From: Sunil K Pandey <skpgkp2@gmail.com>
To: libc-alpha@sourceware.org
Subject: [PATCH 003/126] x86_64: Fix svml_s_acosf8_core_avx2.S code formatting
Date: Mon, 7 Mar 2022 06:59:58 -0800 [thread overview]
Message-ID: <20220307150201.10590-4-skpgkp2@gmail.com> (raw)
In-Reply-To: <20220307150201.10590-1-skpgkp2@gmail.com>
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.
---
.../fpu/multiarch/svml_s_acosf8_core_avx2.S | 411 +++++++++---------
1 file changed, 205 insertions(+), 206 deletions(-)
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_acosf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_acosf8_core_avx2.S
index 94402554ad..bf28a5dd00 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_acosf8_core_avx2.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_acosf8_core_avx2.S
@@ -29,236 +29,235 @@
/* Offsets for data table __svml_sacos_data_internal
*/
-#define SgnBit 0
-#define OneHalf 32
-#define SmallNorm 64
-#define MOne 96
-#define Two 128
-#define sqrt_coeff 160
-#define poly_coeff 224
-#define Pi2H 384
-#define PiH 416
+#define SgnBit 0
+#define OneHalf 32
+#define SmallNorm 64
+#define MOne 96
+#define Two 128
+#define sqrt_coeff 160
+#define poly_coeff 224
+#define Pi2H 384
+#define PiH 416
#include <sysdep.h>
- .text
- .section .text.avx2,"ax",@progbits
+ .section .text.avx2, "ax", @progbits
ENTRY(_ZGVdN8v_acosf_avx2)
- pushq %rbp
- cfi_def_cfa_offset(16)
- movq %rsp, %rbp
- cfi_def_cfa(6, 16)
- cfi_offset(6, -16)
- andq $-32, %rsp
- subq $96, %rsp
-
-/*
- * 2*sqrt(X) ~ Sh - Sl (to 24+ bits)
- * SQ ~ 2*sqrt(X)
- */
- vmovups __svml_sacos_data_internal(%rip), %ymm6
- vmovups OneHalf+__svml_sacos_data_internal(%rip), %ymm7
- vmovaps %ymm0, %ymm5
-
-/* x = -|arg| */
- vorps %ymm5, %ymm6, %ymm4
-
-/* Y = 0.5 + 0.5*(-x) */
- vfmadd231ps %ymm4, %ymm7, %ymm7
-
-/* x^2 */
- vmulps %ymm4, %ymm4, %ymm8
-
-/* SQ ~ 2*sqrt(Y) */
- vmovups sqrt_coeff+__svml_sacos_data_internal(%rip), %ymm0
- vcmpnge_uqps MOne+__svml_sacos_data_internal(%rip), %ymm4, %ymm9
- vcmplt_oqps SmallNorm+__svml_sacos_data_internal(%rip), %ymm7, %ymm10
- vminps %ymm7, %ymm8, %ymm2
- vaddps %ymm7, %ymm7, %ymm14
- vrsqrtps %ymm7, %ymm11
- vmovups poly_coeff+64+__svml_sacos_data_internal(%rip), %ymm8
- vcmpnlt_uqps %ymm7, %ymm2, %ymm1
- vmulps %ymm2, %ymm2, %ymm7
- vfmadd213ps poly_coeff+96+__svml_sacos_data_internal(%rip), %ymm2, %ymm8
- vmovmskps %ymm9, %edx
-
-/* polynomial */
- vmovups poly_coeff+__svml_sacos_data_internal(%rip), %ymm9
- vandnps %ymm11, %ymm10, %ymm12
- vmulps %ymm12, %ymm12, %ymm13
- vfmadd213ps poly_coeff+32+__svml_sacos_data_internal(%rip), %ymm2, %ymm9
-
-/* X<X^2 iff X<0 */
- vcmplt_oqps %ymm2, %ymm5, %ymm10
- vfmadd213ps %ymm8, %ymm7, %ymm9
- vandps %ymm5, %ymm6, %ymm3
- vmulps %ymm14, %ymm12, %ymm6
- vfmsub213ps Two+__svml_sacos_data_internal(%rip), %ymm13, %ymm14
- vfmadd213ps poly_coeff+128+__svml_sacos_data_internal(%rip), %ymm2, %ymm9
- vfmadd213ps sqrt_coeff+32+__svml_sacos_data_internal(%rip), %ymm14, %ymm0
- vmulps %ymm14, %ymm6, %ymm15
- vmulps %ymm9, %ymm2, %ymm14
- vfnmadd213ps %ymm6, %ymm15, %ymm0
- vblendvps %ymm1, %ymm0, %ymm4, %ymm0
- vandps PiH+__svml_sacos_data_internal(%rip), %ymm1, %ymm2
- vandnps Pi2H+__svml_sacos_data_internal(%rip), %ymm1, %ymm12
- vxorps %ymm3, %ymm0, %ymm1
- vfmadd213ps %ymm1, %ymm1, %ymm14
- vandps %ymm10, %ymm2, %ymm11
- vaddps %ymm12, %ymm11, %ymm13
- vaddps %ymm14, %ymm13, %ymm0
- testl %edx, %edx
-
-/* Go to special inputs processing branch */
- jne L(SPECIAL_VALUES_BRANCH)
- # LOE rbx r12 r13 r14 r15 edx ymm0 ymm5
-
-/* 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 $96, %rsp
+
+ /*
+ * 2*sqrt(X) ~ Sh - Sl (to 24+ bits)
+ * SQ ~ 2*sqrt(X)
+ */
+ vmovups __svml_sacos_data_internal(%rip), %ymm6
+ vmovups OneHalf+__svml_sacos_data_internal(%rip), %ymm7
+ vmovaps %ymm0, %ymm5
+
+ /* x = -|arg| */
+ vorps %ymm5, %ymm6, %ymm4
+
+ /* Y = 0.5 + 0.5*(-x) */
+ vfmadd231ps %ymm4, %ymm7, %ymm7
+
+ /* x^2 */
+ vmulps %ymm4, %ymm4, %ymm8
+
+ /* SQ ~ 2*sqrt(Y) */
+ vmovups sqrt_coeff+__svml_sacos_data_internal(%rip), %ymm0
+ vcmpnge_uqps MOne+__svml_sacos_data_internal(%rip), %ymm4, %ymm9
+ vcmplt_oqps SmallNorm+__svml_sacos_data_internal(%rip), %ymm7, %ymm10
+ vminps %ymm7, %ymm8, %ymm2
+ vaddps %ymm7, %ymm7, %ymm14
+ vrsqrtps %ymm7, %ymm11
+ vmovups poly_coeff+64+__svml_sacos_data_internal(%rip), %ymm8
+ vcmpnlt_uqps %ymm7, %ymm2, %ymm1
+ vmulps %ymm2, %ymm2, %ymm7
+ vfmadd213ps poly_coeff+96+__svml_sacos_data_internal(%rip), %ymm2, %ymm8
+ vmovmskps %ymm9, %edx
+
+ /* polynomial */
+ vmovups poly_coeff+__svml_sacos_data_internal(%rip), %ymm9
+ vandnps %ymm11, %ymm10, %ymm12
+ vmulps %ymm12, %ymm12, %ymm13
+ vfmadd213ps poly_coeff+32+__svml_sacos_data_internal(%rip), %ymm2, %ymm9
+
+ /* X<X^2 iff X<0 */
+ vcmplt_oqps %ymm2, %ymm5, %ymm10
+ vfmadd213ps %ymm8, %ymm7, %ymm9
+ vandps %ymm5, %ymm6, %ymm3
+ vmulps %ymm14, %ymm12, %ymm6
+ vfmsub213ps Two+__svml_sacos_data_internal(%rip), %ymm13, %ymm14
+ vfmadd213ps poly_coeff+128+__svml_sacos_data_internal(%rip), %ymm2, %ymm9
+ vfmadd213ps sqrt_coeff+32+__svml_sacos_data_internal(%rip), %ymm14, %ymm0
+ vmulps %ymm14, %ymm6, %ymm15
+ vmulps %ymm9, %ymm2, %ymm14
+ vfnmadd213ps %ymm6, %ymm15, %ymm0
+ vblendvps %ymm1, %ymm0, %ymm4, %ymm0
+ vandps PiH+__svml_sacos_data_internal(%rip), %ymm1, %ymm2
+ vandnps Pi2H+__svml_sacos_data_internal(%rip), %ymm1, %ymm12
+ vxorps %ymm3, %ymm0, %ymm1
+ vfmadd213ps %ymm1, %ymm1, %ymm14
+ vandps %ymm10, %ymm2, %ymm11
+ vaddps %ymm12, %ymm11, %ymm13
+ vaddps %ymm14, %ymm13, %ymm0
+ testl %edx, %edx
+
+ /* Go to special inputs processing branch */
+ jne L(SPECIAL_VALUES_BRANCH)
+ # LOE rbx r12 r13 r14 r15 edx ymm0 ymm5
+
+ /* Restore registers
+ * and exit the function
+ */
L(EXIT):
- 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
- */
+ 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):
- vmovups %ymm5, 32(%rsp)
- vmovups %ymm0, 64(%rsp)
- # LOE rbx r12 r13 r14 r15 edx ymm0
-
- xorl %eax, %eax
- # LOE rbx r12 r13 r14 r15 eax edx
-
- vzeroupper
- 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: -80; DW_OP_plus) */
- .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
- movl %eax, %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: -88; DW_OP_plus) */
- .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
- movl %edx, %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: -96; DW_OP_plus) */
- .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
- * bits check
- */
+ vmovups %ymm5, 32(%rsp)
+ vmovups %ymm0, 64(%rsp)
+ # LOE rbx r12 r13 r14 r15 edx ymm0
+
+ xorl %eax, %eax
+ # LOE rbx r12 r13 r14 r15 eax edx
+
+ vzeroupper
+ 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: -80; DW_OP_plus) */
+ .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
+ movl %eax, %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: -88; DW_OP_plus) */
+ .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
+ movl %edx, %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: -96; DW_OP_plus) */
+ .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
+ * 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 $8, %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)
- vmovups 64(%rsp), %ymm0
-
-/* 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
- /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus) */
- .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 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: -96; DW_OP_plus) */
- .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 ymm0
-
-/* Scalar math fucntion call
- * to process special input
- */
+ incl %r12d
+ cmpl $8, %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)
+ vmovups 64(%rsp), %ymm0
+
+ /* 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
+ /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus) */
+ .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 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: -96; DW_OP_plus) */
+ .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 ymm0
+
+ /* Scalar math fucntion call
+ * to process special input
+ */
L(SCALAR_MATH_CALL):
- movl %r12d, %r14d
- movss 32(%rsp,%r14,4), %xmm0
- call acosf@PLT
- # LOE rbx r14 r15 r12d r13d xmm0
+ movl %r12d, %r14d
+ movss 32(%rsp, %r14, 4), %xmm0
+ call acosf@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 */
- 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(_ZGVdN8v_acosf_avx2)
- .section .rodata, "a"
- .align 32
+ .section .rodata, "a"
+ .align 32
#ifdef __svml_sacos_data_internal_typedef
typedef unsigned int VUINT32;
typedef struct {
- __declspec(align(32)) VUINT32 SgnBit[8][1];
- __declspec(align(32)) VUINT32 OneHalf[8][1];
- __declspec(align(32)) VUINT32 SmallNorm[8][1];
- __declspec(align(32)) VUINT32 MOne[8][1];
- __declspec(align(32)) VUINT32 Two[8][1];
- __declspec(align(32)) VUINT32 sqrt_coeff[2][8][1];
- __declspec(align(32)) VUINT32 poly_coeff[5][8][1];
- __declspec(align(32)) VUINT32 Pi2H[8][1];
- __declspec(align(32)) VUINT32 PiH[8][1];
+ __declspec(align(32)) VUINT32 SgnBit[8][1];
+ __declspec(align(32)) VUINT32 OneHalf[8][1];
+ __declspec(align(32)) VUINT32 SmallNorm[8][1];
+ __declspec(align(32)) VUINT32 MOne[8][1];
+ __declspec(align(32)) VUINT32 Two[8][1];
+ __declspec(align(32)) VUINT32 sqrt_coeff[2][8][1];
+ __declspec(align(32)) VUINT32 poly_coeff[5][8][1];
+ __declspec(align(32)) VUINT32 Pi2H[8][1];
+ __declspec(align(32)) VUINT32 PiH[8][1];
} __svml_sacos_data_internal;
#endif
__svml_sacos_data_internal:
- /*== SgnBit ==*/
- .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000
- /*== OneHalf ==*/
- .align 32
- .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000
- /*== SmallNorm ==*/
- .align 32
- .long 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000
- /*== MOne ==*/
- .align 32
- .long 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000
- /*== Two ==*/
- .align 32
- .long 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000
- /*== sqrt_coeff[2] ==*/
- .align 32
- .long 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004 /* sqrt_coeff2 */
- .long 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001 /* sqrt_coeff1 */
- /*== poly_coeff[5] ==*/
- .align 32
- .long 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07 /* poly_coeff5 */
- .long 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B /* poly_coeff4 */
- .long 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4 /* poly_coeff3 */
- .long 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12 /* poly_coeff2 */
- .long 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF /* poly_coeff1 */
- /*== Pi2H ==*/
- .align 32
- .long 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB
- /*== PiH ==*/
- .align 32
- .long 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB
- .align 32
- .type __svml_sacos_data_internal,@object
- .size __svml_sacos_data_internal,.-__svml_sacos_data_internal
+ /* SgnBit */
+ .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000
+ /* OneHalf */
+ .align 32
+ .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000
+ /* SmallNorm */
+ .align 32
+ .long 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000, 0x2f800000
+ /* MOne */
+ .align 32
+ .long 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000, 0xbf800000
+ /* Two */
+ .align 32
+ .long 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000, 0x40000000
+ /* sqrt_coeff[2] */
+ .align 32
+ .long 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004, 0xbdC00004 /* sqrt_coeff2 */
+ .long 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001, 0x3e800001 /* sqrt_coeff1 */
+ /* poly_coeff[5] */
+ .align 32
+ .long 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07, 0x3d2EDC07 /* poly_coeff5 */
+ .long 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B, 0x3CC32A6B /* poly_coeff4 */
+ .long 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4, 0x3d3A9AB4 /* poly_coeff3 */
+ .long 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12, 0x3d997C12 /* poly_coeff2 */
+ .long 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF, 0x3e2AAAFF /* poly_coeff1 */
+ /* Pi2H */
+ .align 32
+ .long 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB, 0x3fc90FDB
+ /* PiH */
+ .align 32
+ .long 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB, 0x40490FDB
+ .align 32
+ .type __svml_sacos_data_internal, @object
+ .size __svml_sacos_data_internal, .-__svml_sacos_data_internal
--
2.34.1
next prev parent reply other threads:[~2022-03-07 15:02 UTC|newest]
Thread overview: 129+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-07 14:59 [PATCH 000/126] x86_64: Fix libmvec assembly " Sunil K Pandey
2022-03-07 14:59 ` [PATCH 001/126] x86_64: Fix svml_s_acosf16_core_avx512.S " Sunil K Pandey
2022-03-07 21:50 ` Sunil Pandey
2022-03-07 22:52 ` Noah Goldstein
2022-03-07 14:59 ` [PATCH 002/126] x86_64: Fix svml_s_acosf4_core_sse4.S " Sunil K Pandey
2022-03-07 14:59 ` Sunil K Pandey [this message]
2022-03-07 14:59 ` [PATCH 004/126] x86_64: Fix svml_d_acos2_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 005/126] x86_64: Fix svml_d_acos4_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 006/126] x86_64: Fix svml_d_acos8_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 007/126] x86_64: Fix svml_s_acoshf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 008/126] x86_64: Fix svml_s_acoshf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 009/126] x86_64: Fix svml_s_acoshf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 010/126] x86_64: Fix svml_d_acosh2_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 011/126] x86_64: Fix svml_d_acosh4_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 012/126] x86_64: Fix svml_d_acosh8_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 013/126] x86_64: Fix svml_s_asinf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 014/126] x86_64: Fix svml_s_asinf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 015/126] x86_64: Fix svml_s_asinf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 016/126] x86_64: Fix svml_d_asin2_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 017/126] x86_64: Fix svml_d_asin4_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 018/126] x86_64: Fix svml_d_asin8_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 019/126] x86_64: Fix svml_s_asinhf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 020/126] x86_64: Fix svml_s_asinhf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 021/126] x86_64: Fix svml_s_asinhf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 022/126] x86_64: Fix svml_d_asinh2_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 023/126] x86_64: Fix svml_d_asinh4_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 024/126] x86_64: Fix svml_d_asinh8_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 025/126] x86_64: Fix svml_s_atanf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 026/126] x86_64: Fix svml_s_atanf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 027/126] x86_64: Fix svml_s_atanf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 028/126] x86_64: Fix svml_d_atan2_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 029/126] x86_64: Fix svml_d_atan4_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 030/126] x86_64: Fix svml_d_atan8_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 031/126] x86_64: Fix svml_s_atan2f16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 032/126] x86_64: Fix svml_s_atan2f4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 033/126] x86_64: Fix svml_s_atan2f8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 034/126] x86_64: Fix svml_d_atan22_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 035/126] x86_64: Fix svml_d_atan24_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 036/126] x86_64: Fix svml_d_atan28_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 037/126] x86_64: Fix svml_s_atanhf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 038/126] x86_64: Fix svml_s_atanhf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 039/126] x86_64: Fix svml_s_atanhf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 040/126] x86_64: Fix svml_d_atanh2_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 041/126] x86_64: Fix svml_d_atanh4_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 042/126] x86_64: Fix svml_d_atanh8_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 043/126] x86_64: Fix svml_s_cbrtf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 044/126] x86_64: Fix svml_s_cbrtf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 045/126] x86_64: Fix svml_s_cbrtf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 046/126] x86_64: Fix svml_d_cbrt2_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 047/126] x86_64: Fix svml_d_cbrt4_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 048/126] x86_64: Fix svml_d_cbrt8_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 049/126] x86_64: Fix svml_s_coshf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 050/126] x86_64: Fix svml_s_coshf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 051/126] x86_64: Fix svml_s_coshf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 052/126] x86_64: Fix svml_d_cosh2_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 053/126] x86_64: Fix svml_d_cosh4_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 054/126] x86_64: Fix svml_d_cosh8_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 055/126] x86_64: Fix svml_s_erff16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 056/126] x86_64: Fix svml_s_erff4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 057/126] x86_64: Fix svml_s_erff8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 058/126] x86_64: Fix svml_d_erf2_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 059/126] x86_64: Fix svml_d_erf4_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 060/126] x86_64: Fix svml_d_erf8_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 061/126] x86_64: Fix svml_s_erfcf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 062/126] x86_64: Fix svml_s_erfcf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 063/126] x86_64: Fix svml_s_erfcf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:00 ` [PATCH 064/126] x86_64: Fix svml_d_erfc2_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 065/126] x86_64: Fix svml_d_erfc4_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 066/126] x86_64: Fix svml_d_erfc8_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 067/126] x86_64: Fix svml_s_exp10f16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 068/126] x86_64: Fix svml_s_exp10f4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 069/126] x86_64: Fix svml_s_exp10f8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 070/126] x86_64: Fix svml_d_exp102_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 071/126] x86_64: Fix svml_d_exp104_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 072/126] x86_64: Fix svml_d_exp108_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 073/126] x86_64: Fix svml_s_exp2f16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 074/126] x86_64: Fix svml_s_exp2f4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 075/126] x86_64: Fix svml_s_exp2f8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 076/126] x86_64: Fix svml_d_exp22_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 077/126] x86_64: Fix svml_d_exp24_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 078/126] x86_64: Fix svml_d_exp28_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 079/126] x86_64: Fix svml_s_expm1f16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 080/126] x86_64: Fix svml_s_expm1f4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 081/126] x86_64: Fix svml_s_expm1f8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 082/126] x86_64: Fix svml_d_expm12_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 083/126] x86_64: Fix svml_d_expm14_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 084/126] x86_64: Fix svml_d_expm18_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 085/126] x86_64: Fix svml_s_hypotf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 086/126] x86_64: Fix svml_s_hypotf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 087/126] x86_64: Fix svml_s_hypotf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 088/126] x86_64: Fix svml_d_hypot2_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 089/126] x86_64: Fix svml_d_hypot4_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 090/126] x86_64: Fix svml_d_hypot8_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 091/126] x86_64: Fix svml_s_log10f16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 092/126] x86_64: Fix svml_s_log10f4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 093/126] x86_64: Fix svml_s_log10f8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 094/126] x86_64: Fix svml_d_log102_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 095/126] x86_64: Fix svml_d_log104_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 096/126] x86_64: Fix svml_d_log108_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 097/126] x86_64: Fix svml_s_log1pf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 098/126] x86_64: Fix svml_s_log1pf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 099/126] x86_64: Fix svml_s_log1pf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 100/126] x86_64: Fix svml_d_log1p2_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 101/126] x86_64: Fix svml_d_log1p4_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 102/126] x86_64: Fix svml_d_log1p8_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 103/126] x86_64: Fix svml_s_log2f16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 104/126] x86_64: Fix svml_s_log2f4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 105/126] x86_64: Fix svml_s_log2f8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 106/126] x86_64: Fix svml_d_log22_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 107/126] x86_64: Fix svml_d_log24_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 108/126] x86_64: Fix svml_d_log28_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 109/126] x86_64: Fix svml_s_sinhf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 110/126] x86_64: Fix svml_s_sinhf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 111/126] x86_64: Fix svml_s_sinhf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 112/126] x86_64: Fix svml_d_sinh2_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 113/126] x86_64: Fix svml_d_sinh4_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 114/126] x86_64: Fix svml_d_sinh8_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 115/126] x86_64: Fix svml_s_tanf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 116/126] x86_64: Fix svml_s_tanf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 117/126] x86_64: Fix svml_s_tanf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 118/126] x86_64: Fix svml_d_tan2_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 119/126] x86_64: Fix svml_d_tan4_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 120/126] x86_64: Fix svml_d_tan8_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 121/126] x86_64: Fix svml_s_tanhf16_core_avx512.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 122/126] x86_64: Fix svml_s_tanhf4_core_sse4.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 123/126] x86_64: Fix svml_s_tanhf8_core_avx2.S " Sunil K Pandey
2022-03-07 15:01 ` [PATCH 124/126] x86_64: Fix svml_d_tanh2_core_sse4.S " Sunil K Pandey
2022-03-07 15:02 ` [PATCH 125/126] x86_64: Fix svml_d_tanh4_core_avx2.S " Sunil K Pandey
2022-03-07 15:02 ` [PATCH 126/126] x86_64: Fix svml_d_tanh8_core_avx512.S " Sunil K Pandey
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220307150201.10590-4-skpgkp2@gmail.com \
--to=skpgkp2@gmail.com \
--cc=libc-alpha@sourceware.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).