mirror of git://sourceware.org/git/glibc.git
x86_64: Fix svml_s_acoshf8_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>
This commit is contained in:
Sunil K Pandey
parent
c90f386276
commit
dfa127e854
|
|
@ -33,338 +33,337 @@
|
|||
|
||||
/* Offsets for data table __svml_sacosh_data_internal
|
||||
*/
|
||||
#define sOne 0
|
||||
#define sPoly 32
|
||||
#define iBrkValue 288
|
||||
#define iOffExpoMask 320
|
||||
#define sBigThreshold 352
|
||||
#define sC2 384
|
||||
#define sC3 416
|
||||
#define sHalf 448
|
||||
#define sLargestFinite 480
|
||||
#define sThirtyOne 512
|
||||
#define sTopMask8 544
|
||||
#define XScale 576
|
||||
#define sLn2 608
|
||||
#define sOne 0
|
||||
#define sPoly 32
|
||||
#define iBrkValue 288
|
||||
#define iOffExpoMask 320
|
||||
#define sBigThreshold 352
|
||||
#define sC2 384
|
||||
#define sC3 416
|
||||
#define sHalf 448
|
||||
#define sLargestFinite 480
|
||||
#define sThirtyOne 512
|
||||
#define sTopMask8 544
|
||||
#define XScale 576
|
||||
#define sLn2 608
|
||||
|
||||
#include <sysdep.h>
|
||||
|
||||
.text
|
||||
.section .text.avx2,"ax",@progbits
|
||||
.section .text.avx2, "ax", @progbits
|
||||
ENTRY(_ZGVdN8v_acoshf_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
|
||||
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
|
||||
|
||||
/* Load constants, always including One = 1 */
|
||||
vmovups sOne+__svml_sacosh_data_internal(%rip), %ymm2
|
||||
/* Load constants, always including One = 1 */
|
||||
vmovups sOne+__svml_sacosh_data_internal(%rip), %ymm2
|
||||
|
||||
/* Finally, express Y + W = U * V accurately where Y has <= 8 bits */
|
||||
vmovups sTopMask8+__svml_sacosh_data_internal(%rip), %ymm9
|
||||
/* Finally, express Y + W = U * V accurately where Y has <= 8 bits */
|
||||
vmovups sTopMask8+__svml_sacosh_data_internal(%rip), %ymm9
|
||||
|
||||
/*
|
||||
* Now 1 / (1 + d)
|
||||
* = 1 / (1 + (sqrt(1 - e) - 1))
|
||||
* = 1 / sqrt(1 - e)
|
||||
* = 1 + 1/2 * e + 3/8 * e^2 + 5/16 * e^3 + 35/128 * e^4 + ...
|
||||
* So compute the first three nonconstant terms of that, so that
|
||||
* we have a relative correction (1 + Corr) to apply to S etc.
|
||||
* C1 = 1/2
|
||||
* C2 = 3/8
|
||||
* C3 = 5/16
|
||||
*/
|
||||
vmovups sC3+__svml_sacosh_data_internal(%rip), %ymm14
|
||||
vmovaps %ymm0, %ymm3
|
||||
vmovaps %ymm2, %ymm7
|
||||
vfmsub231ps %ymm3, %ymm3, %ymm7
|
||||
/*
|
||||
* Now 1 / (1 + d)
|
||||
* = 1 / (1 + (sqrt(1 - e) - 1))
|
||||
* = 1 / sqrt(1 - e)
|
||||
* = 1 + 1/2 * e + 3/8 * e^2 + 5/16 * e^3 + 35/128 * e^4 + ...
|
||||
* So compute the first three nonconstant terms of that, so that
|
||||
* we have a relative correction (1 + Corr) to apply to S etc.
|
||||
* C1 = 1/2
|
||||
* C2 = 3/8
|
||||
* C3 = 5/16
|
||||
*/
|
||||
vmovups sC3+__svml_sacosh_data_internal(%rip), %ymm14
|
||||
vmovaps %ymm0, %ymm3
|
||||
vmovaps %ymm2, %ymm7
|
||||
vfmsub231ps %ymm3, %ymm3, %ymm7
|
||||
|
||||
/*
|
||||
* Check that 1 < X < +inf; otherwise go to the callout function.
|
||||
* We need the callout for X = 1 to avoid division by zero below.
|
||||
* This test ensures that callout handles NaN and either infinity.
|
||||
*/
|
||||
vcmpnle_uqps sLargestFinite+__svml_sacosh_data_internal(%rip), %ymm3, %ymm4
|
||||
vcmpngt_uqps %ymm2, %ymm3, %ymm5
|
||||
/*
|
||||
* Check that 1 < X < +inf; otherwise go to the callout function.
|
||||
* We need the callout for X = 1 to avoid division by zero below.
|
||||
* This test ensures that callout handles NaN and either infinity.
|
||||
*/
|
||||
vcmpnle_uqps sLargestFinite+__svml_sacosh_data_internal(%rip), %ymm3, %ymm4
|
||||
vcmpngt_uqps %ymm2, %ymm3, %ymm5
|
||||
|
||||
/*
|
||||
* The following computation can go wrong for very large X, e.g.
|
||||
* the X^2 - 1 = U * V can overflow. But for large X we have
|
||||
* acosh(X) / log(2 X) - 1 =~= 1/(4 * X^2), so for X >= 2^30
|
||||
* we can just later stick X back into the log and tweak up the exponent.
|
||||
* Actually we scale X by 2^-30 and tweak the exponent up by 31,
|
||||
* to stay in the safe range for the later log computation.
|
||||
* Compute a flag now telling us when to do this.
|
||||
*/
|
||||
vcmplt_oqps sBigThreshold+__svml_sacosh_data_internal(%rip), %ymm3, %ymm1
|
||||
vandps %ymm9, %ymm7, %ymm10
|
||||
/*
|
||||
* The following computation can go wrong for very large X, e.g.
|
||||
* the X^2 - 1 = U * V can overflow. But for large X we have
|
||||
* acosh(X) / log(2 X) - 1 =~= 1/(4 * X^2), so for X >= 2^30
|
||||
* we can just later stick X back into the log and tweak up the exponent.
|
||||
* Actually we scale X by 2^-30 and tweak the exponent up by 31,
|
||||
* to stay in the safe range for the later log computation.
|
||||
* Compute a flag now telling us when to do this.
|
||||
*/
|
||||
vcmplt_oqps sBigThreshold+__svml_sacosh_data_internal(%rip), %ymm3, %ymm1
|
||||
vandps %ymm9, %ymm7, %ymm10
|
||||
|
||||
/*
|
||||
* Compute R = 1/sqrt(Y + W) * (1 + d)
|
||||
* Force R to <= 8 significant bits.
|
||||
* This means that R * Y and R^2 * Y are exactly representable.
|
||||
*/
|
||||
vrsqrtps %ymm10, %ymm8
|
||||
vsubps %ymm10, %ymm7, %ymm11
|
||||
vandps %ymm9, %ymm8, %ymm12
|
||||
/*
|
||||
* Compute R = 1/sqrt(Y + W) * (1 + d)
|
||||
* Force R to <= 8 significant bits.
|
||||
* This means that R * Y and R^2 * Y are exactly representable.
|
||||
*/
|
||||
vrsqrtps %ymm10, %ymm8
|
||||
vsubps %ymm10, %ymm7, %ymm11
|
||||
vandps %ymm9, %ymm8, %ymm12
|
||||
|
||||
/*
|
||||
* Compute S = (Y/sqrt(Y + W)) * (1 + d)
|
||||
* and T = (W/sqrt(Y + W)) * (1 + d)
|
||||
* so that S + T = sqrt(Y + W) * (1 + d)
|
||||
* S is exact, and the rounding error in T is OK.
|
||||
*/
|
||||
vmulps %ymm12, %ymm10, %ymm15
|
||||
vmulps %ymm11, %ymm12, %ymm0
|
||||
/*
|
||||
* Compute S = (Y/sqrt(Y + W)) * (1 + d)
|
||||
* and T = (W/sqrt(Y + W)) * (1 + d)
|
||||
* so that S + T = sqrt(Y + W) * (1 + d)
|
||||
* S is exact, and the rounding error in T is OK.
|
||||
*/
|
||||
vmulps %ymm12, %ymm10, %ymm15
|
||||
vmulps %ymm11, %ymm12, %ymm0
|
||||
|
||||
/* Now multiplex to the case X = 2^-30 * input, Xl = 0 in the "big" case. */
|
||||
vmulps XScale+__svml_sacosh_data_internal(%rip), %ymm3, %ymm11
|
||||
/* Now multiplex to the case X = 2^-30 * input, Xl = 0 in the "big" case. */
|
||||
vmulps XScale+__svml_sacosh_data_internal(%rip), %ymm3, %ymm11
|
||||
|
||||
/*
|
||||
* Compute e = -(2 * d + d^2)
|
||||
* The first FMR is exact, and the rounding error in the other is acceptable
|
||||
* since d and e are ~ 2^-8
|
||||
*/
|
||||
vmovaps %ymm2, %ymm13
|
||||
vfnmadd231ps %ymm15, %ymm12, %ymm13
|
||||
vfnmadd231ps %ymm0, %ymm12, %ymm13
|
||||
vfmadd213ps sC2+__svml_sacosh_data_internal(%rip), %ymm13, %ymm14
|
||||
vfmadd213ps sHalf+__svml_sacosh_data_internal(%rip), %ymm13, %ymm14
|
||||
vmulps %ymm14, %ymm13, %ymm7
|
||||
vorps %ymm5, %ymm4, %ymm6
|
||||
/*
|
||||
* Compute e = -(2 * d + d^2)
|
||||
* The first FMR is exact, and the rounding error in the other is acceptable
|
||||
* since d and e are ~ 2^-8
|
||||
*/
|
||||
vmovaps %ymm2, %ymm13
|
||||
vfnmadd231ps %ymm15, %ymm12, %ymm13
|
||||
vfnmadd231ps %ymm0, %ymm12, %ymm13
|
||||
vfmadd213ps sC2+__svml_sacosh_data_internal(%rip), %ymm13, %ymm14
|
||||
vfmadd213ps sHalf+__svml_sacosh_data_internal(%rip), %ymm13, %ymm14
|
||||
vmulps %ymm14, %ymm13, %ymm7
|
||||
vorps %ymm5, %ymm4, %ymm6
|
||||
|
||||
/*
|
||||
* For low-accuracy versions, the computation can be done
|
||||
* just as U + ((S + T) + (S + T) * Corr)
|
||||
*/
|
||||
vaddps %ymm0, %ymm15, %ymm5
|
||||
/*
|
||||
* For low-accuracy versions, the computation can be done
|
||||
* just as U + ((S + T) + (S + T) * Corr)
|
||||
*/
|
||||
vaddps %ymm0, %ymm15, %ymm5
|
||||
|
||||
/* sU is needed later on */
|
||||
vsubps %ymm2, %ymm3, %ymm4
|
||||
vfmadd213ps %ymm5, %ymm7, %ymm5
|
||||
vmovmskps %ymm6, %edx
|
||||
vaddps %ymm5, %ymm4, %ymm6
|
||||
/* sU is needed later on */
|
||||
vsubps %ymm2, %ymm3, %ymm4
|
||||
vfmadd213ps %ymm5, %ymm7, %ymm5
|
||||
vmovmskps %ymm6, %edx
|
||||
vaddps %ymm5, %ymm4, %ymm6
|
||||
|
||||
/*
|
||||
* Now resume the main code.
|
||||
* reduction: compute r,n
|
||||
*/
|
||||
vmovups iBrkValue+__svml_sacosh_data_internal(%rip), %ymm4
|
||||
/*
|
||||
* Now resume the main code.
|
||||
* reduction: compute r, n
|
||||
*/
|
||||
vmovups iBrkValue+__svml_sacosh_data_internal(%rip), %ymm4
|
||||
|
||||
/*
|
||||
* Now we feed into the log1p code, using H in place of _VARG1 and
|
||||
* also adding L into Xl.
|
||||
* compute 1+x as high, low parts
|
||||
*/
|
||||
vmaxps %ymm6, %ymm2, %ymm8
|
||||
vminps %ymm6, %ymm2, %ymm9
|
||||
vaddps %ymm9, %ymm8, %ymm12
|
||||
vblendvps %ymm1, %ymm12, %ymm11, %ymm14
|
||||
vsubps %ymm12, %ymm8, %ymm10
|
||||
vpsubd %ymm4, %ymm14, %ymm15
|
||||
vaddps %ymm10, %ymm9, %ymm13
|
||||
vpand iOffExpoMask+__svml_sacosh_data_internal(%rip), %ymm15, %ymm14
|
||||
vpsrad $23, %ymm15, %ymm15
|
||||
vpaddd %ymm4, %ymm14, %ymm8
|
||||
vpslld $23, %ymm15, %ymm5
|
||||
vmovups sPoly+224+__svml_sacosh_data_internal(%rip), %ymm4
|
||||
vcvtdq2ps %ymm15, %ymm0
|
||||
vpsubd %ymm5, %ymm2, %ymm7
|
||||
/*
|
||||
* Now we feed into the log1p code, using H in place of _VARG1 and
|
||||
* also adding L into Xl.
|
||||
* compute 1+x as high, low parts
|
||||
*/
|
||||
vmaxps %ymm6, %ymm2, %ymm8
|
||||
vminps %ymm6, %ymm2, %ymm9
|
||||
vaddps %ymm9, %ymm8, %ymm12
|
||||
vblendvps %ymm1, %ymm12, %ymm11, %ymm14
|
||||
vsubps %ymm12, %ymm8, %ymm10
|
||||
vpsubd %ymm4, %ymm14, %ymm15
|
||||
vaddps %ymm10, %ymm9, %ymm13
|
||||
vpand iOffExpoMask+__svml_sacosh_data_internal(%rip), %ymm15, %ymm14
|
||||
vpsrad $23, %ymm15, %ymm15
|
||||
vpaddd %ymm4, %ymm14, %ymm8
|
||||
vpslld $23, %ymm15, %ymm5
|
||||
vmovups sPoly+224+__svml_sacosh_data_internal(%rip), %ymm4
|
||||
vcvtdq2ps %ymm15, %ymm0
|
||||
vpsubd %ymm5, %ymm2, %ymm7
|
||||
|
||||
/* polynomial evaluation */
|
||||
vsubps %ymm2, %ymm8, %ymm2
|
||||
/* polynomial evaluation */
|
||||
vsubps %ymm2, %ymm8, %ymm2
|
||||
|
||||
/* Add 31 to the exponent in the "large" case to get log(2 * input) */
|
||||
vaddps sThirtyOne+__svml_sacosh_data_internal(%rip), %ymm0, %ymm5
|
||||
vandps %ymm1, %ymm13, %ymm6
|
||||
vmulps %ymm7, %ymm6, %ymm9
|
||||
vblendvps %ymm1, %ymm0, %ymm5, %ymm0
|
||||
vaddps %ymm2, %ymm9, %ymm2
|
||||
vfmadd213ps sPoly+192+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+160+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+128+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+96+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+64+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+32+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vmulps %ymm4, %ymm2, %ymm6
|
||||
vfmadd213ps %ymm2, %ymm2, %ymm6
|
||||
/* Add 31 to the exponent in the "large" case to get log(2 * input) */
|
||||
vaddps sThirtyOne+__svml_sacosh_data_internal(%rip), %ymm0, %ymm5
|
||||
vandps %ymm1, %ymm13, %ymm6
|
||||
vmulps %ymm7, %ymm6, %ymm9
|
||||
vblendvps %ymm1, %ymm0, %ymm5, %ymm0
|
||||
vaddps %ymm2, %ymm9, %ymm2
|
||||
vfmadd213ps sPoly+192+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+160+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+128+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+96+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+64+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+32+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vfmadd213ps sPoly+__svml_sacosh_data_internal(%rip), %ymm2, %ymm4
|
||||
vmulps %ymm4, %ymm2, %ymm6
|
||||
vfmadd213ps %ymm2, %ymm2, %ymm6
|
||||
|
||||
/* final reconstruction */
|
||||
vfmadd132ps sLn2+__svml_sacosh_data_internal(%rip), %ymm6, %ymm0
|
||||
testl %edx, %edx
|
||||
/* final reconstruction */
|
||||
vfmadd132ps sLn2+__svml_sacosh_data_internal(%rip), %ymm6, %ymm0
|
||||
testl %edx, %edx
|
||||
|
||||
/* Go to special inputs processing branch */
|
||||
jne L(SPECIAL_VALUES_BRANCH)
|
||||
# LOE rbx r12 r13 r14 r15 edx ymm0 ymm3
|
||||
/* Go to special inputs processing branch */
|
||||
jne L(SPECIAL_VALUES_BRANCH)
|
||||
# LOE rbx r12 r13 r14 r15 edx ymm0 ymm3
|
||||
|
||||
/* Restore registers
|
||||
* and exit the function
|
||||
*/
|
||||
/* 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)
|
||||
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
|
||||
*/
|
||||
/* Branch to process
|
||||
* special inputs
|
||||
*/
|
||||
|
||||
L(SPECIAL_VALUES_BRANCH):
|
||||
vmovups %ymm3, 32(%rsp)
|
||||
vmovups %ymm0, 64(%rsp)
|
||||
# LOE rbx r12 r13 r14 r15 edx ymm0
|
||||
vmovups %ymm3, 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
|
||||
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
|
||||
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
|
||||
*/
|
||||
/* 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
|
||||
incl %r12d
|
||||
cmpl $8, %r12d
|
||||
|
||||
/* Check bits in range mask */
|
||||
jl L(RANGEMASK_CHECK)
|
||||
# LOE rbx r15 r12d r13d
|
||||
/* 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
|
||||
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
|
||||
/* 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
|
||||
*/
|
||||
/* Scalar math fucntion call
|
||||
* to process special input
|
||||
*/
|
||||
|
||||
L(SCALAR_MATH_CALL):
|
||||
movl %r12d, %r14d
|
||||
movss 32(%rsp,%r14,4), %xmm0
|
||||
call acoshf@PLT
|
||||
# LOE rbx r14 r15 r12d r13d xmm0
|
||||
movl %r12d, %r14d
|
||||
movss 32(%rsp, %r14, 4), %xmm0
|
||||
call acoshf@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_acoshf_avx2)
|
||||
|
||||
.section .rodata, "a"
|
||||
.align 32
|
||||
.section .rodata, "a"
|
||||
.align 32
|
||||
|
||||
#ifdef __svml_sacosh_data_internal_typedef
|
||||
typedef unsigned int VUINT32;
|
||||
typedef struct {
|
||||
__declspec(align(32)) VUINT32 sOne[8][1];
|
||||
__declspec(align(32)) VUINT32 sPoly[8][8][1];
|
||||
__declspec(align(32)) VUINT32 iBrkValue[8][1];
|
||||
__declspec(align(32)) VUINT32 iOffExpoMask[8][1];
|
||||
__declspec(align(32)) VUINT32 sBigThreshold[8][1];
|
||||
__declspec(align(32)) VUINT32 sC2[8][1];
|
||||
__declspec(align(32)) VUINT32 sC3[8][1];
|
||||
__declspec(align(32)) VUINT32 sHalf[8][1];
|
||||
__declspec(align(32)) VUINT32 sLargestFinite[8][1];
|
||||
__declspec(align(32)) VUINT32 sThirtyOne[8][1];
|
||||
__declspec(align(32)) VUINT32 sTopMask8[8][1];
|
||||
__declspec(align(32)) VUINT32 XScale[8][1];
|
||||
__declspec(align(32)) VUINT32 sLn2[8][1];
|
||||
__declspec(align(32)) VUINT32 sOne[8][1];
|
||||
__declspec(align(32)) VUINT32 sPoly[8][8][1];
|
||||
__declspec(align(32)) VUINT32 iBrkValue[8][1];
|
||||
__declspec(align(32)) VUINT32 iOffExpoMask[8][1];
|
||||
__declspec(align(32)) VUINT32 sBigThreshold[8][1];
|
||||
__declspec(align(32)) VUINT32 sC2[8][1];
|
||||
__declspec(align(32)) VUINT32 sC3[8][1];
|
||||
__declspec(align(32)) VUINT32 sHalf[8][1];
|
||||
__declspec(align(32)) VUINT32 sLargestFinite[8][1];
|
||||
__declspec(align(32)) VUINT32 sThirtyOne[8][1];
|
||||
__declspec(align(32)) VUINT32 sTopMask8[8][1];
|
||||
__declspec(align(32)) VUINT32 XScale[8][1];
|
||||
__declspec(align(32)) VUINT32 sLn2[8][1];
|
||||
} __svml_sacosh_data_internal;
|
||||
#endif
|
||||
__svml_sacosh_data_internal:
|
||||
/*== sOne = SP 1.0 ==*/
|
||||
.long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
|
||||
/*== sPoly[] = SP polynomial ==*/
|
||||
.align 32
|
||||
.long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 /* -5.0000000000000000000000000e-01 P0 */
|
||||
.long 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94 /* 3.3333265781402587890625000e-01 P1 */
|
||||
.long 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e /* -2.5004237890243530273437500e-01 P2 */
|
||||
.long 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190 /* 2.0007920265197753906250000e-01 P3 */
|
||||
.long 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37 /* -1.6472326219081878662109375e-01 P4 */
|
||||
.long 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12 /* 1.4042308926582336425781250e-01 P5 */
|
||||
.long 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3 /* -1.5122179687023162841796875e-01 P6 */
|
||||
.long 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed /* 1.3820238411426544189453125e-01 P7 */
|
||||
/*== iBrkValue = SP 2/3 ==*/
|
||||
.align 32
|
||||
.long 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab
|
||||
/*== iOffExpoMask = SP significand mask ==*/
|
||||
.align 32
|
||||
.long 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff
|
||||
/*== sBigThreshold ==*/
|
||||
.align 32
|
||||
.long 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000
|
||||
/*== sC2 ==*/
|
||||
.align 32
|
||||
.long 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000
|
||||
/*== sC3 ==*/
|
||||
.align 32
|
||||
.long 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000
|
||||
/*== sHalf ==*/
|
||||
.align 32
|
||||
.long 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000
|
||||
/*== sLargestFinite ==*/
|
||||
.align 32
|
||||
.long 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF
|
||||
/*== sThirtyOne ==*/
|
||||
.align 32
|
||||
.long 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000
|
||||
/*== sTopMask8 ==*/
|
||||
.align 32
|
||||
.long 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000
|
||||
/*== XScale ==*/
|
||||
.align 32
|
||||
.long 0x30800000, 0x30800000, 0x30800000, 0x30800000, 0x30800000, 0x30800000, 0x30800000, 0x30800000
|
||||
/*== sLn2 = SP ln(2) ==*/
|
||||
.align 32
|
||||
.long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218
|
||||
.align 32
|
||||
.type __svml_sacosh_data_internal,@object
|
||||
.size __svml_sacosh_data_internal,.-__svml_sacosh_data_internal
|
||||
/* sOne = SP 1.0 */
|
||||
.long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
|
||||
/* sPoly[] = SP polynomial */
|
||||
.align 32
|
||||
.long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 /* -5.0000000000000000000000000e-01 P0 */
|
||||
.long 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94 /* 3.3333265781402587890625000e-01 P1 */
|
||||
.long 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e /* -2.5004237890243530273437500e-01 P2 */
|
||||
.long 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190 /* 2.0007920265197753906250000e-01 P3 */
|
||||
.long 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37 /* -1.6472326219081878662109375e-01 P4 */
|
||||
.long 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12 /* 1.4042308926582336425781250e-01 P5 */
|
||||
.long 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3 /* -1.5122179687023162841796875e-01 P6 */
|
||||
.long 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed /* 1.3820238411426544189453125e-01 P7 */
|
||||
/* iBrkValue = SP 2/3 */
|
||||
.align 32
|
||||
.long 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab
|
||||
/* iOffExpoMask = SP significand mask */
|
||||
.align 32
|
||||
.long 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff
|
||||
/* sBigThreshold */
|
||||
.align 32
|
||||
.long 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000, 0x4E800000
|
||||
/* sC2 */
|
||||
.align 32
|
||||
.long 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000, 0x3EC00000
|
||||
/* sC3 */
|
||||
.align 32
|
||||
.long 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000, 0x3EA00000
|
||||
/* sHalf */
|
||||
.align 32
|
||||
.long 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000
|
||||
/* sLargestFinite */
|
||||
.align 32
|
||||
.long 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF, 0x7F7FFFFF
|
||||
/* sThirtyOne */
|
||||
.align 32
|
||||
.long 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000, 0x41F80000
|
||||
/* sTopMask8 */
|
||||
.align 32
|
||||
.long 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000, 0xFFFF0000
|
||||
/* XScale */
|
||||
.align 32
|
||||
.long 0x30800000, 0x30800000, 0x30800000, 0x30800000, 0x30800000, 0x30800000, 0x30800000, 0x30800000
|
||||
/* sLn2 = SP ln(2) */
|
||||
.align 32
|
||||
.long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218
|
||||
.align 32
|
||||
.type __svml_sacosh_data_internal, @object
|
||||
.size __svml_sacosh_data_internal, .-__svml_sacosh_data_internal
|
||||
|
|
|
|||
Loading…
Reference in New Issue