x86_64: Fix svml_s_tanf16_core_avx512.S code formatting

This commit contains following formatting changes

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

Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>

1 files changed, 815 insertions, 818 deletions

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_tanf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_tanf16_core_avx512.S
index fc44c37d4a..f2a18f0b2c 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_tanf16_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_tanf16_core_avx512.S
@@ -34,894 +34,891 @@
 
 /* Offsets for data table __svml_stan_data_internal
  */
-#define _sInvPI_uisa                  	0
-#define _sPI1_uisa                    	64
-#define _sPI2_uisa                    	128
-#define _sPI3_uisa                    	192
-#define Th_tbl_uisa                   	256
-#define _sPC3_uisa                    	384
-#define _sPC5_uisa                    	448
-#define _sRangeReductionVal_uisa      	512
-#define _sAbsMask                     	576
-#define _sRangeVal                    	640
-#define _sRShifter                    	704
-#define _sOne                         	768
-#define _sRangeReductionVal           	832
-#define _sPI1                         	896
-#define _sPI2                         	960
-#define _sPI3                         	1024
+#define _sInvPI_uisa			0
+#define _sPI1_uisa			64
+#define _sPI2_uisa			128
+#define _sPI3_uisa			192
+#define Th_tbl_uisa			256
+#define _sPC3_uisa			384
+#define _sPC5_uisa			448
+#define _sRangeReductionVal_uisa	512
+#define _sAbsMask			576
+#define _sRangeVal			640
+#define _sRShifter			704
+#define _sOne				768
+#define _sRangeReductionVal		832
+#define _sPI1				896
+#define _sPI2				960
+#define _sPI3				1024
 
 #include <sysdep.h>
 
-        .text
-	.section .text.exex512,"ax",@progbits
+	.section .text.exex512, "ax", @progbits
 ENTRY(_ZGVeN16v_tanf_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
-        xorl      %edx, %edx
-
-/* Large values check */
-        vmovups   _sRangeReductionVal_uisa+__svml_stan_data_internal(%rip), %zmm10
-
-/*
- *
- * Main path
- *
- * start arg. reduction
- */
-        vmovups   _sRShifter+__svml_stan_data_internal(%rip), %zmm1
-        vmovups   _sPI1_uisa+__svml_stan_data_internal(%rip), %zmm4
-        vmovups   _sPI2_uisa+__svml_stan_data_internal(%rip), %zmm2
-        vmovups   _sPI3_uisa+__svml_stan_data_internal(%rip), %zmm3
-        vmovaps   %zmm0, %zmm11
-        vandps    _sAbsMask+__svml_stan_data_internal(%rip), %zmm11, %zmm0
-        vcmpps    $22, {sae}, %zmm10, %zmm0, %k6
-        vmovups   __svml_stan_data_internal(%rip), %zmm10
-
-/*
- *
- * End of main path
- */
-
-        kortestw  %k6, %k6
-        vfmadd213ps {rn-sae}, %zmm1, %zmm11, %zmm10
-        vsubps    {rn-sae}, %zmm1, %zmm10, %zmm5
-        vfnmadd213ps {rn-sae}, %zmm11, %zmm5, %zmm4
-        vfnmadd231ps {rn-sae}, %zmm5, %zmm2, %zmm4
-        vfnmadd213ps {rn-sae}, %zmm4, %zmm3, %zmm5
-
-/* Go to auxilary branch */
-        jne       L(AUX_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 edx zmm0 zmm5 zmm10 zmm11 k6
-
-/* Return from auxilary branch
- * for out of main path inputs
- */
+	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
+	xorl	%edx, %edx
+
+	/* Large values check */
+	vmovups	_sRangeReductionVal_uisa+__svml_stan_data_internal(%rip), %zmm10
+
+	/*
+	 *
+	 * Main path
+	 *
+	 * start arg. reduction
+	 */
+	vmovups	_sRShifter+__svml_stan_data_internal(%rip), %zmm1
+	vmovups	_sPI1_uisa+__svml_stan_data_internal(%rip), %zmm4
+	vmovups	_sPI2_uisa+__svml_stan_data_internal(%rip), %zmm2
+	vmovups	_sPI3_uisa+__svml_stan_data_internal(%rip), %zmm3
+	vmovaps	%zmm0, %zmm11
+	vandps	_sAbsMask+__svml_stan_data_internal(%rip), %zmm11, %zmm0
+	vcmpps	$22, {sae}, %zmm10, %zmm0, %k6
+	vmovups	__svml_stan_data_internal(%rip), %zmm10
+
+	/*
+	 *
+	 * End of main path
+	 */
+
+	kortestw %k6, %k6
+	vfmadd213ps {rn-sae}, %zmm1, %zmm11, %zmm10
+	vsubps	{rn-sae}, %zmm1, %zmm10, %zmm5
+	vfnmadd213ps {rn-sae}, %zmm11, %zmm5, %zmm4
+	vfnmadd231ps {rn-sae}, %zmm5, %zmm2, %zmm4
+	vfnmadd213ps {rn-sae}, %zmm4, %zmm3, %zmm5
+
+	/* Go to auxilary branch */
+	jne	L(AUX_BRANCH)
+	# LOE rbx r12 r13 r14 r15 edx zmm0 zmm5 zmm10 zmm11 k6
+
+	/* Return from auxilary branch
+	 * for out of main path inputs
+	 */
 
 L(AUX_BRANCH_RETURN):
-/* Table lookup */
-        vmovups   Th_tbl_uisa+__svml_stan_data_internal(%rip), %zmm3
-        vmovups   _sPC3_uisa+__svml_stan_data_internal(%rip), %zmm0
-        vmulps    {rn-sae}, %zmm5, %zmm5, %zmm1
-        vpermt2ps Th_tbl_uisa+64+__svml_stan_data_internal(%rip), %zmm10, %zmm3
-        vmovups   _sPC5_uisa+__svml_stan_data_internal(%rip), %zmm10
-        vfmadd231ps {rn-sae}, %zmm1, %zmm10, %zmm0
-        vmulps    {rn-sae}, %zmm5, %zmm0, %zmm4
-        vfmadd213ps {rn-sae}, %zmm5, %zmm1, %zmm4
-
-/*
- * Computer Denominator:
- * sDenominator - sDlow ~= 1-(sTh+sTl)*(sP+sPlow)
- */
-        vmovups   _sOne+__svml_stan_data_internal(%rip), %zmm5
-        vmulps    {rn-sae}, %zmm4, %zmm3, %zmm7
-
-/*
- * Compute Numerator:
- * sNumerator + sNlow ~= sTh+sTl+sP+sPlow
- */
-        vaddps    {rn-sae}, %zmm3, %zmm4, %zmm8
-        vsubps    {rn-sae}, %zmm7, %zmm5, %zmm9
-        vsubps    {rn-sae}, %zmm3, %zmm8, %zmm2
-
-/*
- * Now computes (sNumerator + sNlow)/(sDenominator - sDlow)
- * Choose NR iteration instead of hardware division
- */
-        vrcp14ps  %zmm9, %zmm14
-        vsubps    {rn-sae}, %zmm5, %zmm9, %zmm6
-        vsubps    {rn-sae}, %zmm2, %zmm4, %zmm13
-        vmulps    {rn-sae}, %zmm8, %zmm14, %zmm15
-        vaddps    {rn-sae}, %zmm7, %zmm6, %zmm12
-
-/* One NR iteration to refine sQuotient */
-        vfmsub213ps {rn-sae}, %zmm8, %zmm15, %zmm9
-        vfnmadd213ps {rn-sae}, %zmm9, %zmm15, %zmm12
-        vsubps    {rn-sae}, %zmm13, %zmm12, %zmm0
-        vfnmadd213ps {rn-sae}, %zmm15, %zmm14, %zmm0
-        testl     %edx, %edx
-
-/* Go to special inputs processing branch */
-        jne       L(SPECIAL_VALUES_BRANCH)
-                                # LOE rbx r12 r13 r14 r15 edx zmm0 zmm11
-
-/* Restore registers
- * and exit the function
- */
+	/* Table lookup */
+	vmovups	Th_tbl_uisa+__svml_stan_data_internal(%rip), %zmm3
+	vmovups	_sPC3_uisa+__svml_stan_data_internal(%rip), %zmm0
+	vmulps	{rn-sae}, %zmm5, %zmm5, %zmm1
+	vpermt2ps Th_tbl_uisa+64+__svml_stan_data_internal(%rip), %zmm10, %zmm3
+	vmovups	_sPC5_uisa+__svml_stan_data_internal(%rip), %zmm10
+	vfmadd231ps {rn-sae}, %zmm1, %zmm10, %zmm0
+	vmulps	{rn-sae}, %zmm5, %zmm0, %zmm4
+	vfmadd213ps {rn-sae}, %zmm5, %zmm1, %zmm4
+
+	/*
+	 * Computer Denominator:
+	 * sDenominator - sDlow ~= 1-(sTh+sTl)*(sP+sPlow)
+	 */
+	vmovups	_sOne+__svml_stan_data_internal(%rip), %zmm5
+	vmulps	{rn-sae}, %zmm4, %zmm3, %zmm7
+
+	/*
+	 * Compute Numerator:
+	 * sNumerator + sNlow ~= sTh+sTl+sP+sPlow
+	 */
+	vaddps	{rn-sae}, %zmm3, %zmm4, %zmm8
+	vsubps	{rn-sae}, %zmm7, %zmm5, %zmm9
+	vsubps	{rn-sae}, %zmm3, %zmm8, %zmm2
+
+	/*
+	 * Now computes (sNumerator + sNlow)/(sDenominator - sDlow)
+	 * Choose NR iteration instead of hardware division
+	 */
+	vrcp14ps %zmm9, %zmm14
+	vsubps	{rn-sae}, %zmm5, %zmm9, %zmm6
+	vsubps	{rn-sae}, %zmm2, %zmm4, %zmm13
+	vmulps	{rn-sae}, %zmm8, %zmm14, %zmm15
+	vaddps	{rn-sae}, %zmm7, %zmm6, %zmm12
+
+	/* One NR iteration to refine sQuotient */
+	vfmsub213ps {rn-sae}, %zmm8, %zmm15, %zmm9
+	vfnmadd213ps {rn-sae}, %zmm9, %zmm15, %zmm12
+	vsubps	{rn-sae}, %zmm13, %zmm12, %zmm0
+	vfnmadd213ps {rn-sae}, %zmm15, %zmm14, %zmm0
+	testl	%edx, %edx
+
+	/* Go to special inputs processing branch */
+	jne	L(SPECIAL_VALUES_BRANCH)
+	# LOE rbx r12 r13 r14 r15 edx zmm0 zmm11
+
+	/* 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   %zmm11, 64(%rsp)
-        vmovups   %zmm0, 128(%rsp)
-                                # LOE rbx r12 r13 r14 r15 edx zmm0
-
-        xorl      %eax, %eax
-                                # LOE rbx r12 r13 r14 r15 eax edx
-
-        vzeroupper
-        movq      %r12, 16(%rsp)
-        /*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
-        movl      %eax, %r12d
-        movq      %r13, 8(%rsp)
-        /*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
-        movl      %edx, %r13d
-        movq      %r14, (%rsp)
-        /*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
-        .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
-                                # LOE rbx r15 r12d r13d
-
-/* Range mask
- * bits check
- */
+	vmovups	%zmm11, 64(%rsp)
+	vmovups	%zmm0, 128(%rsp)
+	# LOE rbx r12 r13 r14 r15 edx zmm0
+
+	xorl	%eax, %eax
+	# LOE rbx r12 r13 r14 r15 eax edx
+
+	vzeroupper
+	movq	%r12, 16(%rsp)
+	/*  DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
+	movl	%eax, %r12d
+	movq	%r13, 8(%rsp)
+	/*  DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
+	movl	%edx, %r13d
+	movq	%r14, (%rsp)
+	/*  DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus)  */
+	.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
+	# LOE rbx r15 r12d r13d
+
+	/* Range mask
+	 * bits check
+	 */
 
 L(RANGEMASK_CHECK):
-        btl       %r12d, %r13d
+	btl	%r12d, %r13d
 
-/* Call scalar math function */
-        jc        L(SCALAR_MATH_CALL)
-                                # LOE rbx r15 r12d r13d
+	/* Call scalar math function */
+	jc	L(SCALAR_MATH_CALL)
+	# LOE rbx r15 r12d r13d
 
-/* Special inputs
- * processing loop
- */
+	/* Special inputs
+	 * processing loop
+	 */
 
 L(SPECIAL_VALUES_LOOP):
-        incl      %r12d
-        cmpl      $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
- */
+	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
+	 */
 
 L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movss     64(%rsp,%r14,4), %xmm0
-        call      tanf@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
-
-        movss     %xmm0, 128(%rsp,%r14,4)
-
-/* Process special inputs in loop */
-        jmp       L(SPECIAL_VALUES_LOOP)
-        cfi_restore(12)
-        cfi_restore(13)
-        cfi_restore(14)
-                                # LOE rbx r15 r12d r13d
-
-/* Auxilary branch
- * for out of main path inputs
- */
+	movl	%r12d, %r14d
+	movss	64(%rsp, %r14, 4), %xmm0
+	call	tanf@PLT
+	# LOE rbx r14 r15 r12d r13d xmm0
 
-L(AUX_BRANCH):
-        vmovups   _sRangeVal+__svml_stan_data_internal(%rip), %zmm6
+	movss	%xmm0, 128(%rsp, %r14, 4)
 
-/*
- * Get the (2^a / 2pi) mod 1 values from the table.
- * Because doesn't have I-type gather, we need a trivial cast
- */
-        lea       __svml_stan_reduction_data_internal(%rip), %rax
-        vmovups   %zmm5, (%rsp)
-        vandps    %zmm0, %zmm6, %zmm14
-        vcmpps    $0, {sae}, %zmm6, %zmm14, %k0
+	/* Process special inputs in loop */
+	jmp	L(SPECIAL_VALUES_LOOP)
+	cfi_restore(12)
+	cfi_restore(13)
+	cfi_restore(14)
+	# LOE rbx r15 r12d r13d
 
-/*
- * Break the P_xxx and m into 16-bit chunks ready for
- * the long multiplication via 16x16->32 multiplications
- */
-        vmovups   .FLT_15(%rip), %zmm6
-        kxnorw    %k0, %k0, %k1
-        kxnorw    %k0, %k0, %k2
-        kxnorw    %k0, %k0, %k3
-        kmovw     %k0, %edx
-        vpandd    .FLT_12(%rip), %zmm11, %zmm5
-        vpsrld    $23, %zmm5, %zmm7
-        vpslld    $1, %zmm7, %zmm8
-        vpaddd    %zmm7, %zmm8, %zmm9
-        vpslld    $2, %zmm9, %zmm4
-        vpxord    %zmm3, %zmm3, %zmm3
-        vpxord    %zmm15, %zmm15, %zmm15
-        vpxord    %zmm2, %zmm2, %zmm2
-        vgatherdps (%rax,%zmm4), %zmm3{%k1}
-        vgatherdps 4(%rax,%zmm4), %zmm15{%k2}
-        vgatherdps 8(%rax,%zmm4), %zmm2{%k3}
-        vpsrld    $16, %zmm3, %zmm5
-        vpsrld    $16, %zmm2, %zmm13
-
-/*
- * Also get the significand as an integer
- * NB: adding in the integer bit is wrong for denorms!
- * To make this work for denorms we should do something slightly different
- */
-        vpandd    .FLT_13(%rip), %zmm11, %zmm0
-        vpaddd    .FLT_14(%rip), %zmm0, %zmm1
-        vpsrld    $16, %zmm15, %zmm0
-        vpsrld    $16, %zmm1, %zmm8
-        vpandd    %zmm6, %zmm3, %zmm9
-        vpandd    %zmm6, %zmm15, %zmm12
-        vpandd    %zmm6, %zmm2, %zmm7
-        vpandd    %zmm6, %zmm1, %zmm14
-
-/* Now do the big multiplication and carry propagation */
-        vpmulld   %zmm9, %zmm8, %zmm4
-        vpmulld   %zmm0, %zmm8, %zmm3
-        vpmulld   %zmm12, %zmm8, %zmm2
-        vpmulld   %zmm13, %zmm8, %zmm1
-        vpmulld   %zmm7, %zmm8, %zmm8
-        vpmulld   %zmm5, %zmm14, %zmm7
-        vpmulld   %zmm9, %zmm14, %zmm5
-        vpmulld   %zmm0, %zmm14, %zmm9
-        vpmulld   %zmm12, %zmm14, %zmm0
-        vpmulld   %zmm13, %zmm14, %zmm12
-        vpsrld    $16, %zmm12, %zmm14
-        vpsrld    $16, %zmm0, %zmm13
-        vpsrld    $16, %zmm9, %zmm15
-        vpsrld    $16, %zmm5, %zmm12
-        vpsrld    $16, %zmm8, %zmm8
-        vpaddd    %zmm14, %zmm1, %zmm1
-        vpaddd    %zmm13, %zmm2, %zmm2
-        vpaddd    %zmm15, %zmm3, %zmm15
-        vpaddd    %zmm12, %zmm4, %zmm3
-        vpandd    %zmm6, %zmm0, %zmm13
-        vpaddd    %zmm1, %zmm13, %zmm4
-        vpaddd    %zmm4, %zmm8, %zmm14
-        vpsrld    $16, %zmm14, %zmm0
-        vpandd    %zmm6, %zmm9, %zmm9
-        vpaddd    %zmm2, %zmm9, %zmm1
-        vpaddd    %zmm1, %zmm0, %zmm8
-
-/*
- * Now round at the 2^-8 bit position for reduction mod pi/2^7
- * instead of the original 2pi (but still with the same 2pi scaling).
- * Use a shifter of 2^15 + 2^14.
- * The N we get is our final version; it has an offset of
- * 2^8 because of the implicit integer bit, and anyway for negative
- * starting value it's a 2s complement thing. But we need to mask
- * off the exponent part anyway so it's fine.
- */
-        vmovups   .FLT_18(%rip), %zmm1
-        vpandd    %zmm6, %zmm7, %zmm7
-        vpaddd    %zmm3, %zmm7, %zmm13
-        vpsrld    $16, %zmm8, %zmm3
-        vpandd    %zmm6, %zmm5, %zmm5
-        vpaddd    %zmm15, %zmm5, %zmm2
-        vpaddd    %zmm2, %zmm3, %zmm15
-        vpsrld    $16, %zmm15, %zmm12
-        vpaddd    %zmm13, %zmm12, %zmm5
-
-/* Assemble reduced argument from the pieces */
-        vpandd    %zmm6, %zmm14, %zmm9
-        vpandd    %zmm6, %zmm15, %zmm7
-        vpslld    $16, %zmm5, %zmm6
-        vpslld    $16, %zmm8, %zmm5
-        vpaddd    %zmm7, %zmm6, %zmm4
-        vpaddd    %zmm9, %zmm5, %zmm9
-        vpsrld    $9, %zmm4, %zmm6
-
-/*
- * We want to incorporate the original sign now too.
- * Do it here for convenience in getting the right N value,
- * though we could wait right to the end if we were prepared
- * to modify the sign of N later too.
- * So get the appropriate sign mask now (or sooner).
- */
-        vpandd    .FLT_16(%rip), %zmm11, %zmm0
-        vpandd    .FLT_21(%rip), %zmm9, %zmm13
-        vpslld    $5, %zmm13, %zmm14
-
-/*
- * Create floating-point high part, implicitly adding integer bit 1
- * Incorporate overall sign at this stage too.
- */
-        vpxord    .FLT_17(%rip), %zmm0, %zmm8
-        vpord     %zmm8, %zmm6, %zmm2
-        vaddps    {rn-sae}, %zmm2, %zmm1, %zmm12
-        vsubps    {rn-sae}, %zmm1, %zmm12, %zmm3
-        vsubps    {rn-sae}, %zmm3, %zmm2, %zmm7
-
-/*
- * Create floating-point low and medium parts, respectively
- * lo_17, ... lo_0, 0, ..., 0
- * hi_8, ... hi_0, lo_31, ..., lo_18
- * then subtract off the implicitly added integer bits,
- * 2^-46 and 2^-23, respectively.
- * Put the original sign into all of them at this stage.
- */
-        vpxord    .FLT_20(%rip), %zmm0, %zmm6
-        vpord     %zmm6, %zmm14, %zmm15
-        vpandd    .FLT_23(%rip), %zmm4, %zmm4
-        vsubps    {rn-sae}, %zmm6, %zmm15, %zmm8
-        vandps    .FLT_26(%rip), %zmm11, %zmm15
-        vpsrld    $18, %zmm9, %zmm6
+	/* Auxilary branch
+	 * for out of main path inputs
+	 */
 
-/*
- * If the magnitude of the input is <= 2^-20, then
- * just pass through the input, since no reduction will be needed and
- * the main path will only work accurately if the reduced argument is
- * about >= 2^-40 (which it is for all large pi multiples)
- */
-        vmovups   .FLT_27(%rip), %zmm14
-        vcmpps    $26, {sae}, %zmm14, %zmm15, %k4
-        vcmpps    $22, {sae}, %zmm14, %zmm15, %k5
-        vpxord    .FLT_22(%rip), %zmm0, %zmm1
-        vpslld    $14, %zmm4, %zmm0
-        vpord     %zmm6, %zmm0, %zmm0
-        vpord     %zmm1, %zmm0, %zmm4
-        vsubps    {rn-sae}, %zmm1, %zmm4, %zmm2
-        vpternlogd $255, %zmm6, %zmm6, %zmm6
-
-/* Now add them up into 2 reasonably aligned pieces */
-        vaddps    {rn-sae}, %zmm2, %zmm7, %zmm13
-        vsubps    {rn-sae}, %zmm13, %zmm7, %zmm7
-        vaddps    {rn-sae}, %zmm7, %zmm2, %zmm3
-
-/*
- * The output is _VRES_R (high) + _VRES_E (low), and the integer part is _VRES_IND
- * Set sRp2 = _VRES_R^2 and then resume the original code.
- */
-        vmovups   .FLT_28(%rip), %zmm2
-        vaddps    {rn-sae}, %zmm8, %zmm3, %zmm1
-        vmovups   .FLT_25(%rip), %zmm8
-
-/* Grab our final N value as an integer, appropriately masked mod 2^8 */
-        vpandd    .FLT_19(%rip), %zmm12, %zmm5
-
-/*
- * Now multiply those numbers all by 2 pi, reasonably accurately.
- * (RHi + RLo) * (pi_lead + pi_trail) ~=
- * RHi * pi_lead + (RHi * pi_trail + RLo * pi_lead)
- */
-        vmovups   .FLT_24(%rip), %zmm12
-        vmulps    {rn-sae}, %zmm12, %zmm13, %zmm0
-        vmovaps   %zmm12, %zmm9
-        vfmsub213ps {rn-sae}, %zmm0, %zmm13, %zmm9
-        vfmadd213ps {rn-sae}, %zmm9, %zmm8, %zmm13
-        vmovaps   %zmm6, %zmm8
-        vfmadd213ps {rn-sae}, %zmm13, %zmm12, %zmm1
-        vpandnd   %zmm15, %zmm15, %zmm8{%k4}
-        vpandnd   %zmm15, %zmm15, %zmm6{%k5}
-        vandps    %zmm11, %zmm6, %zmm14
-        vandps    %zmm0, %zmm8, %zmm15
-        vandps    %zmm1, %zmm8, %zmm12
-        vorps     %zmm15, %zmm14, %zmm6
-        vpsrld    $31, %zmm6, %zmm3
-        vpsubd    %zmm3, %zmm2, %zmm4
-        vpaddd    %zmm4, %zmm5, %zmm7
-        vpsrld    $2, %zmm7, %zmm13
-        vpslld    $2, %zmm13, %zmm9
-
-/*
- *
- * End of large arguments path
- *
- * Merge results from main and large paths:
- */
-        vblendmps %zmm13, %zmm10, %zmm10{%k6}
-        vpsubd    %zmm9, %zmm5, %zmm5
-        vmovups   .FLT_29(%rip), %zmm9
-        vcvtdq2ps {rn-sae}, %zmm5, %zmm0
-        vmovups   .FLT_30(%rip), %zmm5
-        vfmadd231ps {rn-sae}, %zmm0, %zmm5, %zmm12
-        vmovups   (%rsp), %zmm5
-        vaddps    {rn-sae}, %zmm6, %zmm12, %zmm6
-        vfmadd213ps {rn-sae}, %zmm6, %zmm9, %zmm0
-        vblendmps %zmm0, %zmm5, %zmm5{%k6}
-
-/* Return to main vector processing path */
-        jmp       L(AUX_BRANCH_RETURN)
-                                # LOE rbx r12 r13 r14 r15 edx zmm5 zmm10 zmm11
+L(AUX_BRANCH):
+	vmovups	_sRangeVal+__svml_stan_data_internal(%rip), %zmm6
+
+	/*
+	 * Get the (2^a / 2pi) mod 1 values from the table.
+	 * Because doesn't have I-type gather, we need a trivial cast
+	 */
+	lea	__svml_stan_reduction_data_internal(%rip), %rax
+	vmovups	%zmm5, (%rsp)
+	vandps	%zmm0, %zmm6, %zmm14
+	vcmpps	$0, {sae}, %zmm6, %zmm14, %k0
+
+	/*
+	 * Break the P_xxx and m into 16-bit chunks ready for
+	 * the long multiplication via 16x16->32 multiplications
+	 */
+	vmovups	.FLT_15(%rip), %zmm6
+	kxnorw	%k0, %k0, %k1
+	kxnorw	%k0, %k0, %k2
+	kxnorw	%k0, %k0, %k3
+	kmovw	%k0, %edx
+	vpandd	.FLT_12(%rip), %zmm11, %zmm5
+	vpsrld	$23, %zmm5, %zmm7
+	vpslld	$1, %zmm7, %zmm8
+	vpaddd	%zmm7, %zmm8, %zmm9
+	vpslld	$2, %zmm9, %zmm4
+	vpxord	%zmm3, %zmm3, %zmm3
+	vpxord	%zmm15, %zmm15, %zmm15
+	vpxord	%zmm2, %zmm2, %zmm2
+	vgatherdps (%rax, %zmm4), %zmm3{%k1}
+	vgatherdps 4(%rax, %zmm4), %zmm15{%k2}
+	vgatherdps 8(%rax, %zmm4), %zmm2{%k3}
+	vpsrld	$16, %zmm3, %zmm5
+	vpsrld	$16, %zmm2, %zmm13
+
+	/*
+	 * Also get the significand as an integer
+	 * NB: adding in the integer bit is wrong for denorms!
+	 * To make this work for denorms we should do something slightly different
+	 */
+	vpandd	.FLT_13(%rip), %zmm11, %zmm0
+	vpaddd	.FLT_14(%rip), %zmm0, %zmm1
+	vpsrld	$1