AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-11-22 13:00:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

x86_64: Fix svml_s_hypotf4_core_sse4.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 075dd8a017
commit 214e4f0c20
1 changed files with 145 additions and 147 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
sysdeps/x86_64/fpu/multiarch/svml_s_hypotf4_core_sse4.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
@ -82,13 +82,12 @@
#include <sysdep.h>
.text
.section .text.sse4,"ax",@progbits
.section .text.sse4, "ax", @progbits
ENTRY(_ZGVbN4vv_hypotf_sse4)
subq $88, %rsp
cfi_def_cfa_offset(96)
/*
/*
* Implementation
* Multiprecision branch for _HA_ only
* No multiprecision branch for _LA_
@ -99,7 +98,7 @@ ENTRY(_ZGVbN4vv_hypotf_sse4)
mulps %xmm0, %xmm8
mulps %xmm1, %xmm2
/*
/*
* Variables
* Defines
* Constants loading
@ -107,10 +106,10 @@ ENTRY(_ZGVbN4vv_hypotf_sse4)
movups _sHalf+__svml_shypot_data_internal(%rip), %xmm5
addps %xmm2, %xmm8
/* _s0 ~ 1.0/sqrt(_z) */
/* _s0 ~ 1.0/sqrt(_z) */
rsqrtps %xmm8, %xmm10
/* First iteration */
/* First iteration */
movaps %xmm10, %xmm2
movaps %xmm8, %xmm3
mulps %xmm8, %xmm2
@ -118,11 +117,11 @@ ENTRY(_ZGVbN4vv_hypotf_sse4)
movaps %xmm2, %xmm6
mulps %xmm10, %xmm6
/* Check _z exponent to be withing borders [1E3 ; 60A] else goto Callout */
/* Check _z exponent to be withing borders [1E3 ; 60A] else goto Callout */
movdqu _LowBoundary+__svml_shypot_data_internal(%rip), %xmm4
subps %xmm6, %xmm5
/* Second iteration */
/* Second iteration */
movaps %xmm5, %xmm7
pcmpgtd %xmm8, %xmm4
mulps %xmm2, %xmm5
@ -130,7 +129,7 @@ ENTRY(_ZGVbN4vv_hypotf_sse4)
addps %xmm5, %xmm2
addps %xmm7, %xmm10
/* Finish second iteration in native precision for _LA_ */
/* Finish second iteration in native precision for _LA_ */
movaps %xmm2, %xmm9
mulps %xmm2, %xmm9
pcmpgtd _HighBoundary+__svml_shypot_data_internal(%rip), %xmm3
@ -140,14 +139,14 @@ ENTRY(_ZGVbN4vv_hypotf_sse4)
movmskps %xmm4, %edx
subps %xmm10, %xmm2
/* The end of implementation */
/* 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 rbp r12 r13 r14 r15 edx xmm0 xmm1 xmm2
/* Restore registers
/* Restore registers
* and exit the function
*/
@ -158,7 +157,7 @@ L(EXIT):
ret
cfi_def_cfa_offset(96)
/* Branch to process
/* Branch to process
* special inputs
*/
@ -179,18 +178,18 @@ L(SPECIAL_VALUES_BRANCH):
cfi_offset(14, -96)
# LOE rbx rbp 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 rbp r15 r12d r13d
/* Special inputs
/* Special inputs
* processing loop
*/
@ -198,7 +197,7 @@ L(SPECIAL_VALUES_LOOP):
incl %r12d
cmpl $4, %r12d
/* Check bits in range mask */
/* Check bits in range mask */
jl L(RANGEMASK_CHECK)
# LOE rbx rbp r15 r12d r13d
@ -210,27 +209,27 @@ L(SPECIAL_VALUES_LOOP):
cfi_restore(14)
movups 64(%rsp), %xmm2
/* Go to exit */
/* Go to exit */
jmp L(EXIT)
cfi_offset(12, -80)
cfi_offset(13, -88)
cfi_offset(14, -96)
# LOE rbx rbp r12 r13 r14 r15 xmm2
/* 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 48(%rsp,%r14,4), %xmm1
movss 32(%rsp, %r14, 4), %xmm0
movss 48(%rsp, %r14, 4), %xmm1
call hypotf@PLT
# LOE rbx rbp 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 rbp r15 r12d r13d
END(_ZGVbN4vv_hypotf_sse4)
@ -240,8 +239,7 @@ END(_ZGVbN4vv_hypotf_sse4)
#ifdef __svml_shypot_data_internal_typedef
typedef unsigned int VUINT32;
typedef struct
{
typedef struct {
__declspec(align(16)) VUINT32 _sHiLoMask[4][1];
__declspec(align(16)) VUINT32 _sAbsMask[4][1];
__declspec(align(16)) VUINT32 _sHalf[4][1];
@ -261,5 +259,5 @@ __svml_shypot_data_internal:
.align 16
.long 0x60A00000, 0x60A00000, 0x60A00000, 0x60A00000 /* _HighBoundary */
.align 16
.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