* 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
*
/* Offsets for data table __svml_sexp2_data_internal
*/
-#define _sShifter 0
-#define _sPC0 32
-#define _sPC1 64
-#define _sPC2 96
-#define _sPC3 128
-#define _sPC4 160
-#define _sPC5 192
-#define _sPC6 224
-#define _iAbsMask 256
-#define _iDomainRange 288
+#define _sShifter 0
+#define _sPC0 32
+#define _sPC1 64
+#define _sPC2 96
+#define _sPC3 128
+#define _sPC4 160
+#define _sPC5 192
+#define _sPC6 224
+#define _iAbsMask 256
+#define _iDomainRange 288
#include <sysdep.h>
- .text
- .section .text.avx2,"ax",@progbits
+ .section .text.avx2, "ax", @progbits
ENTRY(_ZGVdN8v_exp2f_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
- vmovups __svml_sexp2_data_internal(%rip), %ymm1
-
-/* Check for overflow\underflow */
- vmovups _sPC6+__svml_sexp2_data_internal(%rip), %ymm7
-
-/* Implementation */
- vaddps %ymm1, %ymm0, %ymm6
- vsubps %ymm1, %ymm6, %ymm4
-
-/* 2^N */
- vpslld $23, %ymm6, %ymm8
-
-/* R */
- vsubps %ymm4, %ymm0, %ymm5
-
-/* Polynomial */
- vfmadd213ps _sPC5+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
- vfmadd213ps _sPC4+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
- vfmadd213ps _sPC3+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
- vfmadd213ps _sPC2+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
- vfmadd213ps _sPC1+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
- vfmadd213ps _sPC0+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
-
-/* Check for overflow\underflow */
- vandps _iAbsMask+__svml_sexp2_data_internal(%rip), %ymm0, %ymm2
- vpcmpgtd _iDomainRange+__svml_sexp2_data_internal(%rip), %ymm2, %ymm3
- vmovmskps %ymm3, %edx
-
-/* Reconstruction */
- vpaddd %ymm8, %ymm7, %ymm1
- testl %edx, %edx
-
-/* Go to special inputs processing branch */
- jne L(SPECIAL_VALUES_BRANCH)
- # LOE rbx r12 r13 r14 r15 edx ymm0 ymm1
-
-/* 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
+ vmovups __svml_sexp2_data_internal(%rip), %ymm1
+
+ /* Check for overflow\underflow */
+ vmovups _sPC6+__svml_sexp2_data_internal(%rip), %ymm7
+
+ /* Implementation */
+ vaddps %ymm1, %ymm0, %ymm6
+ vsubps %ymm1, %ymm6, %ymm4
+
+ /* 2^N */
+ vpslld $23, %ymm6, %ymm8
+
+ /* R */
+ vsubps %ymm4, %ymm0, %ymm5
+
+ /* Polynomial */
+ vfmadd213ps _sPC5+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
+ vfmadd213ps _sPC4+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
+ vfmadd213ps _sPC3+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
+ vfmadd213ps _sPC2+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
+ vfmadd213ps _sPC1+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
+ vfmadd213ps _sPC0+__svml_sexp2_data_internal(%rip), %ymm5, %ymm7
+
+ /* Check for overflow\underflow */
+ vandps _iAbsMask+__svml_sexp2_data_internal(%rip), %ymm0, %ymm2
+ vpcmpgtd _iDomainRange+__svml_sexp2_data_internal(%rip), %ymm2, %ymm3
+ vmovmskps %ymm3, %edx
+
+ /* Reconstruction */
+ vpaddd %ymm8, %ymm7, %ymm1
+ testl %edx, %edx
+
+ /* Go to special inputs processing branch */
+ jne L(SPECIAL_VALUES_BRANCH)
+ # LOE rbx r12 r13 r14 r15 edx ymm0 ymm1
+
+ /* Restore registers
+ * and exit the function
+ */
L(EXIT):
- vmovaps %ymm1, %ymm0
- 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
- */
+ vmovaps %ymm1, %ymm0
+ 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 %ymm0, 32(%rsp)
- vmovups %ymm1, 64(%rsp)
- # LOE rbx r12 r13 r14 r15 edx ymm1
-
- 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 %ymm0, 32(%rsp)
+ vmovups %ymm1, 64(%rsp)
+ # LOE rbx r12 r13 r14 r15 edx ymm1
+
+ 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), %ymm1
-
-/* 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 ymm1
-
-/* 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), %ymm1
+
+ /* 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 ymm1
+
+ /* Scalar math fucntion call
+ * to process special input
+ */
L(SCALAR_MATH_CALL):
- movl %r12d, %r14d
- movss 32(%rsp,%r14,4), %xmm0
- call exp2f@PLT
- # LOE rbx r14 r15 r12d r13d xmm0
+ movl %r12d, %r14d
+ movss 32(%rsp, %r14, 4), %xmm0
+ call exp2f@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_exp2f_avx2)
- .section .rodata, "a"
- .align 32
+ .section .rodata, "a"
+ .align 32
#ifdef __svml_sexp2_data_internal_typedef
typedef unsigned int VUINT32;
-typedef struct
-{
- __declspec(align(32)) VUINT32 _sShifter[8][1];
- __declspec(align(32)) VUINT32 _sPC0[8][1];
- __declspec(align(32)) VUINT32 _sPC1[8][1];
- __declspec(align(32)) VUINT32 _sPC2[8][1];
- __declspec(align(32)) VUINT32 _sPC3[8][1];
- __declspec(align(32)) VUINT32 _sPC4[8][1];
- __declspec(align(32)) VUINT32 _sPC5[8][1];
- __declspec(align(32)) VUINT32 _sPC6[8][1];
- __declspec(align(32)) VUINT32 _iAbsMask[8][1];
- __declspec(align(32)) VUINT32 _iDomainRange[8][1];
+typedef struct {
+ __declspec(align(32)) VUINT32 _sShifter[8][1];
+ __declspec(align(32)) VUINT32 _sPC0[8][1];
+ __declspec(align(32)) VUINT32 _sPC1[8][1];
+ __declspec(align(32)) VUINT32 _sPC2[8][1];
+ __declspec(align(32)) VUINT32 _sPC3[8][1];
+ __declspec(align(32)) VUINT32 _sPC4[8][1];
+ __declspec(align(32)) VUINT32 _sPC5[8][1];
+ __declspec(align(32)) VUINT32 _sPC6[8][1];
+ __declspec(align(32)) VUINT32 _iAbsMask[8][1];
+ __declspec(align(32)) VUINT32 _iDomainRange[8][1];
} __svml_sexp2_data_internal;
#endif
__svml_sexp2_data_internal:
- .long 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000 /* _sShifter */
- .align 32
- .long 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000 /* _sPC0 */
- .align 32
- .long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218 /* _sPC1 */
- .align 32
- .long 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef /* _sPC2 */
- .align 32
- .long 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf /* _sPC3 */
- .align 32
- .long 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c /* _sPC4 */
- .align 32
- .long 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51 /* _sPC5 */
- .align 32
- .long 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c /* _sPC6 */
- //common
- .align 32
- .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff /* _iAbsMask */
- .align 32
- .long 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000 /* _iDomainRange=126.0 */
- .align 32
- .type __svml_sexp2_data_internal,@object
- .size __svml_sexp2_data_internal,.-__svml_sexp2_data_internal
+ .long 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000 /* _sShifter */
+ .align 32
+ .long 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000 /* _sPC0 */
+ .align 32
+ .long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218 /* _sPC1 */
+ .align 32
+ .long 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef, 0x3e75fdef /* _sPC2 */
+ .align 32
+ .long 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf, 0x3d6357cf /* _sPC3 */
+ .align 32
+ .long 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c, 0x3c1d962c /* _sPC4 */
+ .align 32
+ .long 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51, 0x3aaf7a51 /* _sPC5 */
+ .align 32
+ .long 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c, 0x39213c8c /* _sPC6 */
+ //common
+ .align 32
+ .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff /* _iAbsMask */
+ .align 32
+ .long 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000, 0x42fc0000 /* _iDomainRange=126.0 */
+ .align 32
+ .type __svml_sexp2_data_internal, @object
+ .size __svml_sexp2_data_internal, .-__svml_sexp2_data_internal
projects / thirdparty / glibc.git / commitdiff
