mirror/glibc
2
0
Fork 0
mirror of git://sourceware.org/git/glibc.git synced 2024-12-21 04:31:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

x86_64: Fix svml_s_hypotf16_core_avx512.S code formatting

Browse Source 
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 2022-03-07 10:47:13 -08:00
parent c68b8135ff
commit 075dd8a017
1 changed files with 125 additions and 127 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
sysdeps/x86_64/fpu/multiarch/svml_s_hypotf16_core_avx512.S
View File

@ -63,7 +63,7 @@
* result = s - h * d
*
* EP version of the function can be implemented as y[i]=sqrt(a[i]^2+b[i]^2)
* with all intermediate operations done in target precision for i=1,..,n.
* with all intermediate operations done in target precision for i=1, .., n.
* It can return result y[i]=0 in case a[i]^2 and b[i]^2 underflow in target
* precision (for some i). It can return result y[i]=NAN in case
* a[i]^2+b[i]^2 overflow in target precision, for some i. It can return
@ -80,8 +80,7 @@
#include <sysdep.h>
.text
.section .text.exex512,"ax",@progbits
.section .text.exex512, "ax", @progbits
ENTRY(_ZGVeN16vv_hypotf_skx)
pushq %rbp
cfi_def_cfa_offset(16)
@ -105,17 +104,17 @@ ENTRY(_ZGVeN16vv_hypotf_skx)
vfnmadd231ps {rn-sae}, %zmm9, %zmm9, %zmm2
vfmadd213ps {rn-sae}, %zmm9, %zmm8, %zmm2
/*
/*
* VSCALEF( S, _VRES1, _VRES1, sExp );
* The end of implementation
*/
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 zmm0 zmm1 zmm2
/* Restore registers
/* Restore registers
* and exit the function
*/
@ -129,7 +128,7 @@ L(EXIT):
cfi_def_cfa(6, 16)
cfi_offset(6, -16)
/* Branch to process
/* Branch to process
* special inputs
*/
@ -156,18 +155,18 @@ L(SPECIAL_VALUES_BRANCH):
.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x00, 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
*/
@ -175,7 +174,7 @@ L(SPECIAL_VALUES_LOOP):
incl %r12d
cmpl $16, %r12d
/* Check bits in range mask */
/* Check bits in range mask */
jl L(RANGEMASK_CHECK)
# LOE rbx r15 r12d r13d
@ -187,7 +186,7 @@ L(SPECIAL_VALUES_LOOP):
cfi_restore(14)
vmovups 192(%rsp), %zmm2
/* Go to exit */
/* Go to 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: -240; DW_OP_plus) */
.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x10, 0xff, 0xff, 0xff, 0x22
@ -197,20 +196,20 @@ L(SPECIAL_VALUES_LOOP):
.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x00, 0xff, 0xff, 0xff, 0x22
# LOE rbx r12 r13 r14 r15 zmm2
/* Scalar math fucntion call
/* Scalar math fucntion call
* to process special input
*/
L(SCALAR_MATH_CALL):
movl %r12d, %r14d
movss 64(%rsp,%r14,4), %xmm0
movss 128(%rsp,%r14,4), %xmm1
movss 64(%rsp, %r14, 4), %xmm0
movss 128(%rsp, %r14, 4), %xmm1
call hypotf@PLT
# LOE rbx r14 r15 r12d r13d xmm0
movss %xmm0, 192(%rsp,%r14,4)
movss %xmm0, 192(%rsp, %r14, 4)
/* Process special inputs in loop */
/* Process special inputs in loop */
jmp L(SPECIAL_VALUES_LOOP)
# LOE rbx r15 r12d r13d
END(_ZGVeN16vv_hypotf_skx)
@ -220,8 +219,7 @@ END(_ZGVeN16vv_hypotf_skx)
#ifdef __svml_shypot_data_internal_typedef
typedef unsigned int VUINT32;
typedef struct
{
typedef struct {
__declspec(align(64)) VUINT32 _sAbsMask[16][1];
__declspec(align(64)) VUINT32 _sHalf[16][1];
__declspec(align(64)) VUINT32 _iExpBound[16][1];
@ -235,5 +233,5 @@ __svml_shypot_data_internal:
.align 64
.long 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000, 0x427C0000 /* _iExpBound */
.align 64
.type __svml_shypot_data_internal,@object
.size __svml_shypot_data_internal,.-__svml_shypot_data_internal
.type __svml_shypot_data_internal, @object
.size __svml_shypot_data_internal, .-__svml_shypot_data_internal