mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-25 22:40:05 +00:00
x86_64: Fix svml_s_asinf8_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
e597cf3975
commit
3bc1831523
@ -39,8 +39,7 @@
|
||||
|
||||
#include <sysdep.h>
|
||||
|
||||
.text
|
||||
.section .text.avx2,"ax",@progbits
|
||||
.section .text.avx2, "ax", @progbits
|
||||
ENTRY(_ZGVdN8v_asinf_avx2)
|
||||
pushq %rbp
|
||||
cfi_def_cfa_offset(16)
|
||||
@ -54,18 +53,18 @@ ENTRY(_ZGVdN8v_asinf_avx2)
|
||||
vmovups One+__svml_sasin_data_internal(%rip), %ymm6
|
||||
vmovaps %ymm0, %ymm4
|
||||
|
||||
/* x = |arg| */
|
||||
/* x = |arg| */
|
||||
vandps %ymm4, %ymm5, %ymm3
|
||||
|
||||
/* Y = 0.5 - 0.5*x */
|
||||
/* Y = 0.5 - 0.5*x */
|
||||
vmovaps %ymm9, %ymm12
|
||||
vfnmadd231ps %ymm3, %ymm9, %ymm12
|
||||
|
||||
/* x^2 */
|
||||
/* x^2 */
|
||||
vmulps %ymm3, %ymm3, %ymm7
|
||||
vcmplt_oqps %ymm3, %ymm6, %ymm8
|
||||
|
||||
/* SQ ~ -2*sqrt(Y) */
|
||||
/* SQ ~ -2*sqrt(Y) */
|
||||
vcmplt_oqps SmallNorm+__svml_sasin_data_internal(%rip), %ymm12, %ymm10
|
||||
vminps %ymm12, %ymm7, %ymm1
|
||||
vaddps %ymm12, %ymm12, %ymm15
|
||||
@ -77,7 +76,7 @@ ENTRY(_ZGVdN8v_asinf_avx2)
|
||||
vfmadd213ps poly_coeff+96+__svml_sasin_data_internal(%rip), %ymm1, %ymm7
|
||||
vmovmskps %ymm8, %edx
|
||||
|
||||
/* polynomial */
|
||||
/* polynomial */
|
||||
vmovups poly_coeff+__svml_sasin_data_internal(%rip), %ymm8
|
||||
vandnps %ymm11, %ymm10, %ymm13
|
||||
vmulps %ymm13, %ymm13, %ymm14
|
||||
@ -98,11 +97,11 @@ ENTRY(_ZGVdN8v_asinf_avx2)
|
||||
vxorps %ymm2, %ymm10, %ymm0
|
||||
testl %edx, %edx
|
||||
|
||||
/* Go to special inputs processing branch */
|
||||
/* Go to special inputs processing branch */
|
||||
jne L(SPECIAL_VALUES_BRANCH)
|
||||
# LOE rbx r12 r13 r14 r15 edx ymm0 ymm4
|
||||
|
||||
/* Restore registers
|
||||
/* Restore registers
|
||||
* and exit the function
|
||||
*/
|
||||
|
||||
@ -115,7 +114,7 @@ L(EXIT):
|
||||
cfi_def_cfa(6, 16)
|
||||
cfi_offset(6, -16)
|
||||
|
||||
/* Branch to process
|
||||
/* Branch to process
|
||||
* special inputs
|
||||
*/
|
||||
|
||||
@ -141,18 +140,18 @@ L(SPECIAL_VALUES_BRANCH):
|
||||
.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
|
||||
/* Range mask
|
||||
* bits check
|
||||
*/
|
||||
|
||||
L(RANGEMASK_CHECK):
|
||||
btl %r12d, %r13d
|
||||
|
||||
/* Call scalar math function */
|
||||
/* Call scalar math function */
|
||||
jc L(SCALAR_MATH_CALL)
|
||||
# LOE rbx r15 r12d r13d
|
||||
|
||||
/* Special inputs
|
||||
/* Special inputs
|
||||
* processing loop
|
||||
*/
|
||||
|
||||
@ -160,7 +159,7 @@ L(SPECIAL_VALUES_LOOP):
|
||||
incl %r12d
|
||||
cmpl $8, %r12d
|
||||
|
||||
/* Check bits in range mask */
|
||||
/* Check bits in range mask */
|
||||
jl L(RANGEMASK_CHECK)
|
||||
# LOE rbx r15 r12d r13d
|
||||
|
||||
@ -172,7 +171,7 @@ L(SPECIAL_VALUES_LOOP):
|
||||
cfi_restore(14)
|
||||
vmovups 64(%rsp), %ymm0
|
||||
|
||||
/* Go to exit */
|
||||
/* 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
|
||||
@ -182,19 +181,19 @@ L(SPECIAL_VALUES_LOOP):
|
||||
.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
|
||||
/* Scalar math fucntion call
|
||||
* to process special input
|
||||
*/
|
||||
|
||||
L(SCALAR_MATH_CALL):
|
||||
movl %r12d, %r14d
|
||||
movss 32(%rsp,%r14,4), %xmm0
|
||||
movss 32(%rsp, %r14, 4), %xmm0
|
||||
call asinf@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 */
|
||||
/* Process special inputs in loop */
|
||||
jmp L(SPECIAL_VALUES_LOOP)
|
||||
# LOE rbx r15 r12d r13d
|
||||
END(_ZGVdN8v_asinf_avx2)
|
||||
@ -216,34 +215,34 @@ typedef struct {
|
||||
} __svml_sasin_data_internal;
|
||||
#endif
|
||||
__svml_sasin_data_internal:
|
||||
/*== AbsMask ==*/
|
||||
/* AbsMask */
|
||||
.long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
|
||||
/*== OneHalf ==*/
|
||||
/* OneHalf */
|
||||
.align 32
|
||||
.long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000
|
||||
/*== SmallNorm ==*/
|
||||
/* SmallNorm */
|
||||
.align 32
|
||||
.long 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000
|
||||
/*== One ==*/
|
||||
/* One */
|
||||
.align 32
|
||||
.long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
|
||||
/*== Two ==*/
|
||||
/* Two */
|
||||
.align 32
|
||||
.long 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000
|
||||
/*== sqrt_coeff[2] ==*/
|
||||
/* sqrt_coeff[2] */
|
||||
.align 32
|
||||
.long 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004 /* sqrt_coeff2 */
|
||||
.long 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001 /* sqrt_coeff1 */
|
||||
/*== poly_coeff[5] ==*/
|
||||
/* poly_coeff[5] */
|
||||
.align 32
|
||||
.long 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07 /* poly_coeff5 */
|
||||
.long 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B /* poly_coeff4 */
|
||||
.long 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4 /* poly_coeff3 */
|
||||
.long 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12 /* poly_coeff2 */
|
||||
.long 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF /* poly_coeff1 */
|
||||
/*== Pi2H ==*/
|
||||
/* Pi2H */
|
||||
.align 32
|
||||
.long 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB
|
||||
.align 32
|
||||
.type __svml_sasin_data_internal,@object
|
||||
.size __svml_sasin_data_internal,.-__svml_sasin_data_internal
|
||||
.type __svml_sasin_data_internal, @object
|
||||
.size __svml_sasin_data_internal, .-__svml_sasin_data_internal
|
||||
|
||||
Loading…
Reference in New Issue
Block a user