Checking patch sysdeps/x86_64/fpu/multiarch/svml_s_atanhf4_core_sse4.S...
error: while searching for:
	testl	%edx, %edx
	/* Go to special inputs processing branch.  */
	jne	L(SPECIAL_VALUES_BRANCH)
	# LOE rbx rbp r12 r13 r14 r15 xmm0
	/* No registers to restore on fast path.  */
	ret


	/* Cold case. edx has 1s where there was a special value that
	   needs to be handled by a atanhf call. Optimize for code size
	   more so than speed here. */
L(SPECIAL_VALUES_BRANCH):
	# LOE rbx rdx rbp r12 r13 r14 r15 xmm0 xmm5
	/* Stack coming in 16-byte aligned. Set 8-byte misaligned so on
       call entry will be 16-byte aligned. */
	subq	$56, %rsp
	cfi_def_cfa_offset(64)
	movups	%xmm0, 24(%rsp)
	movups	%xmm5, 40(%rsp)

	/* Use rbx/rbp for callee save registers as they get short
       encoding for many instructions (as compared with r12/r13). */
	movq	%rbx, (%rsp)
	cfi_offset(rbx, -64)
	movq	%rbp, 8(%rsp)
	cfi_offset(rbp, -56)
	/* edx has 1s where there was a special value that needs to be handled
	   by a tanhf call.  */
	movl	%edx, %ebx
L(SPECIAL_VALUES_LOOP):
	# LOE rbx rbp r12 r13 r14 r15
	/* use rbp 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	%ebp, %ebp
	bsfl	%ebx, %ebp

	/* Scalar math fucntion call to process special input.  */
	movss	40(%rsp, %rbp, 4), %xmm0
	call	atanhf@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, 24(%rsp, %rbp, 4)

	leal	-1(%rbx), %eax
	andl	%eax, %ebx
	jnz	L(SPECIAL_VALUES_LOOP)
	# LOE r12 r13 r14 r15
	/* All results have been written to 24(%rsp).  */
	movups	24(%rsp), %xmm0
	movq	(%rsp), %rbx
	cfi_restore(rbx)
	movq	8(%rsp), %rbp
	cfi_restore(rbp)
	addq	$56, %rsp
	cfi_def_cfa_offset(8)
	ret
END(_ZGVbN4v_atanhf_sse4)

	.section .rodata, "a"
	.align	16

#ifdef __svml_satanh_data_internal_typedef
typedef unsigned int VUINT32;
typedef struct{
	__declspec(align(16)) VUINT32 sOne[4][1];
	__declspec(align(16)) VUINT32 SgnMask[4][1];
	__declspec(align(16)) VUINT32 sTopMask12[4][1];
	__declspec(align(16)) VUINT32 iBrkValue[4][1];
	__declspec(align(16)) VUINT32 iOffExpoMask[4][1];
	__declspec(align(16)) VUINT32 sPoly[8][4][1];
	__declspec(align(16)) VUINT32 sLn2[4][1];
	__declspec(align(16)) VUINT32 TinyRange[4][1];
} __svml_satanh_data_internal;
#endif

__svml_satanh_data_internal:
	/* sOne = SP 1.0 */
	.align	16
	.long	0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
	/* SgnMask */
	.long	0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
	/* sTopMask12 */
	.align	16
	.long	0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000
	/* iBrkValue = SP 2/3 */
	.align	16
	.long	0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab
	/* iOffExpoMask = SP significand mask ==*/
	.align	16
	.long	0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff

	/* sPoly[] = SP polynomial */
	.align	16
	.long	0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed /* 1.3820238411426544189453125e-01 P7 */
	.long	0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3 /* -1.5122179687023162841796875e-01 P6 */
	.long	0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12 /* 1.4042308926582336425781250e-01 P5 */
	.long	0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37 /* -1.6472326219081878662109375e-01 P4 */
	.long	0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190 /* 2.0007920265197753906250000e-01 P3 */
	.long	0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e /* -2.5004237890243530273437500e-01 P2 */
	.long	0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94 /* 3.3333265781402587890625000e-01 P1 */
	.long	0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 /* -5.0000000000000000000000000e-01 P0 */

	/* sLn2 = SP ln(2) */
	.align	16
	.long	0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218
	/* TinyRange */
	.align	16
	.long	0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000
	.align	16
	.type	__svml_satanh_data_internal, @object
	.size	__svml_satanh_data_internal, .-__svm
error: patch failed: sysdeps/x86_64/fpu/multiarch/svml_s_atanhf4_core_sse4.S:206
error: sysdeps/x86_64/fpu/multiarch/svml_s_atanhf4_core_sse4.S: patch does not apply