public inbox for glibc-cvs@sourceware.org
help / color / mirror / Atom feed
* [glibc] x86_64: Fix svml_s_expm1f4_core_sse4.S code formatting
@ 2022-03-08 5:50 Sunil Pandey
0 siblings, 0 replies; only message in thread
From: Sunil Pandey @ 2022-03-08 5:50 UTC (permalink / raw)
To: glibc-cvs
https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=855ec9df67bbdbd60f3ca82edf50c1fbcaea63eb
commit 855ec9df67bbdbd60f3ca82edf50c1fbcaea63eb
Author: Sunil K Pandey <skpgkp2@gmail.com>
Date: Mon Mar 7 10:47:13 2022 -0800
x86_64: Fix svml_s_expm1f4_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>
Diff:
---
.../fpu/multiarch/svml_s_expm1f4_core_sse4.S | 597 ++++++++++-----------
1 file changed, 298 insertions(+), 299 deletions(-)
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f4_core_sse4.S b/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f4_core_sse4.S
index 6abad6c2c4..c29335d0d9 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f4_core_sse4.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_expm1f4_core_sse4.S
@@ -28,331 +28,330 @@
/* Offsets for data table __svml_sexpm1_data_internal
*/
-#define Expm1_HA_table 0
-#define poly_coeff 512
-#define Log2e 576
-#define L2H 592
-#define L2L 608
-#define ExpAddConst 624
-#define IndexMask 640
-#define ExpMask 656
-#define MOne 672
-#define AbsMask 688
-#define Threshold 704
-#define L2 720
+#define Expm1_HA_table 0
+#define poly_coeff 512
+#define Log2e 576
+#define L2H 592
+#define L2L 608
+#define ExpAddConst 624
+#define IndexMask 640
+#define ExpMask 656
+#define MOne 672
+#define AbsMask 688
+#define Threshold 704
+#define L2 720
#include <sysdep.h>
- .text
- .section .text.sse4,"ax",@progbits
+ .section .text.sse4, "ax", @progbits
ENTRY(_ZGVbN4v_expm1f_sse4)
- pushq %rbp
- cfi_def_cfa_offset(16)
- movq %rsp, %rbp
- cfi_def_cfa(6, 16)
- cfi_offset(6, -16)
- andq $-32, %rsp
- subq $64, %rsp
- movaps %xmm0, %xmm4
- movups Log2e+__svml_sexpm1_data_internal(%rip), %xmm9
- lea __svml_sexpm1_data_internal(%rip), %r8
- mulps %xmm0, %xmm9
- movups .FLT_10(%rip), %xmm5
- movups ExpAddConst+__svml_sexpm1_data_internal(%rip), %xmm2
- addps %xmm5, %xmm9
-
-/* argument reduction */
- movups L2H+__svml_sexpm1_data_internal(%rip), %xmm6
- subps %xmm5, %xmm9
- mulps %xmm9, %xmm6
- addps %xmm9, %xmm2
-
-/* table lookup */
- movdqu IndexMask+__svml_sexpm1_data_internal(%rip), %xmm12
- subps %xmm6, %xmm4
- pand %xmm2, %xmm12
- movups L2L+__svml_sexpm1_data_internal(%rip), %xmm7
- movups AbsMask+__svml_sexpm1_data_internal(%rip), %xmm3
- pshufd $1, %xmm12, %xmm10
- movaps %xmm3, %xmm8
- mulps %xmm9, %xmm7
- andps %xmm0, %xmm8
- cmpnleps Threshold+__svml_sexpm1_data_internal(%rip), %xmm8
- movd %xmm12, %edx
- subps %xmm7, %xmm4
- movd %xmm10, %ecx
- movmskps %xmm8, %eax
- pshufd $2, %xmm12, %xmm11
- movaps %xmm4, %xmm7
- pshufd $3, %xmm12, %xmm13
- andnps %xmm0, %xmm3
- movd %xmm11, %esi
- movd %xmm13, %edi
-
-/* polynomial */
- movups poly_coeff+__svml_sexpm1_data_internal(%rip), %xmm8
- movdqu ExpMask+__svml_sexpm1_data_internal(%rip), %xmm6
- movslq %edx, %rdx
- pand %xmm6, %xmm2
- movslq %ecx, %rcx
- pslld $14, %xmm2
- movslq %esi, %rsi
- movslq %edi, %rdi
- movq (%r8,%rdx), %xmm1
- movq (%r8,%rcx), %xmm14
- movq (%r8,%rsi), %xmm5
- movq (%r8,%rdi), %xmm15
- unpcklps %xmm14, %xmm1
- mulps %xmm4, %xmm8
- movaps %xmm1, %xmm10
- mulps %xmm4, %xmm7
- addps poly_coeff+16+__svml_sexpm1_data_internal(%rip), %xmm8
- unpcklps %xmm15, %xmm5
- movlhps %xmm5, %xmm10
- shufps $238, %xmm5, %xmm1
- orps %xmm2, %xmm10
-
-/* T-1 */
- movups MOne+__svml_sexpm1_data_internal(%rip), %xmm9
- mulps %xmm2, %xmm1
- addps %xmm9, %xmm10
- mulps %xmm7, %xmm8
- addps %xmm1, %xmm10
- addps %xmm8, %xmm4
- movaps %xmm10, %xmm1
- subps %xmm9, %xmm1
- mulps %xmm1, %xmm4
- addps %xmm4, %xmm10
- orps %xmm3, %xmm10
- testl %eax, %eax
-
-/* Go to special inputs processing branch */
- jne L(SPECIAL_VALUES_BRANCH)
- # LOE rbx r12 r13 r14 r15 eax xmm0 xmm10
-
-/* Restore registers
- * and exit the function
- */
+ pushq %rbp
+ cfi_def_cfa_offset(16)
+ movq %rsp, %rbp
+ cfi_def_cfa(6, 16)
+ cfi_offset(6, -16)
+ andq $-32, %rsp
+ subq $64, %rsp
+ movaps %xmm0, %xmm4
+ movups Log2e+__svml_sexpm1_data_internal(%rip), %xmm9
+ lea __svml_sexpm1_data_internal(%rip), %r8
+ mulps %xmm0, %xmm9
+ movups .FLT_10(%rip), %xmm5
+ movups ExpAddConst+__svml_sexpm1_data_internal(%rip), %xmm2
+ addps %xmm5, %xmm9
+
+ /* argument reduction */
+ movups L2H+__svml_sexpm1_data_internal(%rip), %xmm6
+ subps %xmm5, %xmm9
+ mulps %xmm9, %xmm6
+ addps %xmm9, %xmm2
+
+ /* table lookup */
+ movdqu IndexMask+__svml_sexpm1_data_internal(%rip), %xmm12
+ subps %xmm6, %xmm4
+ pand %xmm2, %xmm12
+ movups L2L+__svml_sexpm1_data_internal(%rip), %xmm7
+ movups AbsMask+__svml_sexpm1_data_internal(%rip), %xmm3
+ pshufd $1, %xmm12, %xmm10
+ movaps %xmm3, %xmm8
+ mulps %xmm9, %xmm7
+ andps %xmm0, %xmm8
+ cmpnleps Threshold+__svml_sexpm1_data_internal(%rip), %xmm8
+ movd %xmm12, %edx
+ subps %xmm7, %xmm4
+ movd %xmm10, %ecx
+ movmskps %xmm8, %eax
+ pshufd $2, %xmm12, %xmm11
+ movaps %xmm4, %xmm7
+ pshufd $3, %xmm12, %xmm13
+ andnps %xmm0, %xmm3
+ movd %xmm11, %esi
+ movd %xmm13, %edi
+
+ /* polynomial */
+ movups poly_coeff+__svml_sexpm1_data_internal(%rip), %xmm8
+ movdqu ExpMask+__svml_sexpm1_data_internal(%rip), %xmm6
+ movslq %edx, %rdx
+ pand %xmm6, %xmm2
+ movslq %ecx, %rcx
+ pslld $14, %xmm2
+ movslq %esi, %rsi
+ movslq %edi, %rdi
+ movq (%r8, %rdx), %xmm1
+ movq (%r8, %rcx), %xmm14
+ movq (%r8, %rsi), %xmm5
+ movq (%r8, %rdi), %xmm15
+ unpcklps %xmm14, %xmm1
+ mulps %xmm4, %xmm8
+ movaps %xmm1, %xmm10
+ mulps %xmm4, %xmm7
+ addps poly_coeff+16+__svml_sexpm1_data_internal(%rip), %xmm8
+ unpcklps %xmm15, %xmm5
+ movlhps %xmm5, %xmm10
+ shufps $238, %xmm5, %xmm1
+ orps %xmm2, %xmm10
+
+ /* T-1 */
+ movups MOne+__svml_sexpm1_data_internal(%rip), %xmm9
+ mulps %xmm2, %xmm1
+ addps %xmm9, %xmm10
+ mulps %xmm7, %xmm8
+ addps %xmm1, %xmm10
+ addps %xmm8, %xmm4
+ movaps %xmm10, %xmm1
+ subps %xmm9, %xmm1
+ mulps %xmm1, %xmm4
+ addps %xmm4, %xmm10
+ orps %xmm3, %xmm10
+ testl %eax, %eax
+
+ /* Go to special inputs processing branch */
+ jne L(SPECIAL_VALUES_BRANCH)
+ # LOE rbx r12 r13 r14 r15 eax xmm0 xmm10
+
+ /* Restore registers
+ * and exit the function
+ */
L(EXIT):
- movaps %xmm10, %xmm0
- movq %rbp, %rsp
- popq %rbp
- cfi_def_cfa(7, 8)
- cfi_restore(6)
- ret
- cfi_def_cfa(6, 16)
- cfi_offset(6, -16)
-
-/* Branch to process
- * special inputs
- */
+ movaps %xmm10, %xmm0
+ movq %rbp, %rsp
+ popq %rbp
+ cfi_def_cfa(7, 8)
+ cfi_restore(6)
+ ret
+ cfi_def_cfa(6, 16)
+ cfi_offset(6, -16)
+
+ /* Branch to process
+ * special inputs
+ */
L(SPECIAL_VALUES_BRANCH):
- movups %xmm0, 32(%rsp)
- movups %xmm10, 48(%rsp)
- # LOE rbx r12 r13 r14 r15 eax
-
- xorl %edx, %edx
- movq %r12, 16(%rsp)
- /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -48; DW_OP_plus) */
- .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xd0, 0xff, 0xff, 0xff, 0x22
- movl %edx, %r12d
- movq %r13, 8(%rsp)
- /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -56; DW_OP_plus) */
- .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xc8, 0xff, 0xff, 0xff, 0x22
- movl %eax, %r13d
- movq %r14, (%rsp)
- /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -64; DW_OP_plus) */
- .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x22
- # LOE rbx r15 r12d r13d
-
-/* Range mask
- * bits check
- */
+ movups %xmm0, 32(%rsp)
+ movups %xmm10, 48(%rsp)
+ # LOE rbx r12 r13 r14 r15 eax
+
+ xorl %edx, %edx
+ movq %r12, 16(%rsp)
+ /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -48; DW_OP_plus) */
+ .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xd0, 0xff, 0xff, 0xff, 0x22
+ movl %edx, %r12d
+ movq %r13, 8(%rsp)
+ /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -56; DW_OP_plus) */
+ .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xc8, 0xff, 0xff, 0xff, 0x22
+ movl %eax, %r13d
+ movq %r14, (%rsp)
+ /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -64; DW_OP_plus) */
+ .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x22
+ # LOE rbx r15 r12d r13d
+
+ /* Range mask
+ * bits check
+ */
L(RANGEMASK_CHECK):
- btl %r12d, %r13d
+ btl %r12d, %r13d
-/* Call scalar math function */
- jc L(SCALAR_MATH_CALL)
- # LOE rbx r15 r12d r13d
+ /* Call scalar math function */
+ jc L(SCALAR_MATH_CALL)
+ # LOE rbx r15 r12d r13d
-/* Special inputs
- * processing loop
- */
+ /* Special inputs
+ * processing loop
+ */
L(SPECIAL_VALUES_LOOP):
- incl %r12d
- cmpl $4, %r12d
-
-/* Check bits in range mask */
- jl L(RANGEMASK_CHECK)
- # LOE rbx r15 r12d r13d
-
- movq 16(%rsp), %r12
- cfi_restore(12)
- movq 8(%rsp), %r13
- cfi_restore(13)
- movq (%rsp), %r14
- cfi_restore(14)
- movups 48(%rsp), %xmm10
-
-/* 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: -48; DW_OP_plus) */
- .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xd0, 0xff, 0xff, 0xff, 0x22
- /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -56; DW_OP_plus) */
- .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xc8, 0xff, 0xff, 0xff, 0x22
- /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -64; DW_OP_plus) */
- .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x22
- # LOE rbx r12 r13 r14 r15 xmm10
-
-/* Scalar math fucntion call
- * to process special input
- */
+ incl %r12d
+ cmpl $4, %r12d
+
+ /* Check bits in range mask */
+ jl L(RANGEMASK_CHECK)
+ # LOE rbx r15 r12d r13d
+
+ movq 16(%rsp), %r12
+ cfi_restore(12)
+ movq 8(%rsp), %r13
+ cfi_restore(13)
+ movq (%rsp), %r14
+ cfi_restore(14)
+ movups 48(%rsp), %xmm10
+
+ /* 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: -48; DW_OP_plus) */
+ .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xd0, 0xff, 0xff, 0xff, 0x22
+ /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -56; DW_OP_plus) */
+ .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xc8, 0xff, 0xff, 0xff, 0x22
+ /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -64; DW_OP_plus) */
+ .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x22
+ # LOE rbx r12 r13 r14 r15 xmm10
+
+ /* Scalar math fucntion call
+ * to process special input
+ */
L(SCALAR_MATH_CALL):
- movl %r12d, %r14d
- movss 32(%rsp,%r14,4), %xmm0
- call expm1f@PLT
- # LOE rbx r14 r15 r12d r13d xmm0
+ movl %r12d, %r14d
+ movss 32(%rsp, %r14, 4), %xmm0
+ call expm1f@PLT
+ # LOE rbx r14 r15 r12d r13d xmm0
- movss %xmm0, 48(%rsp,%r14,4)
+ movss %xmm0, 48(%rsp, %r14, 4)
-/* Process special inputs in loop */
- jmp L(SPECIAL_VALUES_LOOP)
- # LOE rbx r15 r12d r13d
+ /* Process special inputs in loop */
+ jmp L(SPECIAL_VALUES_LOOP)
+ # LOE rbx r15 r12d r13d
END(_ZGVbN4v_expm1f_sse4)
- .section .rodata, "a"
- .align 16
+ .section .rodata, "a"
+ .align 16
#ifdef __svml_sexpm1_data_internal_typedef
typedef unsigned int VUINT32;
typedef struct {
- __declspec(align(16)) VUINT32 Expm1_HA_table[(1<<7)][1];
- __declspec(align(16)) VUINT32 poly_coeff[4][4][1];
- __declspec(align(16)) VUINT32 Log2e[4][1];
- __declspec(align(16)) VUINT32 L2H[4][1];
- __declspec(align(16)) VUINT32 L2L[4][1];
- __declspec(align(16)) VUINT32 ExpAddConst[4][1];
- __declspec(align(16)) VUINT32 IndexMask[4][1];
- __declspec(align(16)) VUINT32 ExpMask[4][1];
- __declspec(align(16)) VUINT32 MOne[4][1];
- __declspec(align(16)) VUINT32 AbsMask[4][1];
- __declspec(align(16)) VUINT32 Threshold[4][1];
- __declspec(align(16)) VUINT32 L2[4][1];
+ __declspec(align(16)) VUINT32 Expm1_HA_table[(1<<7)][1];
+ __declspec(align(16)) VUINT32 poly_coeff[4][4][1];
+ __declspec(align(16)) VUINT32 Log2e[4][1];
+ __declspec(align(16)) VUINT32 L2H[4][1];
+ __declspec(align(16)) VUINT32 L2L[4][1];
+ __declspec(align(16)) VUINT32 ExpAddConst[4][1];
+ __declspec(align(16)) VUINT32 IndexMask[4][1];
+ __declspec(align(16)) VUINT32 ExpMask[4][1];
+ __declspec(align(16)) VUINT32 MOne[4][1];
+ __declspec(align(16)) VUINT32 AbsMask[4][1];
+ __declspec(align(16)) VUINT32 Threshold[4][1];
+ __declspec(align(16)) VUINT32 L2[4][1];
} __svml_sexpm1_data_internal;
#endif
__svml_sexpm1_data_internal:
- /* Expm1_HA_table */
- .long 0x00000000, 0x00000000
- .long 0x00016000, 0x391a3e78
- .long 0x0002d000, 0xb89e59d5
- .long 0x00044000, 0xb93ae78a
- .long 0x0005b000, 0xb9279306
- .long 0x00072000, 0xb79e6961
- .long 0x0008a000, 0xb97e2fee
- .long 0x000a1000, 0x391aaea9
- .long 0x000b9000, 0x39383c7d
- .long 0x000d2000, 0xb9241490
- .long 0x000ea000, 0x39073169
- .long 0x00103000, 0x386e218a
- .long 0x0011c000, 0x38f4dceb
- .long 0x00136000, 0xb93a9a1e
- .long 0x0014f000, 0x391df520
- .long 0x00169000, 0x3905a6e4
- .long 0x00183000, 0x397e0a32
- .long 0x0019e000, 0x370b2641
- .long 0x001b9000, 0xb8b1918b
- .long 0x001d4000, 0xb8132c6a
- .long 0x001ef000, 0x39264c12
- .long 0x0020b000, 0x37221f73
- .long 0x00227000, 0x37060619
- .long 0x00243000, 0x3922b5c1
- .long 0x00260000, 0xb814ab27
- .long 0x0027d000, 0xb89b12c6
- .long 0x0029a000, 0x382d5a75
- .long 0x002b8000, 0xb938c94b
- .long 0x002d6000, 0xb97822b8
- .long 0x002f4000, 0xb910ea53
- .long 0x00312000, 0x38fd6075
- .long 0x00331000, 0x38620955
- .long 0x00350000, 0x391e667f
- .long 0x00370000, 0xb89b8736
- .long 0x00390000, 0xb90a1714
- .long 0x003b0000, 0xb7a54ded
- .long 0x003d1000, 0xb96b8c15
- .long 0x003f1000, 0x397336cf
- .long 0x00413000, 0xb8eccd66
- .long 0x00434000, 0x39599b45
- .long 0x00456000, 0x3965422b
- .long 0x00479000, 0xb8a2cdd5
- .long 0x0049c000, 0xb9484f32
- .long 0x004bf000, 0xb8fac043
- .long 0x004e2000, 0x391182a4
- .long 0x00506000, 0x38ccf6bc
- .long 0x0052b000, 0xb97c4dc2
- .long 0x0054f000, 0x38d6aaf4
- .long 0x00574000, 0x391f995b
- .long 0x0059a000, 0xb8ba8f62
- .long 0x005c0000, 0xb9090d05
- .long 0x005e6000, 0x37f4825e
- .long 0x0060d000, 0xb8c844f5
- .long 0x00634000, 0xb76d1a83
- .long 0x0065c000, 0xb95f2310
- .long 0x00684000, 0xb952b5f8
- .long 0x006ac000, 0x37c6e7dd
- .long 0x006d5000, 0xb7cfe126
- .long 0x006fe000, 0x3917337c
- .long 0x00728000, 0x383b9e2d
- .long 0x00752000, 0x392fa2a5
- .long 0x0077d000, 0x37df730b
- .long 0x007a8000, 0x38ecb6dd
- .long 0x007d4000, 0xb879f986
- /*== poly_coeff[4] ==*/
- .align 16
- .long 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF /* coeff3 */
- .long 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F /* coeff2 */
- /* 32 Byte Padding */
- .zero 32
- /*== Log2e ==*/
- .align 16
- .long 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B
- /*== L2H ==*/
- .align 16
- .long 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000
- /*== L2L ==*/
- .align 16
- .long 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083
- /*== ExpAddConst ==*/
- .align 16
- .long 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00
- /*== IndexMask ==*/
- .align 16
- .long 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8
- /*== ExpMask ==*/
- .align 16
- .long 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00
- /*== MOne ==*/
- .align 16
- .long 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000
- /*== AbsMask ==*/
- .align 16
- .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
- /*== Threshold ==*/
- .align 16
- .long 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B // 86.643394
- /*== L2 ==*/
- .align 16
- .long 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218
- .align 16
- .type __svml_sexpm1_data_internal,@object
- .size __svml_sexpm1_data_internal,.-__svml_sexpm1_data_internal
- .align 16
+ /* Expm1_HA_table */
+ .long 0x00000000, 0x00000000
+ .long 0x00016000, 0x391a3e78
+ .long 0x0002d000, 0xb89e59d5
+ .long 0x00044000, 0xb93ae78a
+ .long 0x0005b000, 0xb9279306
+ .long 0x00072000, 0xb79e6961
+ .long 0x0008a000, 0xb97e2fee
+ .long 0x000a1000, 0x391aaea9
+ .long 0x000b9000, 0x39383c7d
+ .long 0x000d2000, 0xb9241490
+ .long 0x000ea000, 0x39073169
+ .long 0x00103000, 0x386e218a
+ .long 0x0011c000, 0x38f4dceb
+ .long 0x00136000, 0xb93a9a1e
+ .long 0x0014f000, 0x391df520
+ .long 0x00169000, 0x3905a6e4
+ .long 0x00183000, 0x397e0a32
+ .long 0x0019e000, 0x370b2641
+ .long 0x001b9000, 0xb8b1918b
+ .long 0x001d4000, 0xb8132c6a
+ .long 0x001ef000, 0x39264c12
+ .long 0x0020b000, 0x37221f73
+ .long 0x00227000, 0x37060619
+ .long 0x00243000, 0x3922b5c1
+ .long 0x00260000, 0xb814ab27
+ .long 0x0027d000, 0xb89b12c6
+ .long 0x0029a000, 0x382d5a75
+ .long 0x002b8000, 0xb938c94b
+ .long 0x002d6000, 0xb97822b8
+ .long 0x002f4000, 0xb910ea53
+ .long 0x00312000, 0x38fd6075
+ .long 0x00331000, 0x38620955
+ .long 0x00350000, 0x391e667f
+ .long 0x00370000, 0xb89b8736
+ .long 0x00390000, 0xb90a1714
+ .long 0x003b0000, 0xb7a54ded
+ .long 0x003d1000, 0xb96b8c15
+ .long 0x003f1000, 0x397336cf
+ .long 0x00413000, 0xb8eccd66
+ .long 0x00434000, 0x39599b45
+ .long 0x00456000, 0x3965422b
+ .long 0x00479000, 0xb8a2cdd5
+ .long 0x0049c000, 0xb9484f32
+ .long 0x004bf000, 0xb8fac043
+ .long 0x004e2000, 0x391182a4
+ .long 0x00506000, 0x38ccf6bc
+ .long 0x0052b000, 0xb97c4dc2
+ .long 0x0054f000, 0x38d6aaf4
+ .long 0x00574000, 0x391f995b
+ .long 0x0059a000, 0xb8ba8f62
+ .long 0x005c0000, 0xb9090d05
+ .long 0x005e6000, 0x37f4825e
+ .long 0x0060d000, 0xb8c844f5
+ .long 0x00634000, 0xb76d1a83
+ .long 0x0065c000, 0xb95f2310
+ .long 0x00684000, 0xb952b5f8
+ .long 0x006ac000, 0x37c6e7dd
+ .long 0x006d5000, 0xb7cfe126
+ .long 0x006fe000, 0x3917337c
+ .long 0x00728000, 0x383b9e2d
+ .long 0x00752000, 0x392fa2a5
+ .long 0x0077d000, 0x37df730b
+ .long 0x007a8000, 0x38ecb6dd
+ .long 0x007d4000, 0xb879f986
+ /* poly_coeff[4] */
+ .align 16
+ .long 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF, 0x3e2AAABF /* coeff3 */
+ .long 0x3f00000F, 0x3f00000F, 0x3f00000F, 0x3f00000F /* coeff2 */
+ /* 32 Byte Padding */
+ .zero 32
+ /* Log2e */
+ .align 16
+ .long 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B, 0x42B8AA3B
+ /* L2H */
+ .align 16
+ .long 0x3c318000, 0x3c318000, 0x3c318000, 0x3c318000
+ /* L2L */
+ .align 16
+ .long 0xb65e8083, 0xb65e8083, 0xb65e8083, 0xb65e8083
+ /* ExpAddConst */
+ .align 16
+ .long 0x49f0fe00, 0x49f0fe00, 0x49f0fe00, 0x49f0fe00
+ /* IndexMask */
+ .align 16
+ .long 0x000001f8, 0x000001f8, 0x000001f8, 0x000001f8
+ /* ExpMask */
+ .align 16
+ .long 0x0001fe00, 0x0001fe00, 0x0001fe00, 0x0001fe00
+ /* MOne */
+ .align 16
+ .long 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000
+ /* AbsMask */
+ .align 16
+ .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
+ /* Threshold */
+ .align 16
+ .long 0x42AD496B, 0x42AD496B, 0x42AD496B, 0x42AD496B // 86.643394
+ /* L2 */
+ .align 16
+ .long 0x3cb17218, 0x3cb17218, 0x3cb17218, 0x3cb17218
+ .align 16
+ .type __svml_sexpm1_data_internal, @object
+ .size __svml_sexpm1_data_internal, .-__svml_sexpm1_data_internal
+ .align 16
.FLT_10:
- .long 0x4b400000,0x4b400000,0x4b400000,0x4b400000
- .type .FLT_10,@object
- .size .FLT_10,16
+ .long 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000
+ .type .FLT_10, @object
+ .size .FLT_10, 16
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2022-03-08 5:50 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-03-08 5:50 [glibc] x86_64: Fix svml_s_expm1f4_core_sse4.S code formatting Sunil Pandey
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).