mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-27 05:00:15 +00:00
x86_64: Fix svml_s_exp2f4_core_sse4.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:
parent
eb927a26fa
commit
ac11206db3
@ -22,7 +22,7 @@
|
||||
* exp2(x) = 2^n * T[j] * (1 + P(y))
|
||||
* where
|
||||
* x = m*(1/K) + y, y in [-1/K..1/K]
|
||||
* m = n*K + j, m,n,j - signed integer, j in [-K/2..K/2]
|
||||
* m = n*K + j, m, n,j - signed integer, j in [-K/2..K/2]
|
||||
*
|
||||
* values of 2^j/K are tabulated
|
||||
*
|
||||
@ -56,31 +56,30 @@
|
||||
|
||||
#include <sysdep.h>
|
||||
|
||||
.text
|
||||
.section .text.sse4,"ax",@progbits
|
||||
.section .text.sse4, "ax", @progbits
|
||||
ENTRY(_ZGVbN4v_exp2f_sse4)
|
||||
subq $72, %rsp
|
||||
cfi_def_cfa_offset(80)
|
||||
|
||||
/* Check for overflow\underflow */
|
||||
/* Check for overflow\underflow */
|
||||
movups __svml_sexp2_data_internal(%rip), %xmm1
|
||||
|
||||
/* Implementation */
|
||||
/* Implementation */
|
||||
movaps %xmm1, %xmm5
|
||||
|
||||
/* Polynomial */
|
||||
/* Polynomial */
|
||||
movups _sPC6+__svml_sexp2_data_internal(%rip), %xmm4
|
||||
addps %xmm0, %xmm5
|
||||
movaps %xmm5, %xmm3
|
||||
|
||||
/* 2^N */
|
||||
/* 2^N */
|
||||
pslld $23, %xmm5
|
||||
|
||||
/* Check for overflow\underflow */
|
||||
/* Check for overflow\underflow */
|
||||
movdqu _iAbsMask+__svml_sexp2_data_internal(%rip), %xmm2
|
||||
subps %xmm1, %xmm3
|
||||
|
||||
/* R */
|
||||
/* R */
|
||||
movaps %xmm0, %xmm1
|
||||
pand %xmm0, %xmm2
|
||||
pcmpgtd _iDomainRange+__svml_sexp2_data_internal(%rip), %xmm2
|
||||
@ -99,15 +98,15 @@ ENTRY(_ZGVbN4v_exp2f_sse4)
|
||||
mulps %xmm4, %xmm1
|
||||
addps _sPC0+__svml_sexp2_data_internal(%rip), %xmm1
|
||||
|
||||
/* Reconstruction */
|
||||
/* Reconstruction */
|
||||
paddd %xmm5, %xmm1
|
||||
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
|
||||
|
||||
/* Restore registers
|
||||
/* Restore registers
|
||||
* and exit the function
|
||||
*/
|
||||
|
||||
@ -118,7 +117,7 @@ L(EXIT):
|
||||
ret
|
||||
cfi_def_cfa_offset(80)
|
||||
|
||||
/* Branch to process
|
||||
/* Branch to process
|
||||
* special inputs
|
||||
*/
|
||||
|
||||
@ -138,18 +137,18 @@ L(SPECIAL_VALUES_BRANCH):
|
||||
cfi_offset(14, -80)
|
||||
# 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
|
||||
*/
|
||||
|
||||
@ -157,7 +156,7 @@ 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
|
||||
|
||||
@ -169,26 +168,26 @@ L(SPECIAL_VALUES_LOOP):
|
||||
cfi_restore(14)
|
||||
movups 48(%rsp), %xmm1
|
||||
|
||||
/* Go to exit */
|
||||
/* Go to exit */
|
||||
jmp L(EXIT)
|
||||
cfi_offset(12, -64)
|
||||
cfi_offset(13, -72)
|
||||
cfi_offset(14, -80)
|
||||
# LOE rbx rbp r12 r13 r14 r15 xmm1
|
||||
|
||||
/* 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 exp2f@PLT
|
||||
# LOE rbx rbp r14 r15 r12d r13d xmm0
|
||||
|
||||
movss %xmm0, 48(%rsp,%r14,4)
|
||||
movss %xmm0, 48(%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(_ZGVbN4v_exp2f_sse4)
|
||||
@ -198,8 +197,7 @@ END(_ZGVbN4v_exp2f_sse4)
|
||||
|
||||
#ifdef __svml_sexp2_data_internal_typedef
|
||||
typedef unsigned int VUINT32;
|
||||
typedef struct
|
||||
{
|
||||
typedef struct {
|
||||
__declspec(align(16)) VUINT32 _sShifter[4][1];
|
||||
__declspec(align(16)) VUINT32 _sPC0[4][1];
|
||||
__declspec(align(16)) VUINT32 _sPC1[4][1];
|
||||
@ -234,5 +232,5 @@ __svml_sexp2_data_internal:
|
||||
.align 16
|
||||
.long 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000 /* _iDomainRange=126.0 */
|
||||
.align 16
|
||||
.type __svml_sexp2_data_internal,@object
|
||||
.size __svml_sexp2_data_internal,.-__svml_sexp2_data_internal
|
||||
.type __svml_sexp2_data_internal, @object
|
||||
.size __svml_sexp2_data_internal, .-__svml_sexp2_data_internal
|
||||
|
Loading…
Reference in New Issue
Block a user