x86_64: Fix svml_s_log10f8_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 2022-03-07 10:47:13 -08:00
parent fda62f29aa
commit eb20f196bb

View File

@ -41,8 +41,7 @@
#include <sysdep.h>
.text
.section .text.avx2,"ax",@progbits
.section .text.avx2, "ax", @progbits
ENTRY(_ZGVdN8v_log10f_avx2)
pushq %rbp
cfi_def_cfa_offset(16)
@ -52,7 +51,7 @@ ENTRY(_ZGVdN8v_log10f_avx2)
andq $-32, %rsp
subq $96, %rsp
/* reduction: compute r,n */
/* reduction: compute r, n */
vmovups iBrkValue+__svml_slog10_data_internal(%rip), %ymm4
vmovups sPoly+__svml_slog10_data_internal(%rip), %ymm15
vmovups sPoly+64+__svml_slog10_data_internal(%rip), %ymm9
@ -79,16 +78,16 @@ ENTRY(_ZGVdN8v_log10f_avx2)
vfmadd213ps %ymm14, %ymm13, %ymm15
vorps %ymm6, %ymm5, %ymm7
/* combine and get argument value range mask */
/* combine and get argument value range mask */
vmovmskps %ymm7, %edx
vfmadd132ps L2H+__svml_slog10_data_internal(%rip), %ymm15, %ymm1
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 ymm1
/* Restore registers
/* Restore registers
* and exit the function
*/
@ -102,7 +101,7 @@ L(EXIT):
cfi_def_cfa(6, 16)
cfi_offset(6, -16)
/* Branch to process
/* Branch to process
* special inputs
*/
@ -128,18 +127,18 @@ 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
*/
@ -147,7 +146,7 @@ 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
@ -159,7 +158,7 @@ L(SPECIAL_VALUES_LOOP):
cfi_restore(14)
vmovups 64(%rsp), %ymm1
/* 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
@ -169,19 +168,19 @@ 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 ymm1
/* 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 log10f@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_log10f_avx2)
@ -204,27 +203,27 @@ typedef struct {
} __svml_slog10_data_internal;
#endif
__svml_slog10_data_internal:
/*== MinNorm ==*/
/* MinNorm */
.long 0x00800000, 0x00800000, 0x00800000, 0x00800000, 0x00800000, 0x00800000, 0x00800000, 0x00800000
/*== MaxNorm ==*/
/* MaxNorm */
.align 32
.long 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff, 0x7f7fffff
/*== L2H ==*/
/* L2H */
.align 32
.long 0x3e9a2100, 0x3e9a2100, 0x3e9a2100, 0x3e9a2100, 0x3e9a2100, 0x3e9a2100, 0x3e9a2100, 0x3e9a2100
/*== L2L ==*/
/* L2L */
.align 32
.long 0xb64AF600, 0xb64AF600, 0xb64AF600, 0xb64AF600, 0xb64AF600, 0xb64AF600, 0xb64AF600, 0xb64AF600
/*== iBrkValue = SP 2/3 ==*/
/* iBrkValue = SP 2/3 */
.align 32
.long 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab
/*== iOffExpoMask = SP significand mask ==*/
/* iOffExpoMask = SP significand mask */
.align 32
.long 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff
/*== sOne = SP 1.0 ==*/
/* sOne = SP 1.0 */
.align 32
.long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
/*== spoly[9] ==*/
/* spoly[9] */
.align 32
.long 0x3d8063B4, 0x3d8063B4, 0x3d8063B4, 0x3d8063B4, 0x3d8063B4, 0x3d8063B4, 0x3d8063B4, 0x3d8063B4 /* coeff9 */
.long 0xbd890073, 0xbd890073, 0xbd890073, 0xbd890073, 0xbd890073, 0xbd890073, 0xbd890073, 0xbd890073 /* coeff8 */
@ -235,9 +234,9 @@ __svml_slog10_data_internal:
.long 0x3e143CE5, 0x3e143CE5, 0x3e143CE5, 0x3e143CE5, 0x3e143CE5, 0x3e143CE5, 0x3e143CE5, 0x3e143CE5 /* coeff3 */
.long 0xbe5E5BC5, 0xbe5E5BC5, 0xbe5E5BC5, 0xbe5E5BC5, 0xbe5E5BC5, 0xbe5E5BC5, 0xbe5E5BC5, 0xbe5E5BC5 /* coeff2 */
.long 0x3eDE5BD9, 0x3eDE5BD9, 0x3eDE5BD9, 0x3eDE5BD9, 0x3eDE5BD9, 0x3eDE5BD9, 0x3eDE5BD9, 0x3eDE5BD9 /* coeff1 */
/*== L2 ==*/
/* L2 */
.align 32
.long 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b, 0x3e9a209b
.align 32
.type __svml_slog10_data_internal,@object
.size __svml_slog10_data_internal,.-__svml_slog10_data_internal
.type __svml_slog10_data_internal, @object
.size __svml_slog10_data_internal, .-__svml_slog10_data_internal