mirror of git://sourceware.org/git/glibc.git
x86_64: Fix svml_d_acos8_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>
This commit is contained in:
Sunil K Pandey
parent
656ff2e94e
commit
67031a3934
|
|
@ -28,280 +28,279 @@
|
||||||
|
|
||||||
/* Offsets for data table __svml_dacos_data_internal
|
/* Offsets for data table __svml_dacos_data_internal
|
||||||
*/
|
*/
|
||||||
#define SgnBit 0
|
#define SgnBit 0
|
||||||
#define OneHalf 64
|
#define OneHalf 64
|
||||||
#define SmallNorm 128
|
#define SmallNorm 128
|
||||||
#define MOne 192
|
#define MOne 192
|
||||||
#define Two 256
|
#define Two 256
|
||||||
#define sqrt_coeff_1 320
|
#define sqrt_coeff_1 320
|
||||||
#define sqrt_coeff_2 384
|
#define sqrt_coeff_2 384
|
||||||
#define sqrt_coeff_3 448
|
#define sqrt_coeff_3 448
|
||||||
#define sqrt_coeff_4 512
|
#define sqrt_coeff_4 512
|
||||||
#define poly_coeff_1 576
|
#define poly_coeff_1 576
|
||||||
#define poly_coeff_2 640
|
#define poly_coeff_2 640
|
||||||
#define poly_coeff_3 704
|
#define poly_coeff_3 704
|
||||||
#define poly_coeff_4 768
|
#define poly_coeff_4 768
|
||||||
#define poly_coeff_5 832
|
#define poly_coeff_5 832
|
||||||
#define poly_coeff_6 896
|
#define poly_coeff_6 896
|
||||||
#define poly_coeff_7 960
|
#define poly_coeff_7 960
|
||||||
#define poly_coeff_8 1024
|
#define poly_coeff_8 1024
|
||||||
#define poly_coeff_9 1088
|
#define poly_coeff_9 1088
|
||||||
#define poly_coeff_10 1152
|
#define poly_coeff_10 1152
|
||||||
#define poly_coeff_11 1216
|
#define poly_coeff_11 1216
|
||||||
#define poly_coeff_12 1280
|
#define poly_coeff_12 1280
|
||||||
#define PiH 1344
|
#define PiH 1344
|
||||||
#define Pi2H 1408
|
#define Pi2H 1408
|
||||||
|
|
||||||
#include <sysdep.h>
|
#include <sysdep.h>
|
||||||
|
|
||||||
.text
|
.section .text.evex512, "ax", @progbits
|
||||||
.section .text.evex512,"ax",@progbits
|
|
||||||
ENTRY(_ZGVeN8v_acos_skx)
|
ENTRY(_ZGVeN8v_acos_skx)
|
||||||
pushq %rbp
|
pushq %rbp
|
||||||
cfi_def_cfa_offset(16)
|
cfi_def_cfa_offset(16)
|
||||||
movq %rsp, %rbp
|
movq %rsp, %rbp
|
||||||
cfi_def_cfa(6, 16)
|
cfi_def_cfa(6, 16)
|
||||||
cfi_offset(6, -16)
|
cfi_offset(6, -16)
|
||||||
andq $-64, %rsp
|
andq $-64, %rsp
|
||||||
subq $192, %rsp
|
subq $192, %rsp
|
||||||
vmovups __svml_dacos_data_internal(%rip), %zmm7
|
vmovups __svml_dacos_data_internal(%rip), %zmm7
|
||||||
vmovups OneHalf+__svml_dacos_data_internal(%rip), %zmm8
|
vmovups OneHalf+__svml_dacos_data_internal(%rip), %zmm8
|
||||||
|
|
||||||
/* S ~ 2*sqrt(Y) */
|
/* S ~ 2*sqrt(Y) */
|
||||||
vmovups SmallNorm+__svml_dacos_data_internal(%rip), %zmm11
|
vmovups SmallNorm+__svml_dacos_data_internal(%rip), %zmm11
|
||||||
vmovups Two+__svml_dacos_data_internal(%rip), %zmm14
|
vmovups Two+__svml_dacos_data_internal(%rip), %zmm14
|
||||||
vmovups sqrt_coeff_1+__svml_dacos_data_internal(%rip), %zmm15
|
vmovups sqrt_coeff_1+__svml_dacos_data_internal(%rip), %zmm15
|
||||||
vmovups sqrt_coeff_2+__svml_dacos_data_internal(%rip), %zmm2
|
vmovups sqrt_coeff_2+__svml_dacos_data_internal(%rip), %zmm2
|
||||||
vmovups sqrt_coeff_3+__svml_dacos_data_internal(%rip), %zmm1
|
vmovups sqrt_coeff_3+__svml_dacos_data_internal(%rip), %zmm1
|
||||||
vmovups MOne+__svml_dacos_data_internal(%rip), %zmm10
|
vmovups MOne+__svml_dacos_data_internal(%rip), %zmm10
|
||||||
vmovaps %zmm0, %zmm6
|
vmovaps %zmm0, %zmm6
|
||||||
|
|
||||||
/* x = -|arg| */
|
/* x = -|arg| */
|
||||||
vorpd %zmm6, %zmm7, %zmm5
|
vorpd %zmm6, %zmm7, %zmm5
|
||||||
vandpd %zmm6, %zmm7, %zmm4
|
vandpd %zmm6, %zmm7, %zmm4
|
||||||
|
|
||||||
/* Y = 0.5 + 0.5*(-x) */
|
/* Y = 0.5 + 0.5*(-x) */
|
||||||
vfmadd231pd {rn-sae}, %zmm5, %zmm8, %zmm8
|
vfmadd231pd {rn-sae}, %zmm5, %zmm8, %zmm8
|
||||||
|
|
||||||
/* x^2 */
|
/* x^2 */
|
||||||
vmulpd {rn-sae}, %zmm5, %zmm5, %zmm9
|
vmulpd {rn-sae}, %zmm5, %zmm5, %zmm9
|
||||||
vrsqrt14pd %zmm8, %zmm12
|
vrsqrt14pd %zmm8, %zmm12
|
||||||
vcmppd $17, {sae}, %zmm11, %zmm8, %k1
|
vcmppd $17, {sae}, %zmm11, %zmm8, %k1
|
||||||
vcmppd $17, {sae}, %zmm10, %zmm5, %k0
|
vcmppd $17, {sae}, %zmm10, %zmm5, %k0
|
||||||
vmovups poly_coeff_5+__svml_dacos_data_internal(%rip), %zmm10
|
vmovups poly_coeff_5+__svml_dacos_data_internal(%rip), %zmm10
|
||||||
vmovups poly_coeff_7+__svml_dacos_data_internal(%rip), %zmm11
|
vmovups poly_coeff_7+__svml_dacos_data_internal(%rip), %zmm11
|
||||||
vminpd {sae}, %zmm8, %zmm9, %zmm3
|
vminpd {sae}, %zmm8, %zmm9, %zmm3
|
||||||
vmovups poly_coeff_3+__svml_dacos_data_internal(%rip), %zmm9
|
vmovups poly_coeff_3+__svml_dacos_data_internal(%rip), %zmm9
|
||||||
vxorpd %zmm12, %zmm12, %zmm12{%k1}
|
vxorpd %zmm12, %zmm12, %zmm12{%k1}
|
||||||
vaddpd {rn-sae}, %zmm8, %zmm8, %zmm0
|
vaddpd {rn-sae}, %zmm8, %zmm8, %zmm0
|
||||||
vcmppd $21, {sae}, %zmm8, %zmm3, %k4
|
vcmppd $21, {sae}, %zmm8, %zmm3, %k4
|
||||||
|
|
||||||
/* X<X^2 iff X<0 */
|
/* X<X^2 iff X<0 */
|
||||||
vcmppd $17, {sae}, %zmm3, %zmm6, %k2
|
vcmppd $17, {sae}, %zmm3, %zmm6, %k2
|
||||||
vmulpd {rn-sae}, %zmm12, %zmm12, %zmm13
|
vmulpd {rn-sae}, %zmm12, %zmm12, %zmm13
|
||||||
vmulpd {rn-sae}, %zmm12, %zmm0, %zmm7
|
vmulpd {rn-sae}, %zmm12, %zmm0, %zmm7
|
||||||
vmovups poly_coeff_4+__svml_dacos_data_internal(%rip), %zmm12
|
vmovups poly_coeff_4+__svml_dacos_data_internal(%rip), %zmm12
|
||||||
|
|
||||||
/* polynomial */
|
/* polynomial */
|
||||||
vmovups poly_coeff_1+__svml_dacos_data_internal(%rip), %zmm8
|
vmovups poly_coeff_1+__svml_dacos_data_internal(%rip), %zmm8
|
||||||
vfmsub213pd {rn-sae}, %zmm14, %zmm13, %zmm0
|
vfmsub213pd {rn-sae}, %zmm14, %zmm13, %zmm0
|
||||||
vmovups sqrt_coeff_4+__svml_dacos_data_internal(%rip), %zmm13
|
vmovups sqrt_coeff_4+__svml_dacos_data_internal(%rip), %zmm13
|
||||||
vfmadd231pd {rn-sae}, %zmm3, %zmm9, %zmm12
|
vfmadd231pd {rn-sae}, %zmm3, %zmm9, %zmm12
|
||||||
vmovups poly_coeff_11+__svml_dacos_data_internal(%rip), %zmm9
|
vmovups poly_coeff_11+__svml_dacos_data_internal(%rip), %zmm9
|
||||||
vfmadd231pd {rn-sae}, %zmm0, %zmm15, %zmm2
|
vfmadd231pd {rn-sae}, %zmm0, %zmm15, %zmm2
|
||||||
vmovups poly_coeff_9+__svml_dacos_data_internal(%rip), %zmm15
|
vmovups poly_coeff_9+__svml_dacos_data_internal(%rip), %zmm15
|
||||||
vmulpd {rn-sae}, %zmm0, %zmm7, %zmm14
|
vmulpd {rn-sae}, %zmm0, %zmm7, %zmm14
|
||||||
vfmadd213pd {rn-sae}, %zmm1, %zmm0, %zmm2
|
vfmadd213pd {rn-sae}, %zmm1, %zmm0, %zmm2
|
||||||
vmovups poly_coeff_2+__svml_dacos_data_internal(%rip), %zmm1
|
vmovups poly_coeff_2+__svml_dacos_data_internal(%rip), %zmm1
|
||||||
kmovw %k0, %edx
|
kmovw %k0, %edx
|
||||||
vfmadd213pd {rn-sae}, %zmm13, %zmm0, %zmm2
|
vfmadd213pd {rn-sae}, %zmm13, %zmm0, %zmm2
|
||||||
vfmadd231pd {rn-sae}, %zmm3, %zmm8, %zmm1
|
vfmadd231pd {rn-sae}, %zmm3, %zmm8, %zmm1
|
||||||
vmovups poly_coeff_10+__svml_dacos_data_internal(%rip), %zmm8
|
vmovups poly_coeff_10+__svml_dacos_data_internal(%rip), %zmm8
|
||||||
vmulpd {rn-sae}, %zmm3, %zmm3, %zmm0
|
vmulpd {rn-sae}, %zmm3, %zmm3, %zmm0
|
||||||
vfnmadd213pd {rn-sae}, %zmm7, %zmm14, %zmm2
|
vfnmadd213pd {rn-sae}, %zmm7, %zmm14, %zmm2
|
||||||
vmovups poly_coeff_6+__svml_dacos_data_internal(%rip), %zmm7
|
vmovups poly_coeff_6+__svml_dacos_data_internal(%rip), %zmm7
|
||||||
vfmadd231pd {rn-sae}, %zmm3, %zmm15, %zmm8
|
vfmadd231pd {rn-sae}, %zmm3, %zmm15, %zmm8
|
||||||
vfmadd213pd {rn-sae}, %zmm12, %zmm0, %zmm1
|
vfmadd213pd {rn-sae}, %zmm12, %zmm0, %zmm1
|
||||||
vblendmpd %zmm2, %zmm5, %zmm2{%k4}
|
vblendmpd %zmm2, %zmm5, %zmm2{%k4}
|
||||||
vfmadd231pd {rn-sae}, %zmm3, %zmm10, %zmm7
|
vfmadd231pd {rn-sae}, %zmm3, %zmm10, %zmm7
|
||||||
vmovups poly_coeff_8+__svml_dacos_data_internal(%rip), %zmm10
|
vmovups poly_coeff_8+__svml_dacos_data_internal(%rip), %zmm10
|
||||||
vfmadd231pd {rn-sae}, %zmm3, %zmm11, %zmm10
|
vfmadd231pd {rn-sae}, %zmm3, %zmm11, %zmm10
|
||||||
vmovups poly_coeff_12+__svml_dacos_data_internal(%rip), %zmm11
|
vmovups poly_coeff_12+__svml_dacos_data_internal(%rip), %zmm11
|
||||||
kandw %k4, %k2, %k3
|
kandw %k4, %k2, %k3
|
||||||
vfmadd213pd {rn-sae}, %zmm10, %zmm0, %zmm7
|
vfmadd213pd {rn-sae}, %zmm10, %zmm0, %zmm7
|
||||||
vfmadd231pd {rn-sae}, %zmm3, %zmm9, %zmm11
|
vfmadd231pd {rn-sae}, %zmm3, %zmm9, %zmm11
|
||||||
vmulpd {rn-sae}, %zmm0, %zmm0, %zmm10
|
vmulpd {rn-sae}, %zmm0, %zmm0, %zmm10
|
||||||
vfmadd213pd {rn-sae}, %zmm7, %zmm10, %zmm1
|
vfmadd213pd {rn-sae}, %zmm7, %zmm10, %zmm1
|
||||||
vfmadd213pd {rn-sae}, %zmm8, %zmm0, %zmm1
|
vfmadd213pd {rn-sae}, %zmm8, %zmm0, %zmm1
|
||||||
vfmadd213pd {rn-sae}, %zmm11, %zmm0, %zmm1
|
vfmadd213pd {rn-sae}, %zmm11, %zmm0, %zmm1
|
||||||
vmovups Pi2H+__svml_dacos_data_internal(%rip), %zmm0
|
vmovups Pi2H+__svml_dacos_data_internal(%rip), %zmm0
|
||||||
vmulpd {rn-sae}, %zmm3, %zmm1, %zmm1
|
vmulpd {rn-sae}, %zmm3, %zmm1, %zmm1
|
||||||
vxorpd %zmm4, %zmm2, %zmm3
|
vxorpd %zmm4, %zmm2, %zmm3
|
||||||
vxorpd %zmm0, %zmm0, %zmm0{%k4}
|
vxorpd %zmm0, %zmm0, %zmm0{%k4}
|
||||||
vfmadd213pd {rn-sae}, %zmm3, %zmm3, %zmm1
|
vfmadd213pd {rn-sae}, %zmm3, %zmm3, %zmm1
|
||||||
vorpd PiH+__svml_dacos_data_internal(%rip), %zmm0, %zmm0{%k3}
|
vorpd PiH+__svml_dacos_data_internal(%rip), %zmm0, %zmm0{%k3}
|
||||||
vaddpd {rn-sae}, %zmm1, %zmm0, %zmm0
|
vaddpd {rn-sae}, %zmm1, %zmm0, %zmm0
|
||||||
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 r12 r13 r14 r15 edx zmm0 zmm6
|
# LOE rbx r12 r13 r14 r15 edx zmm0 zmm6
|
||||||
|
|
||||||
/* Restore registers
|
/* Restore registers
|
||||||
* and exit the function
|
* and exit the function
|
||||||
*/
|
*/
|
||||||
|
|
||||||
L(EXIT):
|
L(EXIT):
|
||||||
movq %rbp, %rsp
|
movq %rbp, %rsp
|
||||||
popq %rbp
|
popq %rbp
|
||||||
cfi_def_cfa(7, 8)
|
cfi_def_cfa(7, 8)
|
||||||
cfi_restore(6)
|
cfi_restore(6)
|
||||||
ret
|
ret
|
||||||
cfi_def_cfa(6, 16)
|
cfi_def_cfa(6, 16)
|
||||||
cfi_offset(6, -16)
|
cfi_offset(6, -16)
|
||||||
|
|
||||||
/* Branch to process
|
/* Branch to process
|
||||||
* special inputs
|
* special inputs
|
||||||
*/
|
*/
|
||||||
|
|
||||||
L(SPECIAL_VALUES_BRANCH):
|
L(SPECIAL_VALUES_BRANCH):
|
||||||
vmovups %zmm6, 64(%rsp)
|
vmovups %zmm6, 64(%rsp)
|
||||||
vmovups %zmm0, 128(%rsp)
|
vmovups %zmm0, 128(%rsp)
|
||||||
# LOE rbx r12 r13 r14 r15 edx zmm0
|
# LOE rbx r12 r13 r14 r15 edx zmm0
|
||||||
|
|
||||||
xorl %eax, %eax
|
xorl %eax, %eax
|
||||||
# LOE rbx r12 r13 r14 r15 eax edx
|
# LOE rbx r12 r13 r14 r15 eax edx
|
||||||
|
|
||||||
vzeroupper
|
vzeroupper
|
||||||
movq %r12, 16(%rsp)
|
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) */
|
/* 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
|
.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
|
||||||
movl %eax, %r12d
|
movl %eax, %r12d
|
||||||
movq %r13, 8(%rsp)
|
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) */
|
/* 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
|
.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
|
||||||
movl %edx, %r13d
|
movl %edx, %r13d
|
||||||
movq %r14, (%rsp)
|
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) */
|
/* 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
|
.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22
|
||||||
# LOE rbx r15 r12d r13d
|
# LOE rbx 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 r15 r12d r13d
|
# LOE rbx r15 r12d r13d
|
||||||
|
|
||||||
/* Special inputs
|
/* Special inputs
|
||||||
* processing loop
|
* processing loop
|
||||||
*/
|
*/
|
||||||
|
|
||||||
L(SPECIAL_VALUES_LOOP):
|
L(SPECIAL_VALUES_LOOP):
|
||||||
incl %r12d
|
incl %r12d
|
||||||
cmpl $8, %r12d
|
cmpl $8, %r12d
|
||||||
|
|
||||||
/* Check bits in range mask */
|
/* Check bits in range mask */
|
||||||
jl L(RANGEMASK_CHECK)
|
jl L(RANGEMASK_CHECK)
|
||||||
# LOE rbx r15 r12d r13d
|
# LOE rbx 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)
|
||||||
vmovups 128(%rsp), %zmm0
|
vmovups 128(%rsp), %zmm0
|
||||||
|
|
||||||
/* Go to exit */
|
/* Go to exit */
|
||||||
jmp L(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) */
|
/* 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
|
.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) */
|
/* 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
|
.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) */
|
/* 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
|
.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
|
# LOE rbx r12 r13 r14 r15 zmm0
|
||||||
|
|
||||||
/* 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
|
||||||
movsd 64(%rsp,%r14,8), %xmm0
|
movsd 64(%rsp, %r14, 8), %xmm0
|
||||||
call acos@PLT
|
call acos@PLT
|
||||||
# LOE rbx r14 r15 r12d r13d xmm0
|
# LOE rbx r14 r15 r12d r13d xmm0
|
||||||
|
|
||||||
movsd %xmm0, 128(%rsp,%r14,8)
|
movsd %xmm0, 128(%rsp, %r14, 8)
|
||||||
|
|
||||||
/* Process special inputs in loop */
|
/* Process special inputs in loop */
|
||||||
jmp L(SPECIAL_VALUES_LOOP)
|
jmp L(SPECIAL_VALUES_LOOP)
|
||||||
# LOE rbx r15 r12d r13d
|
# LOE rbx r15 r12d r13d
|
||||||
END(_ZGVeN8v_acos_skx)
|
END(_ZGVeN8v_acos_skx)
|
||||||
|
|
||||||
.section .rodata, "a"
|
.section .rodata, "a"
|
||||||
.align 64
|
.align 64
|
||||||
|
|
||||||
#ifdef __svml_dacos_data_internal_typedef
|
#ifdef __svml_dacos_data_internal_typedef
|
||||||
typedef unsigned int VUINT32;
|
typedef unsigned int VUINT32;
|
||||||
typedef struct {
|
typedef struct {
|
||||||
__declspec(align(64)) VUINT32 SgnBit[8][2];
|
__declspec(align(64)) VUINT32 SgnBit[8][2];
|
||||||
__declspec(align(64)) VUINT32 OneHalf[8][2];
|
__declspec(align(64)) VUINT32 OneHalf[8][2];
|
||||||
__declspec(align(64)) VUINT32 SmallNorm[8][2];
|
__declspec(align(64)) VUINT32 SmallNorm[8][2];
|
||||||
__declspec(align(64)) VUINT32 MOne[8][2];
|
__declspec(align(64)) VUINT32 MOne[8][2];
|
||||||
__declspec(align(64)) VUINT32 Two[8][2];
|
__declspec(align(64)) VUINT32 Two[8][2];
|
||||||
__declspec(align(64)) VUINT32 sqrt_coeff[4][8][2];
|
__declspec(align(64)) VUINT32 sqrt_coeff[4][8][2];
|
||||||
__declspec(align(64)) VUINT32 poly_coeff[12][8][2];
|
__declspec(align(64)) VUINT32 poly_coeff[12][8][2];
|
||||||
__declspec(align(64)) VUINT32 PiH[8][2];
|
__declspec(align(64)) VUINT32 PiH[8][2];
|
||||||
__declspec(align(64)) VUINT32 Pi2H[8][2];
|
__declspec(align(64)) VUINT32 Pi2H[8][2];
|
||||||
} __svml_dacos_data_internal;
|
} __svml_dacos_data_internal;
|
||||||
#endif
|
#endif
|
||||||
__svml_dacos_data_internal:
|
__svml_dacos_data_internal:
|
||||||
/*== SgnBit ==*/
|
/* SgnBit */
|
||||||
.quad 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000
|
.quad 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000, 0x8000000000000000
|
||||||
/*== OneHalf ==*/
|
/* OneHalf */
|
||||||
.align 64
|
.align 64
|
||||||
.quad 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000
|
.quad 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000, 0x3fe0000000000000
|
||||||
/*== SmallNorm ==*/
|
/* SmallNorm */
|
||||||
.align 64
|
.align 64
|
||||||
.quad 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000
|
.quad 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000, 0x3000000000000000
|
||||||
/*== MOne ==*/
|
/* MOne */
|
||||||
.align 64
|
.align 64
|
||||||
.quad 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000
|
.quad 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000, 0xbff0000000000000
|
||||||
/*== Two ==*/
|
/* Two */
|
||||||
.align 64
|
.align 64
|
||||||
.quad 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000
|
.quad 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000, 0x4000000000000000
|
||||||
/*== sqrt_coeff[4] ==*/
|
/* sqrt_coeff[4] */
|
||||||
.align 64
|
.align 64
|
||||||
.quad 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3 /* sqrt_coeff4 */
|
.quad 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3, 0xbf918000993B24C3 /* sqrt_coeff4 */
|
||||||
.quad 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D /* sqrt_coeff3 */
|
.quad 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D, 0x3fa400006F70D42D /* sqrt_coeff3 */
|
||||||
.quad 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97 /* sqrt_coeff2 */
|
.quad 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97, 0xbfb7FFFFFFFFFE97 /* sqrt_coeff2 */
|
||||||
.quad 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D /* sqrt_coeff1 */
|
.quad 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D, 0x3fcFFFFFFFFFFF9D /* sqrt_coeff1 */
|
||||||
/*== poly_coeff[12] ==*/
|
/* poly_coeff[12] */
|
||||||
.align 64
|
.align 64
|
||||||
.quad 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909 /* poly_coeff12 */
|
.quad 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909, 0x3fa07520C70EB909 /* poly_coeff12 */
|
||||||
.quad 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED /* poly_coeff11 */
|
.quad 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED, 0xbf90FB17F7DBB0ED /* poly_coeff11 */
|
||||||
.quad 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE /* poly_coeff10 */
|
.quad 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE, 0x3f943F44BFBC3BAE /* poly_coeff10 */
|
||||||
.quad 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5 /* poly_coeff9 */
|
.quad 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5, 0x3f7A583395D45ED5 /* poly_coeff9 */
|
||||||
.quad 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6 /* poly_coeff8 */
|
.quad 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6, 0x3f88F8DC2AFCCAD6 /* poly_coeff8 */
|
||||||
.quad 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57 /* poly_coeff7 */
|
.quad 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57, 0x3f8C6DBBCB88BD57 /* poly_coeff7 */
|
||||||
.quad 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E /* poly_coeff6 */
|
.quad 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E, 0x3f91C6DCF538AD2E /* poly_coeff6 */
|
||||||
.quad 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd /* poly_coeff5 */
|
.quad 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd, 0x3f96E89CEBDEFadd /* poly_coeff5 */
|
||||||
.quad 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE /* poly_coeff4 */
|
.quad 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE, 0x3f9F1C72E13AD8BE /* poly_coeff4 */
|
||||||
.quad 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8 /* poly_coeff3 */
|
.quad 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8, 0x3fa6DB6DB3B445F8 /* poly_coeff3 */
|
||||||
.quad 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE /* poly_coeff2 */
|
.quad 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE, 0x3fb333333337E0DE /* poly_coeff2 */
|
||||||
.quad 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C /* poly_coeff1 */
|
.quad 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C, 0x3fc555555555529C /* poly_coeff1 */
|
||||||
/*== PiH ==*/
|
/* PiH */
|
||||||
.align 64
|
.align 64
|
||||||
.quad 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18
|
.quad 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18, 0x400921fb54442d18
|
||||||
/*== Pi2H ==*/
|
/* Pi2H */
|
||||||
.align 64
|
.align 64
|
||||||
.quad 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18
|
.quad 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18, 0x3ff921fb54442d18
|
||||||
.align 64
|
.align 64
|
||||||
.type __svml_dacos_data_internal,@object
|
.type __svml_dacos_data_internal, @object
|
||||||
.size __svml_dacos_data_internal,.-__svml_dacos_data_internal
|
.size __svml_dacos_data_internal, .-__svml_dacos_data_internal
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue