x86_64: Fix svml_s_log10f16_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 2022-03-07 10:47:13 -08:00
parent 2682b27200
commit 602e584f32
1 changed files with 169 additions and 170 deletions

View File

@ -38,8 +38,7 @@
#include <sysdep.h>
.text
.section .text.exex512,"ax",@progbits
.section .text.exex512, "ax", @progbits
ENTRY(_ZGVeN16v_log10f_skx)
pushq %rbp
cfi_def_cfa_offset(16)
@ -61,7 +60,7 @@ ENTRY(_ZGVeN16v_log10f_skx)
vpermps coeff2+__svml_slog10_data_internal_avx512(%rip), %zmm7, %zmm4
vpermps coeff1+__svml_slog10_data_internal_avx512(%rip), %zmm7, %zmm8
/* x<=0? */
/* x<=0? */
vfpclassps $94, %zmm0, %k0
vfmadd213ps {rn-sae}, %zmm2, %zmm11, %zmm1
vmulps {rn-sae}, %zmm10, %zmm9, %zmm12
@ -71,11 +70,11 @@ ENTRY(_ZGVeN16v_log10f_skx)
vfmadd213ps {rn-sae}, %zmm12, %zmm11, %zmm1
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
/* Restore registers
/* Restore registers
* and exit the function
*/
@ -89,7 +88,7 @@ L(EXIT):
cfi_def_cfa(6, 16)
cfi_offset(6, -16)
/* Branch to process
/* Branch to process
* special inputs
*/
@ -115,18 +114,18 @@ L(SPECIAL_VALUES_BRANCH):
.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 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
*/
@ -134,7 +133,7 @@ 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
@ -146,7 +145,7 @@ L(SPECIAL_VALUES_LOOP):
cfi_restore(14)
vmovups 128(%rsp), %zmm1
/* 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: -176; DW_OP_plus) */
.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22
@ -156,19 +155,19 @@ L(SPECIAL_VALUES_LOOP):
.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 zmm1
/* 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 64(%rsp, %r14, 4), %xmm0
call log10f@PLT
# LOE rbx r14 r15 r12d r13d xmm0
movss %xmm0, 128(%rsp,%r14,4)
movss %xmm0, 128(%rsp, %r14, 4)
/* Process special inputs in loop */
/* Process special inputs in loop */
jmp L(SPECIAL_VALUES_LOOP)
# LOE rbx r15 r12d r13d
END(_ZGVeN16v_log10f_skx)
@ -185,10 +184,10 @@ typedef struct {
__declspec(align(64)) VUINT32 coeff2[16][1];
__declspec(align(64)) VUINT32 coeff1[16][1];
__declspec(align(64)) VUINT32 L2[16][1];
} __svml_slog10_data_internal_avx512;
} __svml_slog10_data_internal_avx512;
#endif
__svml_slog10_data_internal_avx512:
/*== One ==*/
/* One */
.long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
// c4
.align 64
@ -230,9 +229,9 @@ __svml_slog10_data_internal_avx512:
.long 0x3ede4967, 0x3ede5490
.long 0x3ede597f, 0x3ede5b50
.long 0x3ede5bca, 0x3ede5bd9
/*== L2 ==*/
/* L2 */
.align 64
.long 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b
.align 64
.type __svml_slog10_data_internal_avx512,@object
.size __svml_slog10_data_internal_avx512,.-__svml_slog10_data_internal_avx512
.type __svml_slog10_data_internal_avx512, @object
.size __svml_slog10_data_internal_avx512, .-__svml_slog10_data_internal_avx512