DD36F9EC2  /* A01 = +1.000028444215715683896e+00 */
-        .quad 0xBF44376634149405  /* A02 = -6.169556656102642569831e-04 */
-        .quad 0xBFD50316F77EDEE5  /* A03 = -3.283135811757190158922e-01 */
-        .quad 0xBEA3B625387BB079  /* A00 = -5.874486399249461304297e-07 */
-        .quad 0x3FF00023E14CFBA9  /* A01 = +1.000034217911642153709e+00 */
-        .quad 0xBF47392F923218D2  /* A02 = -7.087213783883111826306e-04 */
-        .quad 0xBFD4FB1FACDEB938  /* A03 = -3.278273761924483942209e-01 */
-        .quad 0xBEAA6E24F543500A  /* A00 = -7.876828740601738750574e-07 */
-        .quad 0x3FF0002D5C6E8412  /* A01 = +1.000043259679163742959e+00 */
-        .quad 0xBF4BAF02BD7FDD70  /* A02 = -8.448375110664940040861e-04 */
-        .quad 0xBFD4EFEE6527A7DE  /* A03 = -3.271442401734229177279e-01 */
-        .quad 0xBEB16E3EBE2157D0  /* A00 = -1.038947396133402500647e-06 */
-        .quad 0x3FF00038990FEE2F  /* A01 = +1.000053975962952312884e+00 */
-        .quad 0xBF50569481C574CB  /* A02 = -9.972048056490652716971e-04 */
-        .quad 0xBFD4E419278DA2B4  /* A03 = -3.264220129263251113372e-01 */
-        .quad 0xBEB6A7B6723165D4  /* A00 = -1.350350836279403750524e-06 */
-        .quad 0x3FF00045CAB4158E  /* A01 = +1.000066558657042303793e+00 */
-        .quad 0xBF531D7C9C849108  /* A02 = -1.166698160951775212202e-03 */
-        .quad 0xBFD4D7A0BB33B152  /* A03 = -3.256608799117844954552e-01 */
-        .quad 0xBEBD0EE2A8654AFD  /* A00 = -1.732000471561702711532e-06 */
-        .quad 0x3FF00055276F18D6  /* A01 = +1.000081209219890521211e+00 */
-        .quad 0xBF562FDBA3FB6C6C  /* A02 = -1.354183666925102939860e-03 */
-        .quad 0xBFD4CA85F1B93DB2  /* A03 = -3.248610363561638125773e-01 */
-        .quad 0xBEC269D4036A207E  /* A00 = -2.195047297096822741730e-06 */
-        .quad 0x3FF00066E7DA6E4E  /* A01 = +1.000098138500919997540e+00 */
-        .quad 0xBF5991499FC36B3A  /* A02 = -1.560518167983372759405e-03 */
-        .quad 0xBFD4BCC9A72283D6  /* A03 = -3.240226871658341556426e-01 */
-        .quad 0xBEC7154B6C09CFE1  /* A00 = -2.751729738565190291276e-06 */
-        .quad 0x3FF0007B47086B80  /* A01 = +1.000117566559055148900e+00 */
-        .quad 0xBF5D455433B4F8F4  /* A02 = -1.786548832412968197680e-03 */
-        .quad 0xBFD4AE6CC1BFE145  /* A03 = -3.231460468373550942722e-01 */
-        .quad 0xBECCA68CC64A0F8A  /* A00 = -3.415415948561670285790e-06 */
-        .quad 0x3FF00092827742F7  /* A01 = +1.000139722473418535387e+00 */
-        .quad 0xBF60A7BF15A527AF  /* A02 = -2.033112728132522705610e-03 */
-        .quad 0xBFD49F703214084C  /* A03 = -3.222313393636155876010e-01 */
-        .quad 0xBED19E68676B241B  /* A00 = -4.200644630977303616698e-06 */
-        .quad 0x3FF000ACDA037B26  /* A01 = +1.000164844146362863597e+00 */
-        .quad 0xBF62D99F836A02F8  /* A02 = -2.301036405072284102280e-03 */
-        .quad 0xBFD48FD4F2B91B28  /* A03 = -3.212787981359945810311e-01 */
-        .quad 0xBED57CF4B0C7AA54  /* A00 = -5.123164339408145209103e-06 */
-        .quad 0x3FF000CA8FD9E1A1  /* A01 = +1.000193178099017865534e+00 */
-        .quad 0xBF653A014548E686  /* A02 = -2.591135484433962181405e-03 */
-        .quad 0xBFD47F9C0844B38F  /* A03 = -3.202886658426046806447e-01 */
-        .quad 0xBEDA012B1B1A41E2  /* A00 = -6.199971197454598722328e-06 */
-        .quad 0x3FF000EBE868FDF4  /* A01 = +1.000224979259539459520e+00 */
-        .quad 0xBF67CA9427E0A544  /* A02 = -2.904214255086275467410e-03 */
-        .quad 0xBFD46EC6812ADB37  /* A03 = -3.192611943626845749655e-01 */
-        .quad 0xBEDF3EAC5BF12194  /* A00 = -7.449344990702664567927e-06 */
-        .quad 0x3FF001112A520784  /* A01 = +1.000260510744255704196e+00 */
-        .quad 0xBF6A8D01ABDA4DC4  /* A02 = -3.241065277345108255891e-03 */
-        .quad 0xBFD45D55759FFA4A  /* A03 = -3.181966446572103146551e-01 */
-        .quad 0xBEE2A541BC274267  /* A00 = -8.890883582164319970972e-06 */
-        .quad 0x3FF0013A9E5961F2  /* A01 = +1.000300043631906721231e+00 */
-        .quad 0xBF6D82ECD080C540  /* A02 = -3.602468994380686462264e-03 */
-        .quad 0xBFD44B4A0779C0AD  /* A03 = -3.170952866557950611259e-01 */
-        .quad 0xBEE61D97609A27F4  /* A00 = -1.054553560499505625520e-05 */
-        .quad 0x3FF001688F56A3AF  /* A01 = +1.000343856731187974773e+00 */
-        .quad 0xBF7056F8EFB683EC  /* A02 = -3.989193351487490407647e-03 */
-        .quad 0xBFD438A5620F0F74  /* A03 = -3.159573991399533543500e-01 */
-        .quad 0xBEEA145429EDD370  /* A00 = -1.243563138839952927732e-05 */
-        .quad 0x3FF0019B4A242A67  /* A01 = +1.000392236341804297339e+00 */
-        .quad 0xBF7207D31CA78D9B  /* A02 = -4.401993423445739288258e-03 */
-        .quad 0xBFD42568BA16E7CD  /* A03 = -3.147832696228050619602e-01 */
-        .quad 0xBEEE96370D52680F  /* A00 = -1.458491207477835326165e-05 */
-        .quad 0x3FF001D31D8E4115  /* A01 = +1.000445476009251821736e+00 */
-        .quad 0xBF73D4CC11EDC094  /* A02 = -4.841611050196221316400e-03 */
-        .quad 0xBFD411954D8664E7  /* A03 = -3.135731942252974469021e-01 */
-        .quad 0xBEF338C046215EF8  /* A00 = -1.833122622260562810219e-05 */
-        .quad 0x3FF00230C32C2EC1  /* A01 = +1.000534784691737621998e+00 */
-        .quad 0xBF76BD019BCC5DAF  /* A02 = -5.551344188254799492943e-03 */
-        .quad 0xBFD3F2C7156DC21E  /* A03 = -3.116929730668135389848e-01 */
-        .quad 0xBEF9B15EAE411EAE  /* A00 = -2.450261207822986676092e-05 */
-        .quad 0x3FF002C2DF057A4D  /* A01 = +1.000674124886830940184e+00 */
-        .quad 0xBF7B08CCD9AC1E30  /* A02 = -6.600189396301511801646e-03 */
-        .quad 0xBFD3C7A7A114FED8  /* A03 = -3.090609620157755976777e-01 */
-        .quad 0xBF00E36483C373B3  /* A00 = -3.221178528332122595812e-05 */
-        .quad 0x3FF0036F419480D7  /* A01 = +1.000838524028997644777e+00 */
-        .quad 0xBF7FD255D1777007  /* A02 = -7.768950679260206403087e-03 */
-        .quad 0xBFD39A453911D6CE  /* A03 = -3.062909180947429588215e-01 */
-        .quad 0xBF05DFA04DD12059  /* A00 = -4.172046622180685472624e-05 */
-        .quad 0x3FF00438B2A03D8D  /* A01 = +1.001030633695197069599e+00 */
-        .quad 0xBF828F8DBB4A9D10  /* A02 = -9.062869337255224921890e-03 */
-        .quad 0xBFD36AAB704697D9  /* A03 = -3.033856007044711255993e-01 */
-        .quad 0xBF0BF3E0C647DEFB  /* A00 = -5.331544597092331081714e-05 */
-        .quad 0x3FF005221063D36D  /* A01 = +1.001253189109060359741e+00 */
-        .quad 0xBF857A2CB3C96102  /* A02 = -1.048693584122917590862e-02 */
-        .quad 0xBFD338E65BBB4FEC  /* A03 = -3.003478904549854444639e-01 */
-        .quad 0xBF11A506ED7C9D31  /* A00 = -6.730894835681591541979e-05 */
-        .quad 0x3FF0062E4D0EA92A  /* A01 = +1.001508999829250345925e+00 */
-        .quad 0xBF88AB82C2761AF3  /* A02 = -1.204588085125866091241e-02 */
-        .quad 0xBFD305028D6BD206  /* A03 = -2.971807843271395688234e-01 */
-        .quad 0xBF1607C0922D9BF1  /* A00 = -8.403885708006799337092e-05 */
-        .quad 0x3FF007606C341961  /* A01 = +1.001800940198869449560e+00 */
-        .quad 0xBF8C25E6DA487BCF  /* A02 = -1.374416688582682892494e-02 */
-        .quad 0xBFD2CF0D0EE8F7B5  /* A03 = -2.938873906713255768075e-01 */
-        .quad 0xBF1B3A8480A0A16D  /* A00 = -1.038688061788578038307e-04 */
-        .quad 0x3FF008BB802D02D6  /* A01 = +1.002131939589323561535e+00 */
-        .quad 0xBF8FEB8AE99FD100  /* A02 = -1.558598065819483124983e-02 */
-        .quad 0xBFD297135BD0911B  /* A03 = -2.904709240558688843059e-01 */
-        .quad 0xBF20ABB9BDB75C65  /* A00 = -1.271881327357976163798e-04 */
-        .quad 0x3FF00A42A76D8CD1  /* A01 = +1.002504972472525901495e+00 */
-        .quad 0xBF91FF3D752BB9E6  /* A02 = -1.757522609380570560722e-02 */
-        .quad 0xBFD25D235C1F88B4  /* A03 = -2.869346999779154305799e-01 */
-        .quad 0xBF243D3254425461  /* A00 = -1.544116913733432829448e-04 */
-        .quad 0x3FF00BF909D1795E  /* A01 = +1.002923048355647051011e+00 */
-        .quad 0xBF94304E04D44942  /* A02 = -1.971551804042204897316e-02 */
-        .quad 0xBFD2214B5E61CFA6  /* A03 = -2.832821294498394371075e-01 */
-        .quad 0xBF286070011B61CE  /* A00 = -1.859795307186510085994e-04 */
-        .quad 0x3FF00DE1D5E1627E  /* A01 = +1.003389201612804537689e+00 */
-        .quad 0xBF9689D5F4163F59  /* A02 = -2.201017668045266231780e-02 */
-        .quad 0xBFD1E39A11C3B42C  /* A03 = -2.795167134743816728104e-01 */
-        .quad 0xBF2D250B366A79E8  /* A00 = -2.223564326486314902259e-04 */
-        .quad 0x3FF010003E134001  /* A01 = +1.003906481248123094829e+00 */
-        .quad 0xBF990C9FF91F6F81  /* A02 = -2.446222265267250853271e-02 */
-        .quad 0xBFD1A41E80084CDC  /* A03 = -2.756420374218586655246e-01 */
-        .quad 0xBF314DB5DDC2A30E  /* A00 = -2.640313157465248123865e-04 */
-        .quad 0x3FF012577608921B  /* A01 = +1.004477940624503018441e+00 */
-        .quad 0xBF9BB9626875B0C9  /* A02 = -2.707437288829409385849e-02 */
-        .quad 0xBFD162E80768A9D0  /* A03 = -2.716617653228725615122e-01 */
-        .quad 0xBF346A6133808864  /* A00 = -3.115165050094957730625e-04 */
-        .quad 0x3FF014EAAFCC88A3  /* A01 = +1.005106627192198898157e+00 */
-        .quad 0xBF9E90BEF9BF7419  /* A02 = -2.984903716411588595059e-02 */
-        .quad 0xBFD12006545F7FAD  /* A03 = -2.675796340899932457269e-01 */
-        .quad 0xBF37F180DC3848EA  /* A00 = -3.653468704395550778821e-04 */
-        .quad 0x3FF017BD19147861  /* A01 = +1.005795572250939295955e+00 */
-        .quad 0xBFA0C9A14C702E07  /* A02 = -3.278831537326359207851e-02 */
-        .quad 0xBFD0DB895B650092  /* A03 = -2.633994476818851682154e-01 */
-        .quad 0xBF3BEC6AAC6D7635  /* A00 = -4.260788377246944457107e-04 */
-        .quad 0x3FF01AD1D884E719  /* A01 = +1.006547780778822565040e+00 */
-        .quad 0xBFA260B2A1B1434A  /* A02 = -3.589399551186163439542e-02 */
-        .quad 0xBFD09581529E93D6  /* A03 = -2.591250712233067465817e-01 */
-        .quad 0xBF4164E26167882B  /* A00 = -5.308251737086202562063e-04 */
-        .quad 0x3FF01FEF14B62B81  /* A01 = +1.007796364693348545316e+00 */
-        .quad 0xBFA4EB014538AA42  /* A02 = -4.085544557559163403315e-02 */
-        .quad 0xBFD029D36FEAF41F  /* A03 = -2.525528519580024222613e-01 */
-        .quad 0xBF46F6FFF4E53DC8  /* A00 = -7.008313930700277652464e-04 */
-        .quad 0x3FF027CBB51CBBA0  /* A01 = +1.009715754956893363214e+00 */
-        .quad 0xBFA89DEC9FEC112E  /* A02 = -4.807986690687680864098e-02 */
-        .quad 0xBFCF2A99464D0DB4  /* A03 = -2.434875100390009317053e-01 */
-        .quad 0xBF4DCC9C4F66A4D9  /* A00 = -9.094012482836712945103e-04 */
-        .quad 0x3FF030E7CFCCD583  /* A01 = +1.011939822882909068014e+00 */
-        .quad 0xBFACAA3B95814081  /* A02 = -5.598627281199331645611e-02 */
-        .quad 0xBFCDF78F156BE7CF  /* A03 = -2.341173987004467604844e-01 */
-        .quad 0xBF5308ED74E5C7A6  /* A00 = -1.161796466103906435435e-03 */
-        .quad 0x3FF03B5986412ECB  /* A01 = +1.014489674026594512313e+00 */
-        .quad 0xBFB087EBA88DCC3F  /* A02 = -6.457398285947223148806e-02 */
-        .quad 0xBFCCBB9BD134862F  /* A03 = -2.244753619680052991736e-01 */
-        .quad 0xBF57FA23C00DF4B5  /* A00 = -1.463446533505758208674e-03 */
-        .quad 0x3FF0473558A1BCC0  /* A01 = +1.017384859292903342975e+00 */
-        .quad 0xBFB2E702BC6360EF  /* A02 = -7.383744334527241048871e-02 */
-        .quad 0xBFCB77D546379288  /* A03 = -2.145945160729250122955e-01 */
-        .quad 0xBF5DD12971557F71  /* A00 = -1.819887610814388068450e-03 */
-        .quad 0x3FF0548DDF5000A8  /* A01 = +1.020643112482540360020e+00 */
-        .quad 0xBFB571B63DA186E1  /* A02 = -8.376635555898871710045e-02 */
-        .quad 0xBFCA2D5202605148  /* A03 = -2.045080672838912594358e-01 */
-        .quad 0xBF6252B1AD5D4F17  /* A00 = -2.236697221556737096709e-03 */
-        .quad 0x3FF063738A910BF7  /* A01 = +1.024280110622155737232e+00 */
-        .quad 0xBFB8270C8E6B601B  /* A02 = -9.434584118878357184013e-02 */
-        .quad 0xBFC8DD27D950A07E  /* A03 = -1.942491351230763441116e-01 */
-        .quad 0xBF66470C91730CFC  /* A00 = -2.719425723258004842786e-03 */
-        .quad 0x3FF073F468FCF331  /* A01 = +1.028309259519300633556e+00 */
-        .quad 0xBFBB05C2952191E4  /* A02 = -1.055566419686964629854e-01 */
-        .quad 0xBFC7886A770DE2BD  /* A03 = -1.838505822486435070662e-01 */
-        .quad 0xBF6AD114AC8E98EC  /* A00 = -3.273525599485007861467e-03 */
-        .quad 0x3FF0861BF53E5226  /* A01 = +1.032741506559554434119e+00 */
-        .quad 0xBFBE0C4F9B461507  /* A02 = -1.173753503881763554650e-01 */
-        .quad 0xBFC6302A037CDE3A  /* A03 = -1.733448521642786954722e-01 */
-        .quad 0xBF6FFBDE2A6C2AF8  /* A00 = -3.904279630096648551207e-03 */
-        .quad 0x3FF099F2EB8E7DA3  /* A01 = +1.037585182326304034106e+00 */
-        .quad 0xBFC09C74D192DDF0  /* A02 = -1.297746680554463516444e-01 */
-        .quad 0xBFC4D571D8E3079F  /* A03 = -1.627638157861470424859e-01 */
-        .quad 0xBF72E8FDC0B952AA  /* A00 = -4.616728994353872309042e-03 */
-        .quad 0x3FF0AF7F273C9533  /* A01 = +1.042845872181101141152e+00 */
-        .quad 0xBFC244C512736F10  /* A02 = -1.427236881344176033792e-01 */
-        .quad 0xBFC379474F58B902  /* A03 = -1.521386277613104298645e-01 */
-        .quad 0xBF762EABAF17395B  /* A00 = -5.415602341101023557701e-03 */
-        .quad 0x3FF0C6C3886F63FB  /* A01 = +1.048526318502125631582e+00 */
-        .quad 0xBFC3FDF9918EA12A  /* A02 = -1.561881981590514389957e-01 */
-        .quad 0xBFC21CA89ECAB895  /* A03 = -1.414995932913753196036e-01 */
-        .quad 0xBF79D387CE5B2BAE  /* A00 = -6.305246822828998107258e-03 */
-        .quad 0x3FF0DFBFE2346376  /* A01 = +1.054626353847394337748e+00 */
-        .quad 0xBFC5C6DA43602620  /* A02 = -1.701309994680721970894e-01 */
-        .quad 0xBFC0C08BD8DB6631  /* A03 = -1.308760460731704100557e-01 */
-        .quad 0xBF7DDBA8E8DA9060  /* A00 = -7.289562037531366334164e-03 */
-        .quad 0x3FF0FA70F0D1B464  /* A01 = +1.061142864894713433443e+00 */
-        .quad 0xBFC79E18D92BAA7C  /* A02 = -1.845122394946264732241e-01 */
-        .quad 0xBFBECBBBF74C2669  /* A03 = -1.202962378266875381749e-01 */
-        .quad 0xBF81254E76EA25DA  /* A00 = -8.371937755572145950511e-03 */
-        .quad 0x3FF116D05835EBD0  /* A01 = +1.068069786618014660462e+00 */
-        .quad 0xBFC982539E2ED224  /* A02 = -1.992897531869327609755e-01 */
-        .quad 0xBFBC1B043C350159  /* A03 = -1.097872397413132278254e-01 */
-        .quad 0xBF8391ACBA863403  /* A00 = -9.555196230190082448686e-03 */
-        .quad 0x3FF134D4AA477FE2  /* A01 = +1.075398125794884141015e+00 */
-        .quad 0xBFCB7218609FEAFB  /* A02 = -2.144194099235717521079e-01 */
-        .quad 0xBFB970A16CB88329  /* A03 = -9.937485603633135211599e-02 */
-        .quad 0xBF87935088E48E8B  /* A00 = -1.151144902957603431692e-02 */
-        .quad 0x3FF1649892AD7DD3  /* A01 = +1.087059567413110938716e+00 */
-        .quad 0xBFCE6971DDE75409  /* A02 = -2.375929196847723912089e-01 */
-        .quad 0xBFB58291E88CB251  /* A03 = -8.402358939628952472223e-02 */
-        .quad 0xBF8DB3A62C325325  /* A00 = -1.450280973794233242702e-02 */
-        .quad 0x3FF1A9C900C6DEEA  /* A01 = +1.103951457056548068891e+00 */
-        .quad 0xBFD13DBC65B0E08E  /* A02 = -2.693930619311765140012e-01 */
-        .quad 0xBFB06696F62696D1  /* A03 = -6.406539449252625362252e-02 */
-        .quad 0xBF92583699F2E27A  /* A00 = -1.791463198307716858659e-02 */
-        .quad 0x3FF1F451B85AA9F0  /* A01 = +1.122148246892376022288e+00 */
-        .quad 0xBFD34FD5F8288180  /* A02 = -3.017477916164565954205e-01 */
-        .quad 0xBFA6FB692825B683  /* A03 = -4.488686194495718900788e-02 */
-        .quad 0xBF9641C26E673D6F  /* A00 = -2.173522757385398448959e-02 */
-        .quad 0x3FF24364DA5E2B07  /* A01 = +1.141453602790251542487e+00 */
-        .quad 0xBFD564A5A5EF5890  /* A02 = -3.342680092295120530821e-01 */
-        .quad 0xBF9B43712011A982  /* A03 = -2.662445791467283467968e-02 */
-        .quad 0xBF9A901038EC2F39  /* A00 = -2.594018313816024226548e-02 */
-        .quad 0x3FF2961356DFFEBA  /* A01 = +1.161639537196534011088e+00 */
-        .quad 0xBFD775EBB17198C7  /* A02 = -3.665723069046972759644e-01 */
-        .quad 0xBF833B1A926CD462  /* A03 = -9.390075295963199591975e-03 */
-        .quad 0xBF9F396A6A461B91  /* A00 = -3.049246095317987084727e-02 */
-        .quad 0x3FF2EB53BAEF534B  /* A01 = +1.182452898229899629357e+00 */
-        .quad 0xBFD97DABF8AD8BBD  /* A02 = -3.982953957076310058660e-01 */
-        .quad 0x3F7B8F6A3E0F8837  /* A03 = +6.728568086119371925713e-03 */
-        .quad 0xBFA21878590F8BAA  /* A00 = -3.534294211546946951064e-02 */
-        .quad 0x3FF34209790236E1  /* A01 = +1.203622315111197105253e+00 */
-        .quad 0xBFDB764C0E71BECB  /* A02 = -4.290952817018306997277e-01 */
-        .quad 0x3F962FE0C03F84C0  /* A03 = +2.166701482190513949888e-02 */
-        .quad 0xBFA4B36B9AD27ECC  /* A00 = -4.043136849327097492868e-02 */
-        .quad 0x3FF3990C5B12FC16  /* A01 = +1.224865298994477935679e+00 */
-        .quad 0xBFDD5AABB0D01390  /* A02 = -4.586590983092770912322e-01 */
-        .quad 0x3FA21DAF5CA162DB  /* A03 = +3.538272863142363083844e-02 */
-        .quad 0xBFA7645E4D7BF28B  /* A00 = -4.568762489177399105378e-02 */
-        .quad 0x3FF3EF2FD51C0D9F  /* A01 = +1.245895225962932562069e+00 */
-        .quad 0xBFDF26377E1B686E  /* A02 = -4.867075664057044503963e-01 */
-        .quad 0x3FA8803E756EE812  /* A03 = +4.785342391501513914509e-02 */
-        .quad 0xBFAA210925C64413  /* A00 = -5.103329263796054643398e-02 */
-        .quad 0x3FF44349F897D8E7  /* A01 = +1.266427966181760345066e+00 */
-        .quad 0xBFE06A7B02C6D8E2  /* A02 = -5.129981092675530707226e-01 */
-        .quad 0x3FAE3F194734F5D0  /* A03 = +5.907515520309980505687e-02 */
-        .quad 0xBFACDE48F8A19BBB  /* A00 = -5.638340029764018351832e-02 */
-        .quad 0x3FF49439D5466582  /* A01 = +1.286187966447272845727e+00 */
-        .quad 0xBFE131C7C1063DDC  /* A02 = -5.373266954429101183166e-01 */
-        .quad 0x3FB1ADEEC36AD805  /* A03 = +6.906025191241844940482e-02 */
-        .quad 0xBFAF905D8F585680  /* A00 = -6.164829611604449866036e-02 */
-        .quad 0x3FF4E0ED1FD27F99  /* A01 = +1.304913639360142818546e+00 */
-        .quad 0xBFE1E7A859DC1D3D  /* A02 = -5.595285182070380836095e-01 */
-        .quad 0x3FB3ED018E4642A1  /* A03 = +7.783517573831001679086e-02 */
-        .quad 0xBFB11595104160BA  /* A00 = -6.673556944713512906198e-02 */
-        .quad 0x3FF528650340490B  /* A01 = +1.322361958217302513319e+00 */
-        .quad 0xBFE28B14B40BC974  /* A02 = -5.794776455425521000109e-01 */
-        .quad 0x3FB5DF49F5BAF6D7  /* A03 = +8.543836831355676453281e-02 */
-        .quad 0xBFB2513A97344BA4  /* A00 = -7.155195418844911836587e-02 */
-        .quad 0x3FF569BA0DB5EE14  /* A01 = +1.338312200124055273420e+00 */
-        .quad 0xBFE31B53A8B67B20  /* A02 = -5.970857901737396389308e-01 */
-        .quad 0x3FB787F297BB0544  /* A03 = +9.191814617499455275507e-02 */
-        .quad 0xBFB37512E848FAFA  /* A00 = -7.600515528700305112331e-02 */
-        .quad 0x3FF5A41F33B403C8  /* A01 = +1.352568819013173495591e+00 */
-        .quad 0xBFE397F6EA9A58A5  /* A02 = -6.123003561103997904880e-01 */
-        .quad 0x3FB8EAA9FF25CA06  /* A03 = +9.733068923177520814782e-02 */
-        .quad 0xBFB47B3E603AFC5D  /* A00 = -8.000554894805263217439e-02 */
-        .quad 0x3FF5D6E3EDE40487  /* A01 = +1.364963464031718975988e+00 */
-        .quad 0xBFE400D5BCA6D631  /* A02 = -6.251019177058819709103e-01 */
-        .quad 0x3FBA0B830ED567FE  /* A03 = +1.017381583418739132707e-01 */
-        .quad 0xBFB5BBFE8AC90496  /* A00 = -8.489981544791400103200e-02 */
-        .quad 0x3FF612BA70107E95  /* A01 = +1.379572332145390989311e+00 */
-        .quad 0xBFE477EAF1FA7693  /* A02 = -6.396383978023599814478e-01 */
-        .quad 0x3FBB4784B7C08A95  /* A03 = +1.065600346196709652391e-01 */
-        .quad 0xBFB6D5D940743939  /* A00 = -8.920057128509463473254e-02 */
-        .quad 0x3FF644A8748F70CE  /* A01 = +1.391762214006166953340e+00 */
-        .quad 0xBFE4D646AB07EA37  /* A02 = -6.511567440459832267763e-01 */
-        .quad 0x3FBC354F4E1D5292  /* A03 = +1.101884427747086558913e-01 */
-        .quad 0xBFB7223D19E4F3D1  /* A00 = -9.036619074045339206069e-02 */
-        .quad 0x3FF6518FEB42B7FA  /* A01 = +1.394912642466350494175e+00 */
-        .quad 0xBFE4ED86CB87498C  /* A02 = -6.539949393430091184598e-01 */
-        .quad 0x3FBC6D29F28CCA9B  /* A03 = +1.110407082713131127205e-01 */
-        .quad 0xBFB6878652FF6312  /* A00 = -8.800544287022329936754e-02 */
-        .quad 0x3FF63948C302D040  /* A01 = +1.388985406648330922508e+00 */
-        .quad 0xBFE4C4E2E7904E17  /* A02 = -6.490339777687407218920e-01 */
-        .quad 0x3FBC127356CA1ABE  /* A03 = +1.096565329445224612481e-01 */
-        .quad 0xBFB4F5D18B0C91D6  /* A00 = -8.187589306596207427980e-02 */
-        .quad 0x3FF5FD27EB7DD0B8  /* A01 = +1.374305648697413673176e+00 */
-        .quad 0xBFE464E01A2B2FC6  /* A02 = -6.373138915164353601739e-01 */
-        .quad 0x3FBB460547674A30  /* A03 = +1.065371798825160976065e-01 */
-        .quad 0xBFB26642FA16A685  /* A00 = -7.187288861919156890412e-02 */
-        .quad 0x3FF59F9BEDE1C95A  /* A01 = +1.351467065073470141812e+00 */
-        .quad 0xBFE3D67920C8FBEA  /* A02 = -6.199308052381387046381e-01 */
-        .quad 0x3FBA24F6A8D3CBC1  /* A03 = +1.021265184570401413078e-01 */
-        .quad 0xBFADB5294794F097  /* A00 = -5.802277563859197656582e-02 */
-        .quad 0x3FF523EA7B9CF453  /* A01 = +1.321268542159732772845e+00 */
-        .quad 0xBFE322A8B55E35DB  /* A02 = -5.979808370918208160205e-01 */
-        .quad 0x3FB8C8673B1B3E37  /* A03 = +9.680791085269722928697e-02 */
-        .quad 0xBFA4B7D661965C6A  /* A00 = -4.046506825687219699450e-02 */
-        .quad 0x3FF48DE3E2CE3122  /* A01 = +1.284641157110919085227e+00 */
-        .quad 0xBFE251FED1A7F445  /* A02 = -5.725092024655472622285e-01 */
-        .quad 0x3FB745699FCABDB9  /* A03 = +9.090290213747821701507e-02 */
-        .quad 0xBF93E60456E4EE1D  /* A00 = -1.943213253365004902773e-02 */
-        .quad 0x3FF3E1A14E628A59  /* A01 = +1.242585474196536532432e+00 */
-        .quad 0xBFE16C5AB660E876  /* A02 = -5.444768488007543094653e-01 */
-        .quad 0x3FB5AD33AA8C188F  /* A03 = +8.467410005332197397987e-02 */
-        .quad 0x3F738C17C47C7961  /* A00 = +4.772274820224659853951e-03 */
-        .quad 0x3FF3234DDE3BD146  /* A01 = +1.196119182682268355933e+00 */
-        .quad 0xBFE078C0D77A9D3B  /* A02 = -5.147403915952176722826e-01 */
-        .quad 0x3FB40D74B3E276B8  /* A03 = +7.833032027925923568290e-02 */
-        .quad 0x3FA0474BECC689C7  /* A00 = +3.179394975019849550746e-02 */
-        .quad 0x3FF256FB4FA7D18A  /* A01 = +1.146235762743432307076e+00 */
-        .quad 0xBFDEFA8E3FB285E2  /* A02 = -4.840427038235174395098e-01 */
-        .quad 0x3FB270C007493D59  /* A03 = +7.203293016322244446403e-02 */
-        .quad 0x3FAF5BD51E479BDC  /* A00 = +6.124750132203590768931e-02 */
-        .quad 0x3FF18081D0B53BC5  /* A01 = +1.093873801484492647162e+00 */
-        .quad 0xBFDCFE2439BD0C03  /* A02 = -4.530115665294831006626e-01 */
-        .quad 0x3FB0DEFE5A45AFDD  /* A03 = +6.590261176978580437424e-02 */
-        .quad 0x3FB7BD5D2806EA26  /* A00 = +9.273321368429118805032e-02 */
-        .quad 0x3FF0A369E35B4440  /* A01 = +1.039895904647224256223e+00 */
-        .quad 0xBFDB04BC5C9951E7  /* A02 = -4.221640495573226181669e-01 */
-        .quad 0x3FAEBBBAA9D6DEEF  /* A03 = +6.002600978120919278380e-02 */
-        .quad 0x3FC01BE411098DBC  /* A00 = +1.258511622610124502941e-01 */
-        .quad 0x3FEF85BDABC031C1  /* A01 = +9.850757936961188621083e-01 */
-        .quad 0xBFD91521375097C2  /* A02 = -3.919146576102968682065e-01 */
-        .quad 0x3FABE26F0086D982  /* A03 = +5.446192628317005068883e-02 */
-        .quad 0x3FC481D7FF5776B9  /* A00 = +1.602125164781023347604e-01 */
-        .quad 0x3FEDC3506C1E7218  /* A01 = +9.300920592973538347792e-01 */
-        .quad 0xBFD7349A88DA7D4F  /* A02 = -3.625856720409119104964e-01 */
-        .quad 0x3FA936E2DFF8E2AE  /* A03 = +4.924687370334389358018e-02 */
-        .quad 0x3FC90471F96FA27A  /* A00 = +1.954481571149420671141e-01 */
-        .quad 0x3FEC0451601987A2  /* A01 = +8.755270840595026360376e-01 */
-        .quad 0xBFD5671CD4B898DC  /* A02 = -3.344184949259110251063e-01 */
-        .quad 0x3FA6BB9594603B67  /* A03 = +4.439990459660841243261e-02 */
-        .quad 0x3FCFD8ADB9ED944C  /* A00 = +2.488000066615846384011e-01 */
-        .quad 0x3FE978C073F6809A  /* A01 = +7.959902062321078108909e-01 */
-        .quad 0xBFD2DF7E00BCD5A9  /* A02 = -2.948908812716931060471e-01 */
-        .quad 0x3FA3614033D490B2  /* A03 = +3.785133965200894456959e-02 */
-        .quad 0x3FD4846A12AFE5A0  /* A00 = +3.205819303981005674586e-01 */
-        .quad 0x3FE63A1147D40472  /* A01 = +6.945883181471244061100e-01 */
-        .quad 0xBFCFA2268AD34450  /* A02 = -2.471359422548027318101e-01 */
-        .quad 0x3F9F150201D9FFE0  /* A03 = +3.035357605267552383310e-02 */
-        .quad 0x3FD9018641F82BEB  /* A00 = +3.907180446846598154131e-01 */
-        .quad 0x3FE33B7C220FFBDC  /* A01 = +6.010113396913498995389e-01 */
-        .quad 0xBFCA4E4187E29C86  /* A02 = -2.055131829740483584423e-01 */
-        .quad 0x3F98C30CED19F8F4  /* A03 = +2.418155858185229434287e-02 */
-        .quad 0x3FDD4B8255BEB078  /* A00 = +4.577337109901757905561e-01 */
-        .quad 0x3FE0858B19D3A49B  /* A01 = +5.163016800335243905451e-01 */
-        .quad 0xBFC5BC929EACE564  /* A02 = -1.698172831327539045176e-01 */
-        .quad 0x3F93A083CE57DE2B  /* A03 = +1.916700312537337677621e-02 */
-        .quad 0x3FE0A8E5E039295C  /* A00 = +5.206174258576470315063e-01 */
-        .quad 0x3FDC35E1234583FE  /* A01 = +4.407885403107342225937e-01 */
-        .quad 0xBFC1DE034E31AEB9  /* A02 = -1.395877963835710222629e-01 */
-        .quad 0x3F8EFDEBB3471BDC  /* A03 = +1.513275280821162888101e-02 */
-        .quad 0x3FE2851B603CB2A5  /* A00 = +5.787484054213406503564e-01 */
-        .quad 0x3FD7F4A44ABBB286  /* A01 = +3.743067483726821853551e-01 */
-        .quad 0xBFBD3EEB67087DE7  /* A02 = -1.142413260026767657385e-01 */
-        .quad 0x3F8864F38329E8BD  /* A03 = +1.191129917173260922836e-02 */
-        .quad 0x3FE437DBE3C34AC1  /* A00 = +6.318187187665317283702e-01 */
-        .quad 0x3FD43F6F789441B5  /* A01 = +3.163717916040938438194e-01 */
-        .quad 0xBFB7D92E7901B9A4  /* A02 = -9.315767721429907277653e-02 */
-        .quad 0x3F8327ED342308E1  /* A03 = +9.353497651663324544136e-03 */
-        .quad 0x3FE5C0977766D55C  /* A00 = +6.797597248138731451661e-01 */
-        .quad 0x3FD10B42A764D8F9  /* A01 = +2.663122782427219115142e-01 */
-        .quad 0xBFB3633351D3D70F  /* A02 = -7.573242900602060456716e-02 */
-        .quad 0x3F7E079E30FF899C  /* A03 = +7.331483779099558922843e-03 */
-        .quad 0x3FE7202CE08A88C4  /* A00 = +7.226776490754436288455e-01 */
-        .quad 0x3FCC973EB5662B01  /* A01 = +2.233656297433626314319e-01 */
-        .quad 0xBFAF70A455F9920B  /* A02 = -6.140626477716545211782e-02 */
-        .quad 0x3F77812411CE99B6  /* A03 = +5.738392731393584730859e-03 */
-        .quad 0x3FE85879424095B1  /* A00 = +7.608000082006382003286e-01 */
-        .quad 0x3FC7E73BD1674D84  /* A01 = +1.867441914060742336190e-01 */
-        .quad 0xBFA96F84E4BF333B  /* A02 = -4.967894832916504993525e-02 */
-        .quad 0x3F72606DDCA6E117  /* A03 = +4.486493251924870105662e-03 */
-        .quad 0x3FE96BFE4957F4DD  /* A00 = +7.944327766887472330737e-01 */
-        .quad 0x3FC3ED4780D25478  /* A01 = +1.556786898624158421711e-01 */
-        .quad 0xBFA489C5F9A56B58  /* A02 = -4.011362717093075458408e-02 */
-        .quad 0x3F6CB5DC17E9AD2A  /* A03 = +3.504686231556104931972e-03 */
-        .quad 0x3FEA5D9CB2F41234  /* A00 = +8.239272589858672724006e-01 */
-        .quad 0x3FC091A758374DCF  /* A01 = +1.294449978582705440555e-01 */
-        .quad 0xBFA08E436D4B5CE0  /* A02 = -3.233538350257858517978e-02 */
-        .quad 0x3F666997AD53E6B7  /* A03 = +2.735897297154145629133e-03 */
-        .quad 0x3FEB3060342CB850  /* A00 = +8.496552485501158713532e-01 */
-        .quad 0x3FBB7D30BBC7DC1B  /* A01 = +1.073790033768634993860e-01 */
-        .quad 0xBF9AA6BA3443D9E3  /* A02 = -2.602663940430173170060e-02 */
-        .quad 0x3F617CA764B7850B  /* A03 = +2.134634914668814050648e-03 */
-        .quad 0x3FEBE759A6A0C7B8  /* A00 = +8.719909910635044170135e-01 */
-        .quad 0x3FB6C10DE6A703FF  /* A01 = +8.888327485239243264115e-02 */
-        .quad 0xBF956C566D8BE1F6  /* A02 = -2.092108768099084498138e-02 */
-        .quad 0x3F5B46D1A4A59CF8  /* A03 = +1.664833764687232917079e-03 */
-        .quad 0x3FEC858494887A04  /* A00 = +8.912985707318630268503e-01 */
-        .quad 0x3FB2CC31F543394D  /* A01 = +7.342827070099140762682e-02 */
-        .quad 0xBF9133477FF69137  /* A02 = -1.679717749142747504343e-02 */
-        .quad 0x3F5544482FBB4DA5  /* A03 = +1.298017973501022466823e-03 */
-        .quad 0x3FED0DB59D0E32E9  /* A00 = +9.079235141267335551518e-01 */
-        .quad 0x3FAF006BAFFC6EF4  /* A01 = +6.055008433597022787787e-02 */
-        .quad 0xBF8B97146FA2B97A  /* A02 = -1.347175565419144252499e-02 */
-        .quad 0x3F5093B01F4CDC69  /* A03 = +1.011774057770665211434e-03 */
-        .quad 0x3FEDB487C3EC457C  /* A00 = +9.282873942012623835751e-01 */
-        .quad 0x3FA7390C09D0BD1D  /* A01 = +4.535710925881118044112e-02 */
-        .quad 0xBF83D9F7C3181106  /* A02 = -9.693084374710735778846e-03 */
-        .quad 0x3F46E34A0A3C0E64  /* A03 = +6.984817050299072134500e-04 */
-        .quad 0x3FEE5FFCB4E6EB00  /* A00 = +9.492171796076434020506e-01 */
-        .quad 0x3F9F4913ED00AADF  /* A01 = +3.055220731782070861526e-02 */
-        .quad 0xBF79670BD0E59B5C  /* A02 = -6.201788097633133961528e-03 */
-        .quad 0x3F3BC998EBCAF96D  /* A03 = +4.240034429975534616304e-04 */
-        .quad 0x3FEEDBA41E9542FE  /* A00 = +9.643116566968215064293e-01 */
-        .quad 0x3F94F5DD18D9C24D  /* A01 = +2.046914543319848858727e-02 */
-        .quad 0xBF7034896AA122B9  /* A02 = -3.956352980886528904192e-03 */
-        .quad 0x3F30DCCB47810B39  /* A03 = +2.573009765038273091199e-04 */
-        .quad 0x3FEF33F2882520ED  /* A00 = +9.750912341196716903724e-01 */
-        .quad 0x3F8BF37F2CF553FF  /* A01 = +1.364802699996836392315e-02 */
-        .quad 0xBF649F6F05A69619  /* A02 = -2.517430152880317534986e-03 */
-        .quad 0x3F247623C950AAC9  /* A03 = +1.561087307505231250044e-04 */
-        .quad 0x3FEF727757751741  /* A00 = +9.827229221489021115943e-01 */
-        .quad 0x3F828E67912C4400  /* A01 = +9.060677640748693306705e-03 */
-        .quad 0xBF5A2F51A806CC2C  /* A02 = -1.598195784123355826789e-03 */
-        .quad 0x3F18D35D7687E613  /* A03 = +9.470231965016282719549e-05 */
-        .quad 0x3FEF9E6325C5942A  /* A00 = +9.880843866091073568469e-01 */
-        .quad 0x3F788AB117618F76  /* A01 = +5.991641772286606867914e-03 */
-        .quad 0xBF5096EAB0B1EA89  /* A02 = -1.012543859160305046233e-03 */
-        .quad 0x3F0E1E50EC4435AB  /* A03 = +5.744633156910412119652e-05 */
-        .quad 0x3FEFBD0784049369  /* A00 = +9.918248728250605994461e-01 */
-        .quad 0x3F702BBD8294035F  /* A01 = +3.947963975634432264028e-03 */
-        .quad 0xBF44FB55E0F00593  /* A02 = -6.403130845457509273330e-04 */
-        .quad 0x3F0244DCD723230A  /* A03 = +3.484534217219031730379e-05 */
-        .quad 0x3FEFD245E2366A43  /* A00 = +9.944180887426415926811e-01 */
-        .quad 0x3F653D82EC088433  /* A01 = +2.592807490387838333795e-03 */
-        .quad 0xBF3A7DF75E013CB8  /* A02 = -4.042366908878036561859e-04 */
-        .quad 0x3EF6298E69F991CD  /* A03 = +2.113564425911141559972e-05 */
-        .quad 0x3FEFE0EAA508BC69  /* A00 = +9.962056372950317539861e-01 */
-        .quad 0x3F5BD0771AF3FDDA  /* A01 = +1.697651208644282514598e-03 */
-        .quad 0xBF30B2E1254DE571  /* A02 = -2.548026725928887099328e-04 */
-        .quad 0x3EEAE28B70EC0256  /* A03 = +1.281973848454955042307e-05 */
-        .quad 0x3FEFEAF5303D7F96  /* A00 = +9.974313680831865536192e-01 */
-        .quad 0x3F5229111365657E  /* A01 = +1.108423877289460134782e-03 */
-        .quad 0xBF250572D04DFE66  /* A02 = -1.603796628408704519168e-04 */
-        .quad 0x3EE04E89BB57C981  /* A03 = +7.775682983689149966743e-06 */
-        .quad 0x3FEFF1CF52F1CF44  /* A00 = +9.982678051005469122003e-01 */
-        .quad 0x3F47A71316147CEB  /* A01 = +7.218211359577819110842e-04 */
-        .quad 0xBF1A6D7604055719  /* A02 = -1.008132248946049582547e-04 */
-        .quad 0x3ED3C8047586A85C  /* A03 = +4.716233739913014633626e-06 */
-        .quad 0x3FEFF6770369EF69  /* A00 = +9.988360468555416149528e-01 */
-        .quad 0x3F3EBB261180FBF0  /* A01 = +4.689186039321105101130e-04 */
-        .quad 0xBF1097754FE19D7F  /* A02 = -6.329206004950480057066e-05 */
-        .quad 0x3EC7FEFF83BCA0A7  /* A03 = +2.860556404988488738366e-06 */
-        .quad 0x3FEFF99D42371AC4  /* A00 = +9.992204945818561334647e-01 */
-        .quad 0x3F33EB2AEC271F59  /* A01 = +3.039340773764907474054e-04 */
-        .quad 0xBF04CF18E0FC0D79  /* A02 = -3.968996690952969588805e-05 */
-        .quad 0x3EBD1BDBD6019BE9  /* A03 = +1.735021065507727833886e-06 */
-        .quad 0x3FEFFBBCA32B0D91  /* A00 = +9.994795977476532700123e-01 */
-        .quad 0x3F29C41E1615110A  /* A01 = +1.965796209707565346710e-04 */
-        .quad 0xBEFA11F93D9DCB5A  /* A02 = -2.486248909101414873235e-05 */
-        .quad 0x3EB1A7CA4546F7A7  /* A03 = +1.052345642723709228769e-06 */
-        .quad 0x3FEFFD298B8E8DE2  /* A00 = +9.996535993308806045121e-01 */
-        .quad 0x3F20A1C42D523C5B  /* A01 = +1.268913244172078754520e-04 */
-        .quad 0xBEF0507A364AFAE4  /* A02 = -1.555859070622834605755e-05 */
-        .quad 0x3EA56ACA17E7CDF4  /* A03 = +6.382806956848098872313e-07 */
-        .quad 0x3FEFFE1DC82BA5A3  /* A00 = +9.997700604991915929176e-01 */
-        .quad 0x3F156E73B90F1769  /* A01 = +8.175450626798714452801e-05 */
-        .quad 0xBEE4663579D0A09F  /* A02 = -9.727122057226747625365e-06 */
-        .quad 0x3E99FAF6FEC5D4C1  /* A03 = +3.871371052824002996020e-07 */
-        .quad 0x3FEFFEF8D0BB5E81  /* A00 = +9.998745037837154514548e-01 */
-        .quad 0x3F06686DA18D39C3  /* A01 = +4.273972098777251447726e-05 */
-        .quad 0xBED46BC298073E90  /* A02 = -4.868731025855742842491e-06 */
-        .quad 0x3E88E42286B9D0FD  /* A03 = +1.854535328530838170114e-07 */
-        .quad 0x3FEFFF8DBC68DDC7  /* A00 = +9.999455146670975791423e-01 */
-        .quad 0x3EF26B2953A80AF0  /* A01 = +1.756534514108903368909e-05 */
-        .quad 0xBEBFC4472D580F83  /* A02 = -1.893443529411295465239e-06 */
-        .quad 0x3E72505B4553D19F  /* A03 = +6.822456673547912277047e-08 */
-        .quad 0x3FEFFFCED1276609  /* A00 = +9.999765477215883935358e-01 */
-        .quad 0x3EDE1A94C7CC58F5  /* A01 = +7.177313020153979672606e-06 */
-        .quad 0xBEA8A2C988744E57  /* A02 = -7.342066660497443762363e-07 */
-        .quad 0x3E5AF30036BBBAF4  /* A03 = +2.509841882843541084885e-08 */
-        .quad 0x3FEFFFEAFE70FCFC  /* A00 = +9.999899835164849370983e-01 */
-        .quad 0x3EC879175E3549F5  /* A01 = +2.917410471128503564412e-06 */
-        .quad 0xBE930E36677D1813  /* A02 = -2.839493400307523115929e-07 */
-        .quad 0x3E43D4005B42D48F  /* A03 = +9.233192745401904898013e-09 */
-        .quad 0x3ff0000000000000
-        .quad 0x0000000000000000
-        .quad 0x0000000000000000
-        .quad 0x0000000000000000
-        .align 32
-        .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000           /* _sSignMask        */
-        .align 32
-        .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff           /* _sAbsMask         */
-        .align 32
-        .long 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000, 0x7ff80000           /* _iExpMantMask     */
-        .align 32
-        .long 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000, 0x7f000000           /* _iExpMask         */
-        .align 32
-        .long 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000, 0x3cf80000           /* _iMinIdxOfsMask   */
-        .align 32
-        .long 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000, 0x04280000           /* _iMaxIdxMask      */
-        .align 32
-        .type	__svml_stanh_data_internal,@object
-        .size	__svml_stanh_data_internal,.-__svml_stanh_data_internal
+	vcvtps2pd %xmm4, %ymm5
+
+	vextractf128 $1, %ymm4, %xmm4
+	vcvtps2pd %xmm4, %ymm4
+
+	vmovdqu	16(%rcx, %rax), %xmm2
+	vinsertf128 $1, 16(%r11, %rax), %ymm2, %ymm2
+
+	vfmadd213pd %ymm3, %ymm5, %ymm1
+
+	vmovupd	16(%rdx, %rax), %xmm3
+	vinsertf128 $1, 16(%r10, %rax), %ymm3, %ymm3
+
+	vunpcklpd %ymm3, %ymm2, %ymm10
+	vunpckhpd %ymm3, %ymm2, %ymm2
+
+	vfmadd213pd %ymm10, %ymm4, %ymm2
+	vfmadd213pd %ymm6, %ymm4, %ymm2
+	vfmadd213pd %ymm7, %ymm4, %ymm2
+	vcvtpd2ps %ymm2, %xmm2
+
+	vmovdqu	(%r9, %rax), %xmm7
+	vinsertf128 $1, (%rdi, %rax), %ymm7, %ymm7
+
+	vmovupd	(%r8, %rax), %xmm3
+	vinsertf128 $1, (%rsi, %rax), %ymm3, %ymm3
+
+	vunpckhpd %ymm3, %ymm7, %ymm4
+	vunpcklpd %ymm3, %ymm7, %ymm7
+
+	vfmadd213pd %ymm4, %ymm5, %ymm1
+	vfmadd213pd %ymm7, %ymm5, %ymm1
+
+
+	vcvtpd2ps %ymm1, %xmm1
+	vinsertf128 $1, %xmm2, %ymm1, %ymm1
+
+	vmovmskps %ymm15, %edx
+	vandnps	%ymm0, %ymm11, %ymm2
+	testl	%edx, %edx
+	/* Go to special inputs processing branch.  */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	/* Wait until after branch of write over ymm0.  */
+	vorps	%ymm2, %ymm1, %ymm0
+	/* No stack restoration on the fastpath.  */
+	ret
+
+
+L(SPECIAL_VALUES_BRANCH):
+	pushq	%rbp
+	/* Need to callee save registers to preserve state across tanhf calls.
+	 */
+	pushq	%r12
+	pushq	%r13
+	movq	%rsp, %rbp
+
+	/* Align stack and make room for 2x ymm vectors.  */
+	andq	$-32, %rsp
+	addq	$-64, %rsp
+
+	/* Save all already computed inputs.  */
+	vorps	%ymm2, %ymm1, %ymm1
+	vmovups	%ymm1, (%rsp)
+	/* Save origional input (ymm0 unchanged up to this point).  */
+	vmovups	%ymm0, 32(%rsp)
+
+	vzeroupper
+
+	/* edx has 1s where there was a special value that needs to be handled
+	   by a tanhf call.  */
+	movl	%edx, %r13d
+L(SPECIAL_VALUES_LOOP):
+	/* use r12 as index for special value that is saved across calls to
+	   tanhf. We technically don't need a callee save register here as offset
+	   to rsp is always [0, 28] so we can restore rsp by realigning to 64.
+	   Essentially the tradeoff is 1 extra save/restore vs 2 extra instructions
+	   in the loop.  */
+	xorl	%r12d, %r12d
+	tzcntl	%r13d, %r12d
+
+	/* Scalar math fucntion call to process special input.  */
+	movss	32(%rsp, %r12, 4), %xmm0
+	call	tanhf@PLT
+	/* No good way to avoid the store-forwarding fault this will cause on
+	   return. `lfence` avoids the SF fault but at greater cost as it
+	   serialized stack/callee save restoration.  */
+	movss	%xmm0, (%rsp, %r12, 4)
+
+	blsr	%r13d, %r13d
+	jnz	L(SPECIAL_VALUES_LOOP)
+
+	/* All results have been written to 32(%rsp).  */
+	vmovups	(%rsp), %ymm0
+	movq	%rbp, %rsp
+	popq	%r13
+	popq	%r12
+	popq	%rbp
+	ret
+END(_ZGVdN8v_tanhf_avx2)
-- 
2.25.1


^ permalink raw reply	[flat|nested] 9+ messages in thread

end of thread, other threads:[~2022-02-02  0:42 UTC | newest]

Thread overview: 9+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-01-30  4:36 [PATCH v1] x86: Optimize svml_s_tanhf_core_{sse4|avx2|avx512}.S Noah Goldstein
2022-02-01 20:02 ` Sunil Pandey
2022-02-01 20:20   ` Noah Goldstein
2022-02-01 20:58     ` [PATCH v2 1/3] x86: Optimize svml_s_tanhf_core_avx512.S Noah Goldstein
2022-02-01 20:58       ` [PATCH v2 2/3] x86: Optimize svml_s_tanhf_core_avx2.S Noah Goldstein
2022-02-01 20:58       ` [PATCH v2 3/3] x86: Optimize svml_s_tanhf_core_sse2.S Noah Goldstein
2022-02-01 21:29     ` [PATCH v1] x86: Optimize svml_s_tanhf_core_{sse4|avx2|avx512}.S Sunil Pandey
2022-02-01 21:54       ` Noah Goldstein
2022-02-02  0:41         ` Sunil Pandey

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).