@@ -27,39 +27,35 @@
*
*/
-/* Offsets for data table __svml_slog2_data_internal_avx512
- */
-#define One 0
-#define coeff4 64
-#define coeff3 128
-#define coeff2 192
-#define coeff1 256
+#define LOCAL_DATA_NAME __svml_slog2_data_internal
+#include "svml_s_common_evex512_rodata_offsets.h"
+
+/* Offsets for data table __svml_slog2_data_internal. */
+#define _Coeff_4 0
+#define _Coeff_3 64
+#define _Coeff_2 128
+#define _Coeff_1 192
+
#include <sysdep.h>
.section .text.evex512, "ax", @progbits
ENTRY(_ZGVeN16v_log2f_skx)
- pushq %rbp
- cfi_def_cfa_offset(16)
- movq %rsp, %rbp
- cfi_def_cfa(6, 16)
- cfi_offset(6, -16)
- andq $-64, %rsp
- subq $192, %rsp
vgetmantps $11, {sae}, %zmm0, %zmm3
- vmovups __svml_slog2_data_internal_avx512(%rip), %zmm1
+ vmovups COMMON_DATA(_OneF)(%rip), %zmm1
vgetexpps {sae}, %zmm0, %zmm5
- /* x<=0? */
- vfpclassps $94, %zmm0, %k0
+
vsubps {rn-sae}, %zmm1, %zmm3, %zmm9
vpsrld $19, %zmm3, %zmm7
vgetexpps {sae}, %zmm3, %zmm6
- vpermps coeff4+__svml_slog2_data_internal_avx512(%rip), %zmm7, %zmm1
- vpermps coeff3+__svml_slog2_data_internal_avx512(%rip), %zmm7, %zmm2
- vpermps coeff2+__svml_slog2_data_internal_avx512(%rip), %zmm7, %zmm4
- vpermps coeff1+__svml_slog2_data_internal_avx512(%rip), %zmm7, %zmm8
+ vpermps LOCAL_DATA(_Coeff_4)(%rip), %zmm7, %zmm1
+ vpermps LOCAL_DATA(_Coeff_3)(%rip), %zmm7, %zmm2
+ vpermps LOCAL_DATA(_Coeff_2)(%rip), %zmm7, %zmm4
+ vpermps LOCAL_DATA(_Coeff_1)(%rip), %zmm7, %zmm8
vsubps {rn-sae}, %zmm6, %zmm5, %zmm10
+ /* x<=0? */
+ vfpclassps $0x5e, %zmm0, %k0
vfmadd213ps {rn-sae}, %zmm2, %zmm9, %zmm1
kmovw %k0, %edx
vfmadd213ps {rn-sae}, %zmm4, %zmm9, %zmm1
@@ -67,164 +63,128 @@ ENTRY(_ZGVeN16v_log2f_skx)
vfmadd213ps {rn-sae}, %zmm10, %zmm9, %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
- * and exit the function
- */
-
-L(EXIT):
vmovaps %zmm1, %zmm0
- 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
- */
+ /* Restore registers * and exit the function. */
+
+ /* Branch to process * special inputs. */
+ /* Cold case. edx has 1s where there was a special value that
+ needs to be handled by a tanf call. Optimize for code size
+ moreso than speed here. */
L(SPECIAL_VALUES_BRANCH):
- vmovups %zmm0, 64(%rsp)
- vmovups %zmm1, 128(%rsp)
- # LOE rbx r12 r13 r14 r15 edx zmm1
- xorl %eax, %eax
- # LOE rbx r12 r13 r14 r15 eax edx
+ /* Use r13 to save/restore the stack. This allows us to use rbp
+ as callee save register saving code size. */
+ pushq %r13
+ cfi_def_cfa (rsp, 16)
+ /* Need to callee save registers to preserve state across tanf
+ calls. */
+ pushq %rbx
+ cfi_def_cfa (rsp, 24)
+ pushq %rbp
+ cfi_def_cfa (rsp, 32)
+ movq %rsp, %r13
+ cfi_def_cfa (r13, 32)
+
+ /* Align stack and make room for 2x zmm vectors. */
+ andq $-64, %rsp
+ addq $-128, %rsp
+
+ /* Save origional input. */
+ vmovaps %zmm0, 64(%rsp)
+ /* Save all already computed inputs. */
+ vmovaps %zmm1, (%rsp)
vzeroupper
- movq %r12, 16(%rsp)
- /* 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
- movl %eax, %r12d
- movq %r13, 8(%rsp)
- /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */
- .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
- movl %edx, %r13d
- movq %r14, (%rsp)
- /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */
- .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
- * bits check
- */
-
-L(RANGEMASK_CHECK):
- btl %r12d, %r13d
-
- /* Call scalar math function */
- jc L(SCALAR_MATH_CALL)
- # LOE rbx r15 r12d r13d
-
- /* Special inputs
- * processing loop
- */
+ /* edx has 1s where there was a special value that needs to be
+ handled by a tanf call. */
+ movl %edx, %ebx
L(SPECIAL_VALUES_LOOP):
- incl %r12d
- cmpl $16, %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 128(%rsp), %zmm1
-
- /* 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
- /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */
- .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22
- /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */
- .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
- * to process special input
- */
-
-L(SCALAR_MATH_CALL):
- movl %r12d, %r14d
- vmovss 64(%rsp, %r14, 4), %xmm0
+
+ /* use rbp as index for special value that is saved across calls
+ to tanf. We technically don't need a callee save register
+ here as offset to rsp is always [0, 56] so we can restore
+ rsp by realigning to 64. Essentially the tradeoff is 1 extra
+ save/restore vs 2 extra instructions in the loop. Realigning
+ also costs more code size. */
+ xorl %ebp, %ebp
+ tzcntl %ebx, %ebp
+
+ /* Scalar math fucntion call to process special input. */
+ movss 64(%rsp, %rbp, 4), %xmm0
call log2f@PLT
- # LOE rbx r14 r15 r12d r13d xmm0
- vmovss %xmm0, 128(%rsp, %r14, 4)
+ /* No good way to avoid the store-forwarding fault this will
+ cause on return. `lfence` avoids the SF fault but at greater
+ cost as it serialized stack/callee save restoration. */
+ movss %xmm0, (%rsp, %rbp, 4)
- /* Process special inputs in loop */
- jmp L(SPECIAL_VALUES_LOOP)
- # LOE rbx r15 r12d r13d
+ blsrl %ebx, %ebx
+ jnz L(SPECIAL_VALUES_LOOP)
+
+
+ /* All results have been written to 64(%rsp). */
+ vmovaps (%rsp), %zmm0
+ /* Restore rsp. */
+ movq %r13, %rsp
+ cfi_def_cfa (rsp, 32)
+ /* Restore callee save registers. */
+ popq %rbp
+ cfi_def_cfa (rsp, 24)
+ popq %rbx
+ cfi_def_cfa (rsp, 16)
+ popq %r13
+ ret
END(_ZGVeN16v_log2f_skx)
- .section .rodata, "a"
+ .section .rodata.evex512, "a"
.align 64
-#ifdef __svml_slog2_data_internal_avx512_typedef
-typedef unsigned int VUINT32;
-typedef struct {
- __declspec(align(64)) VUINT32 One[16][1];
- __declspec(align(64)) VUINT32 coeff4[16][1];
- __declspec(align(64)) VUINT32 coeff3[16][1];
- __declspec(align(64)) VUINT32 coeff2[16][1];
- __declspec(align(64)) VUINT32 coeff1[16][1];
-} __svml_slog2_data_internal_avx512;
-#endif
-__svml_slog2_data_internal_avx512:
- /* One */
- .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
- // c4
- .align 64
- .long 0xbea77e4a, 0xbe8aae3d
- .long 0xbe67fe32, 0xbe43d1b6
- .long 0xbe26a589, 0xbe0ee09b
- .long 0xbdf6a8a1, 0xbdd63b49
- .long 0xbf584e51, 0xbf3e80a1
- .long 0xbf2892f0, 0xbf15d377
- .long 0xbf05b525, 0xbeef8e30
- .long 0xbed75c8f, 0xbec24184
- // c3
- .align 64
- .long 0x3ef5910c, 0x3ef045a1
- .long 0x3ee7d87e, 0x3eddbb84
- .long 0x3ed2d6df, 0x3ec7bbd2
- .long 0x3ebcc42f, 0x3eb22616
- .long 0x3e8f3399, 0x3eb1223e
- .long 0x3ec9db4a, 0x3edb7a09
- .long 0x3ee79a1a, 0x3eef77cb
- .long 0x3ef407a4, 0x3ef607b4
- // c2
- .align 64
- .long 0xbf38a934, 0xbf387de6
- .long 0xbf37f6f0, 0xbf37048b
- .long 0xbf35a88a, 0xbf33ed04
- .long 0xbf31df56, 0xbf2f8d82
- .long 0xbf416814, 0xbf3daf58
- .long 0xbf3b5c08, 0xbf39fa2a
- .long 0xbf393713, 0xbf38d7e1
- .long 0xbf38b2cd, 0xbf38aa62
- // c1
- .align 64
- .long 0x3fb8aa3b, 0x3fb8a9c0
- .long 0x3fb8a6e8, 0x3fb89f4e
- .long 0x3fb890cb, 0x3fb879b1
- .long 0x3fb858d8, 0x3fb82d90
- .long 0x3fb8655e, 0x3fb8883a
- .long 0x3fb89aea, 0x3fb8a42f
- .long 0x3fb8a848, 0x3fb8a9c9
- .long 0x3fb8aa2f, 0x3fb8aa3b
- .align 64
- .type __svml_slog2_data_internal_avx512, @object
- .size __svml_slog2_data_internal_avx512, .-__svml_slog2_data_internal_avx512
+LOCAL_DATA_NAME:
+ float_block (LOCAL_DATA_NAME, _Coeff_4,
+ 0xbea77e4a, 0xbe8aae3d,
+ 0xbe67fe32, 0xbe43d1b6,
+ 0xbe26a589, 0xbe0ee09b,
+ 0xbdf6a8a1, 0xbdd63b49,
+ 0xbf584e51, 0xbf3e80a1,
+ 0xbf2892f0, 0xbf15d377,
+ 0xbf05b525, 0xbeef8e30,
+ 0xbed75c8f, 0xbec24184)
+
+ float_block (LOCAL_DATA_NAME, _Coeff_3,
+ 0x3ef5910c, 0x3ef045a1,
+ 0x3ee7d87e, 0x3eddbb84,
+ 0x3ed2d6df, 0x3ec7bbd2,
+ 0x3ebcc42f, 0x3eb22616,
+ 0x3e8f3399, 0x3eb1223e,
+ 0x3ec9db4a, 0x3edb7a09,
+ 0x3ee79a1a, 0x3eef77cb,
+ 0x3ef407a4, 0x3ef607b4)
+
+ float_block (LOCAL_DATA_NAME, _Coeff_2,
+ 0xbf38a934, 0xbf387de6,
+ 0xbf37f6f0, 0xbf37048b,
+ 0xbf35a88a, 0xbf33ed04,
+ 0xbf31df56, 0xbf2f8d82,
+ 0xbf416814, 0xbf3daf58,
+ 0xbf3b5c08, 0xbf39fa2a,
+ 0xbf393713, 0xbf38d7e1,
+ 0xbf38b2cd, 0xbf38aa62)
+
+ float_block (LOCAL_DATA_NAME, _Coeff_1,
+ 0x3fb8aa3b, 0x3fb8a9c0,
+ 0x3fb8a6e8, 0x3fb89f4e,
+ 0x3fb890cb, 0x3fb879b1,
+ 0x3fb858d8, 0x3fb82d90,
+ 0x3fb8655e, 0x3fb8883a,
+ 0x3fb89aea, 0x3fb8a42f,
+ 0x3fb8a848, 0x3fb8a9c9,
+ 0x3fb8aa2f, 0x3fb8aa3b)
+
+ .type LOCAL_DATA_NAME, @object
+ .size LOCAL_DATA_NAME, .-LOCAL_DATA_NAME