mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-25 22:40:05 +00:00
x86_64: Fix svml_s_atanhf4_core_sse4.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>
This commit is contained in:
parent
38986fb9bc
commit
5aa7f304d9
@ -32,330 +32,329 @@
|
|||||||
|
|
||||||
/* Offsets for data table __svml_satanh_data_internal
|
/* Offsets for data table __svml_satanh_data_internal
|
||||||
*/
|
*/
|
||||||
#define SgnMask 0
|
#define SgnMask 0
|
||||||
#define sOne 16
|
#define sOne 16
|
||||||
#define sPoly 32
|
#define sPoly 32
|
||||||
#define iBrkValue 160
|
#define iBrkValue 160
|
||||||
#define iOffExpoMask 176
|
#define iOffExpoMask 176
|
||||||
#define sHalf 192
|
#define sHalf 192
|
||||||
#define sSign 208
|
#define sSign 208
|
||||||
#define sTopMask12 224
|
#define sTopMask12 224
|
||||||
#define TinyRange 240
|
#define TinyRange 240
|
||||||
#define sLn2 256
|
#define sLn2 256
|
||||||
|
|
||||||
#include <sysdep.h>
|
#include <sysdep.h>
|
||||||
|
|
||||||
.text
|
.section .text.sse4, "ax", @progbits
|
||||||
.section .text.sse4,"ax",@progbits
|
|
||||||
ENTRY(_ZGVbN4v_atanhf_sse4)
|
ENTRY(_ZGVbN4v_atanhf_sse4)
|
||||||
subq $72, %rsp
|
subq $72, %rsp
|
||||||
cfi_def_cfa_offset(80)
|
cfi_def_cfa_offset(80)
|
||||||
movaps %xmm0, %xmm5
|
movaps %xmm0, %xmm5
|
||||||
|
|
||||||
/* Load constants including One = 1 */
|
/* Load constants including One = 1 */
|
||||||
movups sOne+__svml_satanh_data_internal(%rip), %xmm4
|
movups sOne+__svml_satanh_data_internal(%rip), %xmm4
|
||||||
movaps %xmm5, %xmm3
|
movaps %xmm5, %xmm3
|
||||||
|
|
||||||
/* Strip off the sign, so treat X as positive until right at the end */
|
/* Strip off the sign, so treat X as positive until right at the end */
|
||||||
movups SgnMask+__svml_satanh_data_internal(%rip), %xmm7
|
movups SgnMask+__svml_satanh_data_internal(%rip), %xmm7
|
||||||
movaps %xmm4, %xmm8
|
movaps %xmm4, %xmm8
|
||||||
andps %xmm5, %xmm7
|
andps %xmm5, %xmm7
|
||||||
movaps %xmm4, %xmm10
|
movaps %xmm4, %xmm10
|
||||||
movups sTopMask12+__svml_satanh_data_internal(%rip), %xmm11
|
movups sTopMask12+__svml_satanh_data_internal(%rip), %xmm11
|
||||||
movaps %xmm4, %xmm14
|
movaps %xmm4, %xmm14
|
||||||
movaps %xmm11, %xmm9
|
movaps %xmm11, %xmm9
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Compute V = 2 * X trivially, and UHi + U_lo = 1 - X in two pieces,
|
* Compute V = 2 * X trivially, and UHi + U_lo = 1 - X in two pieces,
|
||||||
* the upper part UHi being <= 12 bits long. Then we have
|
* the upper part UHi being <= 12 bits long. Then we have
|
||||||
* atanh(X) = 1/2 * log((1 + X) / (1 - X)) = 1/2 * log1p(V / (UHi + ULo)).
|
* atanh(X) = 1/2 * log((1 + X) / (1 - X)) = 1/2 * log1p(V / (UHi + ULo)).
|
||||||
*/
|
*/
|
||||||
movaps %xmm7, %xmm12
|
movaps %xmm7, %xmm12
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Check whether |X| < 1, in which case we use the main function.
|
* Check whether |X| < 1, in which case we use the main function.
|
||||||
* Otherwise set the rangemask so that the callout will get used.
|
* Otherwise set the rangemask so that the callout will get used.
|
||||||
* Note that this will also use the callout for NaNs since not(NaN < 1).
|
* Note that this will also use the callout for NaNs since not(NaN < 1).
|
||||||
*/
|
*/
|
||||||
movaps %xmm7, %xmm6
|
movaps %xmm7, %xmm6
|
||||||
movaps %xmm7, %xmm2
|
movaps %xmm7, %xmm2
|
||||||
cmpnltps %xmm4, %xmm6
|
cmpnltps %xmm4, %xmm6
|
||||||
cmpltps TinyRange+__svml_satanh_data_internal(%rip), %xmm2
|
cmpltps TinyRange+__svml_satanh_data_internal(%rip), %xmm2
|
||||||
mulps %xmm5, %xmm3
|
mulps %xmm5, %xmm3
|
||||||
subps %xmm7, %xmm8
|
subps %xmm7, %xmm8
|
||||||
addps %xmm7, %xmm12
|
addps %xmm7, %xmm12
|
||||||
movmskps %xmm6, %edx
|
movmskps %xmm6, %edx
|
||||||
subps %xmm8, %xmm10
|
subps %xmm8, %xmm10
|
||||||
addps %xmm5, %xmm3
|
addps %xmm5, %xmm3
|
||||||
subps %xmm7, %xmm10
|
subps %xmm7, %xmm10
|
||||||
andps %xmm8, %xmm9
|
andps %xmm8, %xmm9
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Now we feed into the log1p code, using H in place of _VARG1 and
|
* Now we feed into the log1p code, using H in place of _VARG1 and
|
||||||
* later incorporating L into the reduced argument.
|
* later incorporating L into the reduced argument.
|
||||||
* compute 1+x as high, low parts
|
* compute 1+x as high, low parts
|
||||||
*/
|
*/
|
||||||
movaps %xmm4, %xmm7
|
movaps %xmm4, %xmm7
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Now compute R = 1/(UHi+ULo) * (1 - E) and the error term E
|
* Now compute R = 1/(UHi+ULo) * (1 - E) and the error term E
|
||||||
* The first FMR is exact (we force R to 12 bits just in case it
|
* The first FMR is exact (we force R to 12 bits just in case it
|
||||||
* isn't already, to make absolutely sure), and since E is ~ 2^-12,
|
* isn't already, to make absolutely sure), and since E is ~ 2^-12,
|
||||||
* the rounding error in the other one is acceptable.
|
* the rounding error in the other one is acceptable.
|
||||||
*/
|
*/
|
||||||
rcpps %xmm9, %xmm15
|
rcpps %xmm9, %xmm15
|
||||||
subps %xmm9, %xmm8
|
subps %xmm9, %xmm8
|
||||||
andps %xmm11, %xmm15
|
andps %xmm11, %xmm15
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Split V as well into upper 12 bits and lower part, so that we can get
|
* Split V as well into upper 12 bits and lower part, so that we can get
|
||||||
* a preliminary quotient estimate without rounding error.
|
* a preliminary quotient estimate without rounding error.
|
||||||
*/
|
*/
|
||||||
andps %xmm12, %xmm11
|
andps %xmm12, %xmm11
|
||||||
mulps %xmm15, %xmm9
|
mulps %xmm15, %xmm9
|
||||||
addps %xmm8, %xmm10
|
addps %xmm8, %xmm10
|
||||||
subps %xmm11, %xmm12
|
subps %xmm11, %xmm12
|
||||||
|
|
||||||
/* Hence get initial quotient estimate QHi + QLo = R * VHi + R * VLo */
|
/* Hence get initial quotient estimate QHi + QLo = R * VHi + R * VLo */
|
||||||
mulps %xmm15, %xmm11
|
mulps %xmm15, %xmm11
|
||||||
mulps %xmm15, %xmm10
|
mulps %xmm15, %xmm10
|
||||||
subps %xmm9, %xmm14
|
subps %xmm9, %xmm14
|
||||||
mulps %xmm12, %xmm15
|
mulps %xmm12, %xmm15
|
||||||
subps %xmm10, %xmm14
|
subps %xmm10, %xmm14
|
||||||
|
|
||||||
/* Compute D = E + E^2 */
|
/* Compute D = E + E^2 */
|
||||||
movaps %xmm14, %xmm13
|
movaps %xmm14, %xmm13
|
||||||
movaps %xmm4, %xmm8
|
movaps %xmm4, %xmm8
|
||||||
mulps %xmm14, %xmm13
|
mulps %xmm14, %xmm13
|
||||||
|
|
||||||
/* reduction: compute r,n */
|
/* reduction: compute r, n */
|
||||||
movdqu iBrkValue+__svml_satanh_data_internal(%rip), %xmm9
|
movdqu iBrkValue+__svml_satanh_data_internal(%rip), %xmm9
|
||||||
addps %xmm13, %xmm14
|
addps %xmm13, %xmm14
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Compute R * (VHi + VLo) * (1 + E + E^2)
|
* Compute R * (VHi + VLo) * (1 + E + E^2)
|
||||||
* = R * (VHi + VLo) * (1 + D)
|
* = R * (VHi + VLo) * (1 + D)
|
||||||
* = QHi + (QHi * D + QLo + QLo * D)
|
* = QHi + (QHi * D + QLo + QLo * D)
|
||||||
*/
|
*/
|
||||||
movaps %xmm14, %xmm0
|
movaps %xmm14, %xmm0
|
||||||
mulps %xmm15, %xmm14
|
mulps %xmm15, %xmm14
|
||||||
mulps %xmm11, %xmm0
|
mulps %xmm11, %xmm0
|
||||||
addps %xmm14, %xmm15
|
addps %xmm14, %xmm15
|
||||||
movdqu iOffExpoMask+__svml_satanh_data_internal(%rip), %xmm12
|
movdqu iOffExpoMask+__svml_satanh_data_internal(%rip), %xmm12
|
||||||
movaps %xmm4, %xmm14
|
movaps %xmm4, %xmm14
|
||||||
|
|
||||||
/* Record the sign for eventual reincorporation. */
|
/* Record the sign for eventual reincorporation. */
|
||||||
movups sSign+__svml_satanh_data_internal(%rip), %xmm1
|
movups sSign+__svml_satanh_data_internal(%rip), %xmm1
|
||||||
addps %xmm15, %xmm0
|
addps %xmm15, %xmm0
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Now finally accumulate the high and low parts of the
|
* Now finally accumulate the high and low parts of the
|
||||||
* argument to log1p, H + L, with a final compensated summation.
|
* argument to log1p, H + L, with a final compensated summation.
|
||||||
*/
|
*/
|
||||||
movaps %xmm0, %xmm6
|
movaps %xmm0, %xmm6
|
||||||
andps %xmm5, %xmm1
|
andps %xmm5, %xmm1
|
||||||
|
|
||||||
/* Or the sign bit in with the tiny result to handle atanh(-0) correctly */
|
/* Or the sign bit in with the tiny result to handle atanh(-0) correctly */
|
||||||
orps %xmm1, %xmm3
|
orps %xmm1, %xmm3
|
||||||
addps %xmm11, %xmm6
|
addps %xmm11, %xmm6
|
||||||
maxps %xmm6, %xmm7
|
maxps %xmm6, %xmm7
|
||||||
minps %xmm6, %xmm8
|
minps %xmm6, %xmm8
|
||||||
subps %xmm6, %xmm11
|
subps %xmm6, %xmm11
|
||||||
movaps %xmm7, %xmm10
|
movaps %xmm7, %xmm10
|
||||||
andps %xmm2, %xmm3
|
andps %xmm2, %xmm3
|
||||||
addps %xmm8, %xmm10
|
addps %xmm8, %xmm10
|
||||||
addps %xmm11, %xmm0
|
addps %xmm11, %xmm0
|
||||||
subps %xmm10, %xmm7
|
subps %xmm10, %xmm7
|
||||||
psubd %xmm9, %xmm10
|
psubd %xmm9, %xmm10
|
||||||
addps %xmm7, %xmm8
|
addps %xmm7, %xmm8
|
||||||
pand %xmm10, %xmm12
|
pand %xmm10, %xmm12
|
||||||
psrad $23, %xmm10
|
psrad $23, %xmm10
|
||||||
cvtdq2ps %xmm10, %xmm13
|
cvtdq2ps %xmm10, %xmm13
|
||||||
addps %xmm8, %xmm0
|
addps %xmm8, %xmm0
|
||||||
|
|
||||||
/* final reconstruction */
|
/* final reconstruction */
|
||||||
mulps sLn2+__svml_satanh_data_internal(%rip), %xmm13
|
mulps sLn2+__svml_satanh_data_internal(%rip), %xmm13
|
||||||
pslld $23, %xmm10
|
pslld $23, %xmm10
|
||||||
paddd %xmm9, %xmm12
|
paddd %xmm9, %xmm12
|
||||||
psubd %xmm10, %xmm14
|
psubd %xmm10, %xmm14
|
||||||
|
|
||||||
/* polynomial evaluation */
|
/* polynomial evaluation */
|
||||||
subps %xmm4, %xmm12
|
subps %xmm4, %xmm12
|
||||||
mulps %xmm0, %xmm14
|
mulps %xmm0, %xmm14
|
||||||
movups sPoly+112+__svml_satanh_data_internal(%rip), %xmm0
|
movups sPoly+112+__svml_satanh_data_internal(%rip), %xmm0
|
||||||
addps %xmm12, %xmm14
|
addps %xmm12, %xmm14
|
||||||
mulps %xmm14, %xmm0
|
mulps %xmm14, %xmm0
|
||||||
|
|
||||||
/* Finally, halve the result and reincorporate the sign */
|
/* Finally, halve the result and reincorporate the sign */
|
||||||
movups sHalf+__svml_satanh_data_internal(%rip), %xmm4
|
movups sHalf+__svml_satanh_data_internal(%rip), %xmm4
|
||||||
pxor %xmm1, %xmm4
|
pxor %xmm1, %xmm4
|
||||||
addps sPoly+96+__svml_satanh_data_internal(%rip), %xmm0
|
addps sPoly+96+__svml_satanh_data_internal(%rip), %xmm0
|
||||||
mulps %xmm14, %xmm0
|
mulps %xmm14, %xmm0
|
||||||
addps sPoly+80+__svml_satanh_data_internal(%rip), %xmm0
|
addps sPoly+80+__svml_satanh_data_internal(%rip), %xmm0
|
||||||
mulps %xmm14, %xmm0
|
mulps %xmm14, %xmm0
|
||||||
addps sPoly+64+__svml_satanh_data_internal(%rip), %xmm0
|
addps sPoly+64+__svml_satanh_data_internal(%rip), %xmm0
|
||||||
mulps %xmm14, %xmm0
|
mulps %xmm14, %xmm0
|
||||||
addps sPoly+48+__svml_satanh_data_internal(%rip), %xmm0
|
addps sPoly+48+__svml_satanh_data_internal(%rip), %xmm0
|
||||||
mulps %xmm14, %xmm0
|
mulps %xmm14, %xmm0
|
||||||
addps sPoly+32+__svml_satanh_data_internal(%rip), %xmm0
|
addps sPoly+32+__svml_satanh_data_internal(%rip), %xmm0
|
||||||
mulps %xmm14, %xmm0
|
mulps %xmm14, %xmm0
|
||||||
addps sPoly+16+__svml_satanh_data_internal(%rip), %xmm0
|
addps sPoly+16+__svml_satanh_data_internal(%rip), %xmm0
|
||||||
mulps %xmm14, %xmm0
|
mulps %xmm14, %xmm0
|
||||||
addps sPoly+__svml_satanh_data_internal(%rip), %xmm0
|
addps sPoly+__svml_satanh_data_internal(%rip), %xmm0
|
||||||
mulps %xmm14, %xmm0
|
mulps %xmm14, %xmm0
|
||||||
mulps %xmm14, %xmm0
|
mulps %xmm14, %xmm0
|
||||||
addps %xmm0, %xmm14
|
addps %xmm0, %xmm14
|
||||||
movaps %xmm2, %xmm0
|
movaps %xmm2, %xmm0
|
||||||
addps %xmm13, %xmm14
|
addps %xmm13, %xmm14
|
||||||
mulps %xmm14, %xmm4
|
mulps %xmm14, %xmm4
|
||||||
andnps %xmm4, %xmm0
|
andnps %xmm4, %xmm0
|
||||||
orps %xmm3, %xmm0
|
orps %xmm3, %xmm0
|
||||||
testl %edx, %edx
|
testl %edx, %edx
|
||||||
|
|
||||||
/* Go to special inputs processing branch */
|
/* Go to special inputs processing branch */
|
||||||
jne L(SPECIAL_VALUES_BRANCH)
|
jne L(SPECIAL_VALUES_BRANCH)
|
||||||
# LOE rbx rbp r12 r13 r14 r15 edx xmm0 xmm5
|
# LOE rbx rbp r12 r13 r14 r15 edx xmm0 xmm5
|
||||||
|
|
||||||
/* Restore registers
|
/* Restore registers
|
||||||
* and exit the function
|
* and exit the function
|
||||||
*/
|
*/
|
||||||
|
|
||||||
L(EXIT):
|
L(EXIT):
|
||||||
addq $72, %rsp
|
addq $72, %rsp
|
||||||
cfi_def_cfa_offset(8)
|
cfi_def_cfa_offset(8)
|
||||||
ret
|
ret
|
||||||
cfi_def_cfa_offset(80)
|
cfi_def_cfa_offset(80)
|
||||||
|
|
||||||
/* Branch to process
|
/* Branch to process
|
||||||
* special inputs
|
* special inputs
|
||||||
*/
|
*/
|
||||||
|
|
||||||
L(SPECIAL_VALUES_BRANCH):
|
L(SPECIAL_VALUES_BRANCH):
|
||||||
movups %xmm5, 32(%rsp)
|
movups %xmm5, 32(%rsp)
|
||||||
movups %xmm0, 48(%rsp)
|
movups %xmm0, 48(%rsp)
|
||||||
# LOE rbx rbp r12 r13 r14 r15 edx
|
# LOE rbx rbp r12 r13 r14 r15 edx
|
||||||
|
|
||||||
xorl %eax, %eax
|
xorl %eax, %eax
|
||||||
movq %r12, 16(%rsp)
|
movq %r12, 16(%rsp)
|
||||||
cfi_offset(12, -64)
|
cfi_offset(12, -64)
|
||||||
movl %eax, %r12d
|
movl %eax, %r12d
|
||||||
movq %r13, 8(%rsp)
|
movq %r13, 8(%rsp)
|
||||||
cfi_offset(13, -72)
|
cfi_offset(13, -72)
|
||||||
movl %edx, %r13d
|
movl %edx, %r13d
|
||||||
movq %r14, (%rsp)
|
movq %r14, (%rsp)
|
||||||
cfi_offset(14, -80)
|
cfi_offset(14, -80)
|
||||||
# LOE rbx rbp r15 r12d r13d
|
# LOE rbx rbp r15 r12d r13d
|
||||||
|
|
||||||
/* Range mask
|
/* Range mask
|
||||||
* bits check
|
* bits check
|
||||||
*/
|
*/
|
||||||
|
|
||||||
L(RANGEMASK_CHECK):
|
L(RANGEMASK_CHECK):
|
||||||
btl %r12d, %r13d
|
btl %r12d, %r13d
|
||||||
|
|
||||||
/* Call scalar math function */
|
/* Call scalar math function */
|
||||||
jc L(SCALAR_MATH_CALL)
|
jc L(SCALAR_MATH_CALL)
|
||||||
# LOE rbx rbp r15 r12d r13d
|
# LOE rbx rbp r15 r12d r13d
|
||||||
|
|
||||||
/* Special inputs
|
/* Special inputs
|
||||||
* processing loop
|
* processing loop
|
||||||
*/
|
*/
|
||||||
|
|
||||||
L(SPECIAL_VALUES_LOOP):
|
L(SPECIAL_VALUES_LOOP):
|
||||||
incl %r12d
|
incl %r12d
|
||||||
cmpl $4, %r12d
|
cmpl $4, %r12d
|
||||||
|
|
||||||
/* Check bits in range mask */
|
/* Check bits in range mask */
|
||||||
jl L(RANGEMASK_CHECK)
|
jl L(RANGEMASK_CHECK)
|
||||||
# LOE rbx rbp r15 r12d r13d
|
# LOE rbx rbp r15 r12d r13d
|
||||||
|
|
||||||
movq 16(%rsp), %r12
|
movq 16(%rsp), %r12
|
||||||
cfi_restore(12)
|
cfi_restore(12)
|
||||||
movq 8(%rsp), %r13
|
movq 8(%rsp), %r13
|
||||||
cfi_restore(13)
|
cfi_restore(13)
|
||||||
movq (%rsp), %r14
|
movq (%rsp), %r14
|
||||||
cfi_restore(14)
|
cfi_restore(14)
|
||||||
movups 48(%rsp), %xmm0
|
movups 48(%rsp), %xmm0
|
||||||
|
|
||||||
/* Go to exit */
|
/* Go to exit */
|
||||||
jmp L(EXIT)
|
jmp L(EXIT)
|
||||||
cfi_offset(12, -64)
|
cfi_offset(12, -64)
|
||||||
cfi_offset(13, -72)
|
cfi_offset(13, -72)
|
||||||
cfi_offset(14, -80)
|
cfi_offset(14, -80)
|
||||||
# LOE rbx rbp r12 r13 r14 r15 xmm0
|
# LOE rbx rbp r12 r13 r14 r15 xmm0
|
||||||
|
|
||||||
/* Scalar math fucntion call
|
/* Scalar math fucntion call
|
||||||
* to process special input
|
* to process special input
|
||||||
*/
|
*/
|
||||||
|
|
||||||
L(SCALAR_MATH_CALL):
|
L(SCALAR_MATH_CALL):
|
||||||
movl %r12d, %r14d
|
movl %r12d, %r14d
|
||||||
movss 32(%rsp,%r14,4), %xmm0
|
movss 32(%rsp, %r14, 4), %xmm0
|
||||||
call atanhf@PLT
|
call atanhf@PLT
|
||||||
# LOE rbx rbp r14 r15 r12d r13d xmm0
|
# LOE rbx rbp r14 r15 r12d r13d xmm0
|
||||||
|
|
||||||
movss %xmm0, 48(%rsp,%r14,4)
|
movss %xmm0, 48(%rsp, %r14, 4)
|
||||||
|
|
||||||
/* Process special inputs in loop */
|
/* Process special inputs in loop */
|
||||||
jmp L(SPECIAL_VALUES_LOOP)
|
jmp L(SPECIAL_VALUES_LOOP)
|
||||||
# LOE rbx rbp r15 r12d r13d
|
# LOE rbx rbp r15 r12d r13d
|
||||||
END(_ZGVbN4v_atanhf_sse4)
|
END(_ZGVbN4v_atanhf_sse4)
|
||||||
|
|
||||||
.section .rodata, "a"
|
.section .rodata, "a"
|
||||||
.align 16
|
.align 16
|
||||||
|
|
||||||
#ifdef __svml_satanh_data_internal_typedef
|
#ifdef __svml_satanh_data_internal_typedef
|
||||||
typedef unsigned int VUINT32;
|
typedef unsigned int VUINT32;
|
||||||
typedef struct {
|
typedef struct {
|
||||||
__declspec(align(16)) VUINT32 SgnMask[4][1];
|
__declspec(align(16)) VUINT32 SgnMask[4][1];
|
||||||
__declspec(align(16)) VUINT32 sOne[4][1];
|
__declspec(align(16)) VUINT32 sOne[4][1];
|
||||||
__declspec(align(16)) VUINT32 sPoly[8][4][1];
|
__declspec(align(16)) VUINT32 sPoly[8][4][1];
|
||||||
__declspec(align(16)) VUINT32 iBrkValue[4][1];
|
__declspec(align(16)) VUINT32 iBrkValue[4][1];
|
||||||
__declspec(align(16)) VUINT32 iOffExpoMask[4][1];
|
__declspec(align(16)) VUINT32 iOffExpoMask[4][1];
|
||||||
__declspec(align(16)) VUINT32 sHalf[4][1];
|
__declspec(align(16)) VUINT32 sHalf[4][1];
|
||||||
__declspec(align(16)) VUINT32 sSign[4][1];
|
__declspec(align(16)) VUINT32 sSign[4][1];
|
||||||
__declspec(align(16)) VUINT32 sTopMask12[4][1];
|
__declspec(align(16)) VUINT32 sTopMask12[4][1];
|
||||||
__declspec(align(16)) VUINT32 TinyRange[4][1];
|
__declspec(align(16)) VUINT32 TinyRange[4][1];
|
||||||
__declspec(align(16)) VUINT32 sLn2[4][1];
|
__declspec(align(16)) VUINT32 sLn2[4][1];
|
||||||
} __svml_satanh_data_internal;
|
} __svml_satanh_data_internal;
|
||||||
#endif
|
#endif
|
||||||
__svml_satanh_data_internal:
|
__svml_satanh_data_internal:
|
||||||
/*== SgnMask ==*/
|
/* SgnMask */
|
||||||
.long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
|
.long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
|
||||||
/*== sOne = SP 1.0 ==*/
|
/* sOne = SP 1.0 */
|
||||||
.align 16
|
.align 16
|
||||||
.long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
|
.long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
|
||||||
/*== sPoly[] = SP polynomial ==*/
|
/* sPoly[] = SP polynomial */
|
||||||
.align 16
|
.align 16
|
||||||
.long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 /* -5.0000000000000000000000000e-01 P0 */
|
.long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 /* -5.0000000000000000000000000e-01 P0 */
|
||||||
.long 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94 /* 3.3333265781402587890625000e-01 P1 */
|
.long 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94 /* 3.3333265781402587890625000e-01 P1 */
|
||||||
.long 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e /* -2.5004237890243530273437500e-01 P2 */
|
.long 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e /* -2.5004237890243530273437500e-01 P2 */
|
||||||
.long 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190 /* 2.0007920265197753906250000e-01 P3 */
|
.long 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190 /* 2.0007920265197753906250000e-01 P3 */
|
||||||
.long 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37 /* -1.6472326219081878662109375e-01 P4 */
|
.long 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37 /* -1.6472326219081878662109375e-01 P4 */
|
||||||
.long 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12 /* 1.4042308926582336425781250e-01 P5 */
|
.long 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12 /* 1.4042308926582336425781250e-01 P5 */
|
||||||
.long 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3 /* -1.5122179687023162841796875e-01 P6 */
|
.long 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3 /* -1.5122179687023162841796875e-01 P6 */
|
||||||
.long 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed /* 1.3820238411426544189453125e-01 P7 */
|
.long 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed /* 1.3820238411426544189453125e-01 P7 */
|
||||||
/*== iBrkValue = SP 2/3 ==*/
|
/* iBrkValue = SP 2/3 */
|
||||||
.align 16
|
.align 16
|
||||||
.long 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab
|
.long 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab
|
||||||
/*== iOffExpoMask = SP significand mask ==*/
|
/* iOffExpoMask = SP significand mask */
|
||||||
.align 16
|
.align 16
|
||||||
.long 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff
|
.long 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff
|
||||||
/*== sHalf ==*/
|
/* sHalf */
|
||||||
.align 16
|
.align 16
|
||||||
.long 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000
|
.long 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000
|
||||||
/*== sSign ==*/
|
/* sSign */
|
||||||
.align 16
|
.align 16
|
||||||
.long 0x80000000, 0x80000000, 0x80000000, 0x80000000
|
.long 0x80000000, 0x80000000, 0x80000000, 0x80000000
|
||||||
/*== sTopMask12 ==*/
|
/* sTopMask12 */
|
||||||
.align 16
|
.align 16
|
||||||
.long 0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000
|
.long 0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000
|
||||||
/*== TinyRange ==*/
|
/* TinyRange */
|
||||||
.align 16
|
.align 16
|
||||||
.long 0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000
|
.long 0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000
|
||||||
/*== sLn2 = SP ln(2) ==*/
|
/* sLn2 = SP ln(2) */
|
||||||
.align 16
|
.align 16
|
||||||
.long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218
|
.long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218
|
||||||
.align 16
|
.align 16
|
||||||
.type __svml_satanh_data_internal,@object
|
.type __svml_satanh_data_internal, @object
|
||||||
.size __svml_satanh_data_internal,.-__svml_satanh_data_internal
|
.size __svml_satanh_data_internal, .-__svml_satanh_data_internal
|
||||||
|
Loading…
Reference in New Issue
Block a user