about summary refs log tree commit diff
diff options
context:
space:
mode:
authorSunil K Pandey <skpgkp2@gmail.com>2022-03-07 10:47:14 -0800
committerSunil K Pandey <skpgkp2@gmail.com>2022-03-07 21:44:09 -0800
commite6303e19bb9be7014f235695e3617078756f767d (patch)
tree4f9f960bf0bfc0eb0f860924b5a653a4858999ad
parentedc4a5012be626f6e05a8cbcf5ae352f2b79fcff (diff)
downloadglibc-e6303e19bb9be7014f235695e3617078756f767d.tar.gz
glibc-e6303e19bb9be7014f235695e3617078756f767d.tar.xz
glibc-e6303e19bb9be7014f235695e3617078756f767d.zip
x86_64: Fix svml_s_sinhf8_core_avx2.S code formatting
This commit contains following formatting changes

1. Instructions proceeded by a tab.
2. Instruction less than 8 characters in length have a tab
   between it and the first operand.
3. Instruction greater than 7 characters in length have a
   space between it and the first operand.
4. Tabs after `#define`d names and their value.
5. 8 space at the beginning of line replaced by tab.
6. Indent comments with code.
7. Remove redundent .text section.
8. 1 space between line content and line comment.
9. Space after all commas.

Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
-rw-r--r--sysdeps/x86_64/fpu/multiarch/svml_s_sinhf8_core_avx2.S492
1 files changed, 245 insertions, 247 deletions
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sinhf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sinhf8_core_avx2.S
index ada2f6dd1d..8c4b46cee2 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_sinhf8_core_avx2.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sinhf8_core_avx2.S
@@ -34,276 +34,274 @@
 
 /* Offsets for data table __svml_ssinh_data_internal
  */
-#define _sInvLn2                      	0
-#define _sLn2hi                       	32
-#define _sLn2lo                       	64
-#define _sSign                        	96
-#define _sShifter                     	128
-#define _iDomainRange                 	160
-#define _sPC1                         	192
-#define _sPC2                         	224
-#define _sPC3                         	256
-#define _sPC4                         	288
-#define _sPC5                         	320
-#define _sPC6                         	352
-#define _iHalf                        	384
+#define _sInvLn2			0
+#define _sLn2hi				32
+#define _sLn2lo				64
+#define _sSign				96
+#define _sShifter			128
+#define _iDomainRange			160
+#define _sPC1				192
+#define _sPC2				224
+#define _sPC3				256
+#define _sPC4				288
+#define _sPC5				320
+#define _sPC6				352
+#define _iHalf				384
 
 #include <sysdep.h>
 
-        .text
-	.section .text.avx2,"ax",@progbits
+	.section .text.avx2, "ax", @progbits
 ENTRY(_ZGVdN8v_sinhf_avx2)
-        pushq     %rbp
-        cfi_def_cfa_offset(16)
-        movq      %rsp, %rbp
-        cfi_def_cfa(6, 16)
-        cfi_offset(6, -16)
-        andq      $-32, %rsp
-        subq      $96, %rsp
-        vmovups   _sInvLn2+__svml_ssinh_data_internal(%rip), %ymm7
-        vmovups   _sShifter+__svml_ssinh_data_internal(%rip), %ymm4
-        vmovups   _sLn2hi+__svml_ssinh_data_internal(%rip), %ymm5
-
-/*
- * sinh(X) = sG2 + sG1*sinh(dR) + sG2*sR2*(a2+sR2*(a4+a6*sR2)
- * sOut = (a4 +a6*sR2)
- */
-        vmovups   _sPC6+__svml_ssinh_data_internal(%rip), %ymm14
-
-/*
- * sinh(r) = r*((a1=1)+r^2*(a3+r^2*(a5+{v1 r^2*a7})))) = r + r*(r^2*(a3+r^2*(a5+r^2*a7))) ....
- * sSinh_r = (a3+r^2*a5)
- */
-        vmovups   _sPC5+__svml_ssinh_data_internal(%rip), %ymm12
-        vmovups   _iHalf+__svml_ssinh_data_internal(%rip), %ymm8
-        vmovaps   %ymm0, %ymm2
-
-/*
- *  Implementation
- *  Abs argument
- */
-        vandps    _sSign+__svml_ssinh_data_internal(%rip), %ymm2, %ymm1
-        vxorps    %ymm2, %ymm1, %ymm0
-
-/*
- *  Load argument
- * dM = x/log(2) + RShifter
- */
-        vfmadd213ps %ymm4, %ymm0, %ymm7
-
-/*
- *  R
- * sN = sM - RShifter
- */
-        vsubps    %ymm4, %ymm7, %ymm6
-
-/*
- *  G1,G2 2^N,2^(-N)
- * iM now is an EXP(2^N)
- */
-        vpslld    $23, %ymm7, %ymm9
-
-/*
- * Check for overflow\underflow
- * MORE faster than GE?
- */
-        vpcmpgtd  _iDomainRange+__svml_ssinh_data_internal(%rip), %ymm0, %ymm3
-
-/* sR = sX - sN*Log2_hi */
-        vfnmadd231ps %ymm5, %ymm6, %ymm0
-        vpaddd    %ymm9, %ymm8, %ymm10
-        vpsubd    %ymm9, %ymm8, %ymm11
-
-/* sR = (sX - sN*Log2_hi) - sN*Log2_lo */
-        vfnmadd231ps _sLn2lo+__svml_ssinh_data_internal(%rip), %ymm6, %ymm0
-
-/* sR2 = sR^2 */
-        vmulps    %ymm0, %ymm0, %ymm13
-        vfmadd213ps _sPC4+__svml_ssinh_data_internal(%rip), %ymm13, %ymm14
-        vfmadd213ps _sPC3+__svml_ssinh_data_internal(%rip), %ymm13, %ymm12
-
-/* sOut = a2+sR2*(a4+a6*sR2) */
-        vfmadd213ps _sPC2+__svml_ssinh_data_internal(%rip), %ymm13, %ymm14
-
-/* sSinh_r = r^2*(a3+r^2*a5) */
-        vmulps    %ymm12, %ymm13, %ymm12
-
-/* sOut = sR2*(a2+sR2*(a4+a6*sR2) */
-        vmulps    %ymm14, %ymm13, %ymm15
-
-/* sSinh_r = r + r*(r^2*(a3+r^2*a5)) */
-        vfmadd213ps %ymm0, %ymm0, %ymm12
-        vmovmskps %ymm3, %edx
-
-/* sG1 = 2^(N-1)+2^(-N-1) */
-        vaddps    %ymm11, %ymm10, %ymm3
-
-/* sG2 = 2^(N-1)-2^(-N-1) */
-        vsubps    %ymm11, %ymm10, %ymm10
-
-/* sOut = sG2*sR2*(a2+sR2*(a4+a6*sR2) */
-        vmulps    %ymm15, %ymm10, %ymm0
-
-/* sOut = sG1*sinh(dR)+sG2*sR2*(a2+sR2*(a4+a6*sR2) */
-        vfmadd213ps %ymm0, %ymm12, %ymm3
-
-/* sOut = sG2 + sG1*sinh(dR) + sG2*sR2*(a2+sR2*(a4+a6*sR2) */
-        vaddps    %ymm3, %ymm10, %ymm4
-
-/*  Ret H  */
-        vorps     %ymm4, %ymm1, %ymm0
-        testl     %edx, %edx
-
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 edx ymm0 ymm2
-
-/* Restore registers
- * and exit the function
- */
+	pushq	%rbp
+	cfi_def_cfa_offset(16)
+	movq	%rsp, %rbp
+	cfi_def_cfa(6, 16)
+	cfi_offset(6, -16)
+	andq	$-32, %rsp
+	subq	$96, %rsp
+	vmovups	_sInvLn2+__svml_ssinh_data_internal(%rip), %ymm7
+	vmovups	_sShifter+__svml_ssinh_data_internal(%rip), %ymm4
+	vmovups	_sLn2hi+__svml_ssinh_data_internal(%rip), %ymm5
+
+	/*
+	 * sinh(X) = sG2 + sG1*sinh(dR) + sG2*sR2*(a2+sR2*(a4+a6*sR2)
+	 * sOut = (a4 +a6*sR2)
+	 */
+	vmovups	_sPC6+__svml_ssinh_data_internal(%rip), %ymm14
+
+	/*
+	 * sinh(r) = r*((a1=1)+r^2*(a3+r^2*(a5+{v1 r^2*a7})))) = r + r*(r^2*(a3+r^2*(a5+r^2*a7))) ....
+	 * sSinh_r = (a3+r^2*a5)
+	 */
+	vmovups	_sPC5+__svml_ssinh_data_internal(%rip), %ymm12
+	vmovups	_iHalf+__svml_ssinh_data_internal(%rip), %ymm8
+	vmovaps	%ymm0, %ymm2
+
+	/*
+	 *  Implementation
+	 *  Abs argument
+	 */
+	vandps	_sSign+__svml_ssinh_data_internal(%rip), %ymm2, %ymm1
+	vxorps	%ymm2, %ymm1, %ymm0
+
+	/*
+	 *  Load argument
+	 * dM = x/log(2) + RShifter
+	 */
+	vfmadd213ps %ymm4, %ymm0, %ymm7
+
+	/*
+	 *  R
+	 * sN = sM - RShifter
+	 */
+	vsubps	%ymm4, %ymm7, %ymm6
+
+	/*
+	 *  G1, G2 2^N, 2^(-N)
+	 * iM now is an EXP(2^N)
+	 */
+	vpslld	$23, %ymm7, %ymm9
+
+	/*
+	 * Check for overflow\underflow
+	 * MORE faster than GE?
+	 */
+	vpcmpgtd _iDomainRange+__svml_ssinh_data_internal(%rip), %ymm0, %ymm3
+
+	/* sR = sX - sN*Log2_hi */
+	vfnmadd231ps %ymm5, %ymm6, %ymm0
+	vpaddd	%ymm9, %ymm8, %ymm10
+	vpsubd	%ymm9, %ymm8, %ymm11
+
+	/* sR = (sX - sN*Log2_hi) - sN*Log2_lo */
+	vfnmadd231ps _sLn2lo+__svml_ssinh_data_internal(%rip), %ymm6, %ymm0
+
+	/* sR2 = sR^2 */
+	vmulps	%ymm0, %ymm0, %ymm13
+	vfmadd213ps _sPC4+__svml_ssinh_data_internal(%rip), %ymm13, %ymm14
+	vfmadd213ps _sPC3+__svml_ssinh_data_internal(%rip), %ymm13, %ymm12
+
+	/* sOut = a2+sR2*(a4+a6*sR2) */
+	vfmadd213ps _sPC2+__svml_ssinh_data_internal(%rip), %ymm13, %ymm14
+
+	/* sSinh_r = r^2*(a3+r^2*a5) */
+	vmulps	%ymm12, %ymm13, %ymm12
+
+	/* sOut = sR2*(a2+sR2*(a4+a6*sR2) */
+	vmulps	%ymm14, %ymm13, %ymm15
+
+	/* sSinh_r = r + r*(r^2*(a3+r^2*a5)) */
+	vfmadd213ps %ymm0, %ymm0, %ymm12
+	vmovmskps %ymm3, %edx
+
+	/* sG1 = 2^(N-1)+2^(-N-1) */
+	vaddps	%ymm11, %ymm10, %ymm3
+
+	/* sG2 = 2^(N-1)-2^(-N-1) */
+	vsubps	%ymm11, %ymm10, %ymm10
+
+	/* sOut = sG2*sR2*(a2+sR2*(a4+a6*sR2) */
+	vmulps	%ymm15, %ymm10, %ymm0
+
+	/* sOut = sG1*sinh(dR)+sG2*sR2*(a2+sR2*(a4+a6*sR2) */
+	vfmadd213ps %ymm0, %ymm12, %ymm3
+
+	/* sOut = sG2 + sG1*sinh(dR) + sG2*sR2*(a2+sR2*(a4+a6*sR2) */
+	vaddps	%ymm3, %ymm10, %ymm4
+
+	/*  Ret H  */
+	vorps	%ymm4, %ymm1, %ymm0
+	testl	%edx, %edx
+
+	/* Go to special inputs processing branch */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	# LOE rbx r12 r13 r14 r15 edx ymm0 ymm2
+
+	/* Restore registers
+	 * and exit the function
+	 */
 
 L(EXIT):
-        movq      %rbp, %rsp
-        popq      %rbp
-        cfi_def_cfa(7, 8)
-        cfi_restore(6)
-        ret
-        cfi_def_cfa(6, 16)
-        cfi_offset(6, -16)
-
-/* Branch to process
- * special inputs
- */
+	movq	%rbp, %rsp
+	popq	%rbp
+	cfi_def_cfa(7, 8)
+	cfi_restore(6)
+	ret
+	cfi_def_cfa(6, 16)
+	cfi_offset(6, -16)
+
+	/* Branch to process
+	 * special inputs
+	 */
 
 L(SPECIAL_VALUES_BRANCH):
-        vmovups   %ymm2, 32(%rsp)
-        vmovups   %ymm0, 64(%rsp)
-                                # LOE rbx r12 r13 r14 r15 edx ymm0
-
-        xorl      %eax, %eax
-                                # LOE rbx r12 r13 r14 r15 eax edx
-
-        vzeroupper
-        movq      %r12, 16(%rsp)
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
-        movl      %eax, %r12d
-        movq      %r13, 8(%rsp)
-        /*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
-        movl      %edx, %r13d
-        movq      %r14, (%rsp)
-        /*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r15 r12d r13d
-
-/* Range mask
- * bits check
- */
+	vmovups	%ymm2, 32(%rsp)
+	vmovups	%ymm0, 64(%rsp)
+	# LOE rbx r12 r13 r14 r15 edx ymm0
+
+	xorl	%eax, %eax
+	# LOE rbx r12 r13 r14 r15 eax edx
+
+	vzeroupper
+	movq	%r12, 16(%rsp)
+	/*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
+	movl	%eax, %r12d
+	movq	%r13, 8(%rsp)
+	/*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
+	movl	%edx, %r13d
+	movq	%r14, (%rsp)
+	/*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r15 r12d r13d
+
+	/* Range mask
+	 * bits check
+	 */
 
 L(RANGEMASK_CHECK):
-        btl       %r12d, %r13d
+	btl	%r12d, %r13d
 
-/* Call scalar math function */
-        jc        L(SCALAR_MATH_CALL)
-                                # LOE rbx r15 r12d r13d
+	/* Call scalar math function */
+	jc	L(SCALAR_MATH_CALL)
+	# LOE rbx r15 r12d r13d
 
-/* Special inputs
- * processing loop
- */
+	/* Special inputs
+	 * processing loop
+	 */
 
 L(SPECIAL_VALUES_LOOP):
-        incl      %r12d
-        cmpl      $8, %r12d
-
-/* Check bits in range mask */
-        jl        L(RANGEMASK_CHECK)
-                                # LOE rbx r15 r12d r13d
-
-        movq      16(%rsp), %r12
-        cfi_restore(12)
-        movq      8(%rsp), %r13
-        cfi_restore(13)
-        movq      (%rsp), %r14
-        cfi_restore(14)
-        vmovups   64(%rsp), %ymm0
-
-/* Go to exit */
-        jmp       L(EXIT)
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
-        /*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
-        /*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r12 r13 r14 r15 ymm0
-
-/* Scalar math fucntion call
- * to process special input
- */
+	incl	%r12d
+	cmpl	$8, %r12d
+
+	/* Check bits in range mask */
+	jl	L(RANGEMASK_CHECK)
+	# LOE rbx r15 r12d r13d
+
+	movq	16(%rsp), %r12
+	cfi_restore(12)
+	movq	8(%rsp), %r13
+	cfi_restore(13)
+	movq	(%rsp), %r14
+	cfi_restore(14)
+	vmovups	64(%rsp), %ymm0
+
+	/* Go to exit */
+	jmp	L(EXIT)
+	/*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
+	/*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
+	/*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r12 r13 r14 r15 ymm0
+
+	/* Scalar math fucntion call
+	 * to process special input
+	 */
 
 L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movss     32(%rsp,%r14,4), %xmm0
-        call      sinhf@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
+	movl	%r12d, %r14d
+	movss	32(%rsp, %r14, 4), %xmm0
+	call	sinhf@PLT
+	# LOE rbx r14 r15 r12d r13d xmm0
 
-        movss     %xmm0, 64(%rsp,%r14,4)
+	movss	%xmm0, 64(%rsp, %r14, 4)
 
-/* Process special inputs in loop */
-        jmp       L(SPECIAL_VALUES_LOOP)
-                                # LOE rbx r15 r12d r13d
+	/* Process special inputs in loop */
+	jmp	L(SPECIAL_VALUES_LOOP)
+	# LOE rbx r15 r12d r13d
 END(_ZGVdN8v_sinhf_avx2)
 
-        .section .rodata, "a"
-        .align 32
+	.section .rodata, "a"
+	.align	32
 
 #ifdef __svml_ssinh_data_internal_typedef
 typedef unsigned int VUINT32;
-typedef struct
-{
-        __declspec(align(32)) VUINT32 _sInvLn2[8][1];
-        __declspec(align(32)) VUINT32 _sLn2hi[8][1];
-        __declspec(align(32)) VUINT32 _sLn2lo[8][1];
-        __declspec(align(32)) VUINT32 _sSign[8][1];
-        __declspec(align(32)) VUINT32 _sShifter[8][1];
-        __declspec(align(32)) VUINT32 _iDomainRange[8][1];
-        __declspec(align(32)) VUINT32 _sPC1[8][1];
-        __declspec(align(32)) VUINT32 _sPC2[8][1];
-        __declspec(align(32)) VUINT32 _sPC3[8][1];
-        __declspec(align(32)) VUINT32 _sPC4[8][1];
-        __declspec(align(32)) VUINT32 _sPC5[8][1];
-        __declspec(align(32)) VUINT32 _sPC6[8][1];
-        __declspec(align(32)) VUINT32 _iHalf[8][1];
+typedef struct {
+	__declspec(align(32)) VUINT32 _sInvLn2[8][1];
+	__declspec(align(32)) VUINT32 _sLn2hi[8][1];
+	__declspec(align(32)) VUINT32 _sLn2lo[8][1];
+	__declspec(align(32)) VUINT32 _sSign[8][1];
+	__declspec(align(32)) VUINT32 _sShifter[8][1];
+	__declspec(align(32)) VUINT32 _iDomainRange[8][1];
+	__declspec(align(32)) VUINT32 _sPC1[8][1];
+	__declspec(align(32)) VUINT32 _sPC2[8][1];
+	__declspec(align(32)) VUINT32 _sPC3[8][1];
+	__declspec(align(32)) VUINT32 _sPC4[8][1];
+	__declspec(align(32)) VUINT32 _sPC5[8][1];
+	__declspec(align(32)) VUINT32 _sPC6[8][1];
+	__declspec(align(32)) VUINT32 _iHalf[8][1];
 } __svml_ssinh_data_internal;
 #endif
 __svml_ssinh_data_internal:
-        .long 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B           /* _sInvLn2  */  //k=0
-        .align 32
-        .long 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000           /* _sLn2hi   */
-        .align 32
-        .long 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4           /* _sLn2lo   */
-        .align 32
-        .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000           /* _sSign    */
-        .align 32
-        .long 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000           /* _sShifter */
-        .align 32
-        .long 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E           /* _iDomainRange */
-        .align 32
-        .long 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000         /* _sPC1=1  */
-        .align 32
-        .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000         /* _sPC2  */
-        .align 32
-        .long 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57         /* _sPC3  */
-        .align 32
-        .long 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72         /* _sPC4  */
-        .align 32
-        .long 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461         /* _sPC5  */
-        .align 32
-        .long 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3         /* _sPC6  */
-        // Integer constants
-        .align 32
-        .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 /* _iHalf*/
-        .align 32
-        .type	__svml_ssinh_data_internal,@object
-        .size	__svml_ssinh_data_internal,.-__svml_ssinh_data_internal
+	.long	0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B /* _sInvLn2 */ // k=0
+	.align	32
+	.long	0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000 /* _sLn2hi */
+	.align	32
+	.long	0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4 /* _sLn2lo */
+	.align	32
+	.long	0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000 /* _sSign */
+	.align	32
+	.long	0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000 /* _sShifter */
+	.align	32
+	.long	0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E /* _iDomainRange */
+	.align	32
+	.long	0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000 /* _sPC1=1 */
+	.align	32
+	.long	0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 /* _sPC2 */
+	.align	32
+	.long	0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57 /* _sPC3 */
+	.align	32
+	.long	0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72 /* _sPC4 */
+	.align	32
+	.long	0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461 /* _sPC5 */
+	.align	32
+	.long	0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3 /* _sPC6 */
+	// Integer constants
+	.align	32
+	.long	0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 /* _iHalf */
+	.align	32
+	.type	__svml_ssinh_data_internal, @object
+	.size	__svml_ssinh_data_internal, .-__svml_ssinh_data_internal