From: Noah Goldstein <goldstein.w.n@gmail.com>
To: libc-alpha@sourceware.org
Cc: goldstein.w.n@gmail.com, hjl.tools@gmail.com,
andrey.kolesov@intel.com, carlos@systemhalted.org
Subject: [PATCH v1 10/27] x86/fpu: Update rodata usage in svml_s_atanhf8_core_avx2.S
Date: Wed, 7 Dec 2022 00:52:19 -0800 [thread overview]
Message-ID: <20221207085236.1424424-10-goldstein.w.n@gmail.com> (raw)
In-Reply-To: <20221207085236.1424424-1-goldstein.w.n@gmail.com>
No changes to the logic, just change how rodata is handled.
1. Define the rodatas using the new macros so they check that the
offset is correct.
2. Use common data where applicable.
---
.../fpu/multiarch/svml_s_atanhf8_core_avx2.S | 308 ++++++++----------
1 file changed, 129 insertions(+), 179 deletions(-)
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf8_core_avx2.S
index 49ffd7a9b2..0c93da0166 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf8_core_avx2.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf8_core_avx2.S
@@ -1,5 +1,5 @@
/* Function atanhf vectorized with AVX2.
- Copyright (C) 2021-2022 Free Software Foundation, Inc.
+n Copyright (C) 2021-2022 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
@@ -30,181 +30,178 @@
*
*/
-/* Offsets for data table __svml_satanh_data_internal_avx512. Ordered
+
+#define LOCAL_DATA_NAME __svml_satan_data_internal
+#include "svml_s_common_avx2_rodata_offsets.h"
+
+/* Offsets for data table __svml_satanh_data_internal. Ordered
by use in the function. On cold-starts this might hhelp the
prefetcher. Possibly a better idea is to interleave start/end so
that the prefetcher is less likely to detect a stream and pull
irrelivant lines into cache. */
-#define SgnMask 0
-#define sOne 32
-#define sTopMask12 64
-#define TinyRange 96
-#define iBrkValue 128
-#define iOffExpoMask 160
-#define sPoly 192
-#define sLn2 448
-#define sHalf 480
+#define _TinyRange 0
+#define _Poly_1 32
+#define _Poly_2 64
+#define _Poly_3 96
+#define _Poly_4 128
+#define _Poly_5 160
+#define _Poly_6 192
+#define _Poly_7 224
+#define _Half 256
#include <sysdep.h>
-#define ATANHF_DATA(x) ((x)+__svml_satanh_data_internal)
.section .text.avx2, "ax", @progbits
ENTRY(_ZGVdN8v_atanhf_avx2)
- /* Strip off the sign, so treat X as positive until right at the end */
- vmovaps ATANHF_DATA(SgnMask)(%rip), %ymm2
+ /* Strip off the sign, so treat X as positive until right at the end. */
+ vmovaps COMMON_DATA(_AbsMask)(%rip), %ymm2
vandps %ymm2, %ymm0, %ymm3
- /* Load constants including One = 1 */
- vmovups ATANHF_DATA(sOne)(%rip), %ymm5
+ /* Load constants including One = 1. */
+ vmovups COMMON_DATA(_OneF)(%rip), %ymm5
vsubps %ymm3, %ymm5, %ymm1
- vmovups ATANHF_DATA(sTopMask12)(%rip), %ymm4
+ vmovups COMMON_DATA(_Neg4096)(%rip), %ymm4
vrcpps %ymm1, %ymm7
vsubps %ymm1, %ymm5, %ymm9
vandps %ymm4, %ymm7, %ymm6
vsubps %ymm3, %ymm9, %ymm7
- /* No need to split sU when FMA is available */
+ /* No need to split sU when FMA is available. */
vfnmadd213ps %ymm5, %ymm6, %ymm1
vmovaps %ymm0, %ymm8
vfmadd213ps %ymm0, %ymm0, %ymm0
vfnmadd231ps %ymm6, %ymm7, %ymm1
- /*
- * Check whether |X| < 1, in which case we use the main function.
- * Otherwise set the rangemask so that the callout will get used.
- * Note that this will also use the callout for NaNs since not(NaN < 1).
- */
+ /* Check whether |X| < 1, in which case we use the main
+ function. Otherwise set the rangemask so that the callout
+ will get used. Note that this will also use the callout for
+ NaNs since not(NaN < 1). */
vcmpnlt_uqps %ymm5, %ymm3, %ymm14
- vcmplt_oqps ATANHF_DATA(TinyRange)(%rip), %ymm3, %ymm15
+ vcmplt_oqps LOCAL_DATA(_TinyRange)(%rip), %ymm3, %ymm15
- /*
- * Compute V = 2 * X trivially, and UHi + U_lo = 1 - X in two pieces,
- * the upper part UHi being <= 12 bits long. Then we have
- * atanh(X) = 1/2 * log((1 + X) / (1 - X)) = 1/2 * log1p(V / (UHi + ULo)).
- */
+ /* Compute V = 2 * X trivially, and UHi + U_lo = 1 - X in two
+ pieces, the upper part UHi being <= 12 bits long. Then we
+ have atanh(X) = 1/2 * log((1 + X) / (1 - X)) = 1/2 * log1p(V
+ / (UHi + ULo)). */
vaddps %ymm3, %ymm3, %ymm3
- /*
- * Split V as well into upper 12 bits and lower part, so that we can get
- * a preliminary quotient estimate without rounding error.
- */
+ /* Split V as well into upper 12 bits and lower part, so that we
+ can get a preliminary quotient estimate without rounding
+ error. */
vandps %ymm4, %ymm3, %ymm4
vsubps %ymm4, %ymm3, %ymm7
- /* Hence get initial quotient estimate QHi + QLo = R * VHi + R * VLo */
+ /* Hence get initial quotient estimate QHi + QLo = R * VHi + R * VLo. */
vmulps %ymm4, %ymm6, %ymm4
- /* Compute D = E + E^2 */
+ /* Compute D = E + E^2. */
vfmadd213ps %ymm1, %ymm1, %ymm1
/* Record the sign for eventual reincorporation. */
vandnps %ymm8, %ymm2, %ymm3
- /* Or the sign bit in with the tiny result to handle atanh(-0) correctly */
+ /* Or the sign bit in with the tiny result to handle atanh(-0)
+ correctly. */
vorps %ymm3, %ymm0, %ymm13
vmulps %ymm7, %ymm6, %ymm2
- /*
- * Compute R * (VHi + VLo) * (1 + E + E^2)
- * = R * (VHi + VLo) * (1 + D)
- * = QHi + (QHi * D + QLo + QLo * D)
- */
-
- /*
- * If less precision is acceptable the `vmulps %ymm1, %ymm4, %ymm9;
- * vaddps %ymm1, %ymm9, %ymm1` can be replaced with
- * `vfmadd231ps %ymm1, %ymm4, %ymm4`.
- */
+ /* Compute R * (VHi + VLo) * (1 + E + E^2)
+ = R * (VHi + VLo) * (1 + D)
+ = QHi + (QHi * D + QLo + QLo * D). */
+
+ /* If less precision is acceptable the:
+ `vmulps %ymm1, %ymm4, %ymm6; vaddps %ymm1, %ymm9, %ymm1`
+ can be replaced with:
+ `vfmadd231ps %ymm1, %ymm4, %ymm4`. */
vmulps %ymm1, %ymm4, %ymm6
vfmadd213ps %ymm2, %ymm2, %ymm1
vaddps %ymm1, %ymm6, %ymm1
- /*
- * Now finally accumulate the high and low parts of the
- * argument to log1p, H + L, with a final compensated summation.
- */
+ /* Now finally accumulate the high and low parts of the
+ argument to log1p, H + L, with a final compensated summation. */
vaddps %ymm1, %ymm4, %ymm2
- /* reduction: compute r, n */
- vmovups ATANHF_DATA(iBrkValue)(%rip), %ymm9
+ /* reduction: compute r, n. */
+ vmovups COMMON_DATA(_IBrkValue)(%rip), %ymm9
- /*
- * Now we feed into the log1p code, using H in place of _VARG1 and
- * later incorporating L into the reduced argument.
- * compute 1+x as high, low parts
- */
+ /* Now we feed into the log1p code, using H in place of _VARG1 and
+ later incorporating L into the reduced argument.
+ compute 1+x as high, low parts. */
vmaxps %ymm2, %ymm5, %ymm0
vminps %ymm2, %ymm5, %ymm6
- /* This is needed for rounding (see `vaddps %ymm1, %ymm4, %ymm2`). */
+ /* This is needed for rounding (see `vaddps %ymm1, %ymm4,
+ %ymm2`). */
vsubps %ymm2, %ymm4, %ymm2
vaddps %ymm6, %ymm0, %ymm4
vpsubd %ymm9, %ymm4, %ymm7
vsubps %ymm4, %ymm0, %ymm4
vaddps %ymm2, %ymm1, %ymm2
- vmovaps ATANHF_DATA(iOffExpoMask)(%rip), %ymm1
+ vmovaps COMMON_DATA(_NotiOffExpoMask)(%rip), %ymm1
- vandps %ymm1, %ymm7, %ymm0
+ vandnps %ymm7, %ymm1, %ymm0
vaddps %ymm4, %ymm6, %ymm4
- vandnps %ymm7, %ymm1, %ymm6
- vmovups ATANHF_DATA(sPoly+0)(%rip), %ymm1
+ vandps %ymm7, %ymm1, %ymm6
+
+ vmovups LOCAL_DATA(_Poly_1)(%rip), %ymm1
vpaddd %ymm9, %ymm0, %ymm0
vaddps %ymm4, %ymm2, %ymm4
vpsubd %ymm6, %ymm5, %ymm6
- /* polynomial evaluation */
+ /* polynomial evaluation. */
vsubps %ymm5, %ymm0, %ymm2
vfmadd231ps %ymm4, %ymm6, %ymm2
- vfmadd213ps ATANHF_DATA(sPoly+32)(%rip), %ymm2, %ymm1
- vfmadd213ps ATANHF_DATA(sPoly+64)(%rip), %ymm2, %ymm1
- vfmadd213ps ATANHF_DATA(sPoly+96)(%rip), %ymm2, %ymm1
- vfmadd213ps ATANHF_DATA(sPoly+128)(%rip), %ymm2, %ymm1
- vfmadd213ps ATANHF_DATA(sPoly+160)(%rip), %ymm2, %ymm1
- vfmadd213ps ATANHF_DATA(sPoly+192)(%rip), %ymm2, %ymm1
- vfmadd213ps ATANHF_DATA(sPoly+224)(%rip), %ymm2, %ymm1
+
+ vfmadd213ps LOCAL_DATA(_Poly_2)(%rip), %ymm2, %ymm1
+ vfmadd213ps LOCAL_DATA(_Poly_3)(%rip), %ymm2, %ymm1
+ vfmadd213ps LOCAL_DATA(_Poly_4)(%rip), %ymm2, %ymm1
+ vfmadd213ps LOCAL_DATA(_Poly_5)(%rip), %ymm2, %ymm1
+ vfmadd213ps LOCAL_DATA(_Poly_6)(%rip), %ymm2, %ymm1
+ vfmadd213ps LOCAL_DATA(_Poly_7)(%rip), %ymm2, %ymm1
+ vfmadd213ps COMMON_DATA(_Neg5F)(%rip), %ymm2, %ymm1
vmulps %ymm1, %ymm2, %ymm1
vfmadd213ps %ymm2, %ymm2, %ymm1
- /* final reconstruction */
+ /* final reconstruction. */
vpsrad $23, %ymm7, %ymm6
vcvtdq2ps %ymm6, %ymm2
- vfmadd132ps ATANHF_DATA(sLn2)(%rip), %ymm1, %ymm2
+ vfmadd132ps COMMON_DATA(_Ln2)(%rip), %ymm1, %ymm2
- /* Finally, halve the result and reincorporate the sign */
- vxorps ATANHF_DATA(sHalf)(%rip), %ymm3, %ymm3
+ /* Finally, halve the result and reincorporate the sign. */
+ vxorps LOCAL_DATA(_Half)(%rip), %ymm3, %ymm3
vmulps %ymm2, %ymm3, %ymm2
vmovmskps %ymm14, %edx
testl %edx, %edx
vblendvps %ymm15, %ymm13, %ymm2, %ymm0
- /* Go to special inputs processing branch */
+ /* Go to special inputs processing branch. */
jne L(SPECIAL_VALUES_BRANCH)
- # LOE rbx rdx r12 r13 r14 r15 ymm0
+
/* No registers to restore on fast path. */
ret
/* Cold case. edx has 1s where there was a special value that
needs to be handled by a atanhf call. Optimize for code size
- more so than speed here. */
+ more so than speed here. */
L(SPECIAL_VALUES_BRANCH):
- # LOE rbx rdx r12 r13 r14 r15 ymm0 ymm8
- /* Use r13 to save/restore the stack. This allows us to use rbp as
- callee save register saving code size. */
+
+ /* Use r13 to save/restore the stack. This allows us to use rbp
+ as callee save register saving code size. */
pushq %r13
- cfi_adjust_cfa_offset(8)
- cfi_offset(r13, -16)
- /* Need to callee save registers to preserve state across tanhf calls.
- */
+ cfi_adjust_cfa_offset (8)
+ cfi_offset (r13, -16)
+ /* Need to callee save registers to preserve state across tanhf
+ calls. */
pushq %rbx
- cfi_adjust_cfa_offset(8)
- cfi_offset(rbx, -24)
+ cfi_adjust_cfa_offset (8)
+ cfi_offset (rbx, -24)
pushq %rbp
- cfi_adjust_cfa_offset(8)
- cfi_offset(rbp, -32)
+ cfi_adjust_cfa_offset (8)
+ cfi_offset (rbp, -32)
movq %rsp, %r13
- cfi_def_cfa_register(r13)
+ cfi_def_cfa_register (r13)
/* Align stack and make room for 2x ymm vectors. */
andq $-32, %rsp
@@ -217,16 +214,17 @@ L(SPECIAL_VALUES_BRANCH):
vzeroupper
- /* edx has 1s where there was a special value that needs to be handled
- by a atanhf call. */
+ /* edx has 1s where there was a special value that needs to be
+ handled by a atanhf call. */
movl %edx, %ebx
L(SPECIAL_VALUES_LOOP):
- # LOE rbx rbp r12 r13 r14 r15
- /* use rbp as index for special value that is saved across calls to
- atanhf. We technically don't need a callee save register here as offset
- to rsp is always [0, 28] 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. */
+
+ /* use rbp as index for special value that is saved across calls
+ to atanhf. We technically don't need a callee save register
+ here as offset to rsp is always [0, 28] 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
@@ -234,100 +232,52 @@ L(SPECIAL_VALUES_LOOP):
vmovss 32(%rsp, %rbp, 4), %xmm0
call atanhf@PLT
- /* 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. */
+ /* 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. */
vmovss %xmm0, (%rsp, %rbp, 4)
- blsrl %ebx, %ebx
+ blsrl %ebx, %ebx
jnz L(SPECIAL_VALUES_LOOP)
- # LOE r12 r13 r14 r15
-
/* All results have been written to (%rsp). */
vmovups (%rsp), %ymm0
/* Restore rsp. */
movq %r13, %rsp
- cfi_def_cfa_register(rsp)
+ cfi_def_cfa_register (rsp)
/* Restore callee save registers. */
popq %rbp
- cfi_adjust_cfa_offset(-8)
- cfi_restore(rbp)
+ cfi_adjust_cfa_offset (-8)
+ cfi_restore (rbp)
popq %rbx
- cfi_adjust_cfa_offset(-8)
- cfi_restore(rbp)
+ cfi_adjust_cfa_offset (-8)
+ cfi_restore (rbp)
popq %r13
- cfi_adjust_cfa_offset(-8)
- cfi_restore(r13)
+ cfi_adjust_cfa_offset (-8)
+ cfi_restore (r13)
ret
END(_ZGVdN8v_atanhf_avx2)
- .section .rodata, "a"
- .align 32
-#ifdef __svml_satanh_data_internal_typedef
-typedef unsigned int VUINT32;
-typedef struct{
- __declspec(align(32)) VUINT32 SgnMask[8][1];
- __declspec(align(32)) VUINT32 sOne[8][1];
- __declspec(align(32)) VUINT32 sTopMask12[8][1];
- __declspec(align(32)) VUINT32 TinyRange[8][1];
- __declspec(align(32)) VUINT32 iBrkValue[8][1];
- __declspec(align(32)) VUINT32 iOffExpoMask[8][1];
- __declspec(align(32)) VUINT32 sPoly[8][8][1];
- __declspec(align(32)) VUINT32 sLn2[8][1];
- __declspec(align(32)) VUINT32 sHalf[8][1];
-} __svml_satanh_data_internal;
-#endif
-__svml_satanh_data_internal:
- /* SgnMask */
- .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
- .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
- /* sOne = SP 1.0 */
+ .section .rodata.avx2, "a"
.align 32
- .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
- .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
- /* sTopMask12 */
- .align 32
- .long 0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000
- .long 0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000
- /* TinyRange */
- .align 32
- .long 0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000
- .long 0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000
- /* iBrkValue = SP 2/3 */
- .align 32
- .long 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab
- .long 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab
- /* iOffExpoMask = SP significand mask */
- .align 32
- .long 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff
- .long 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff
- /* sPoly[] = SP polynomial */
- .align 32
- .long 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed
- .long 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed /* 1.3820238411426544189453125e-01 P7 */
- .long 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3
- .long 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3 /* -1.5122179687023162841796875e-01 P6 */
- .long 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12
- .long 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12 /* 1.4042308926582336425781250e-01 P5 */
- .long 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37
- .long 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37 /* -1.6472326219081878662109375e-01 P4 */
- .long 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190
- .long 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190 /* 2.0007920265197753906250000e-01 P3 */
- .long 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e
- .long 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e /* -2.5004237890243530273437500e-01 P2 */
- .long 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94
- .long 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94 /* 3.3333265781402587890625000e-01 P1 */
- .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000
- .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 /* -5.0000000000000000000000000e-01 P0 */
- /* sLn2 = SP ln(2) */
- .align 32
- .long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218
- .long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218
- /* sHalf */
- .align 32
- .long 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000
- .long 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000
- .align 32
- .type __svml_satanh_data_internal, @object
- .size __svml_satanh_data_internal, .-__svml_satanh_data_internal
+
+LOCAL_DATA_NAME:
+ DATA_VEC (LOCAL_DATA_NAME, _TinyRange, 0x0C000000)
+ /* _Poly[] = SP polynomial. */
+ /* 1.3820238411426544189453125e-01 P7. */
+ DATA_VEC (LOCAL_DATA_NAME, _Poly_1, 0x3e0d84ed)
+ /* -1.5122179687023162841796875e-01 P6. */
+ DATA_VEC (LOCAL_DATA_NAME, _Poly_2, 0xbe1ad9e3)
+ /* 1.4042308926582336425781250e-01 P5. */
+ DATA_VEC (LOCAL_DATA_NAME, _Poly_3, 0x3e0fcb12)
+ /* -1.6472326219081878662109375e-01 P4. */
+ DATA_VEC (LOCAL_DATA_NAME, _Poly_4, 0xbe28ad37)
+ /* 2.0007920265197753906250000e-01 P3. */
+ DATA_VEC (LOCAL_DATA_NAME, _Poly_5, 0x3e4ce190)
+ /* -2.5004237890243530273437500e-01 P2. */
+ DATA_VEC (LOCAL_DATA_NAME, _Poly_6, 0xbe80058e)
+ /* 3.3333265781402587890625000e-01 P1. */
+ DATA_VEC (LOCAL_DATA_NAME, _Poly_7, 0x3eaaaa94)
+ DATA_VEC (LOCAL_DATA_NAME, _Half, 0x3F000000)
+ .type LOCAL_DATA_NAME, @object
+ .size LOCAL_DATA_NAME, .-LOCAL_DATA_NAME
--
2.34.1
next prev parent reply other threads:[~2022-12-07 8:53 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-12-07 8:52 [PATCH v1 01/27] x86/fpu: Create helper file for common data macros Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 02/27] x86/fpu: Add file for common data used across svml_s_*_avx2.S files Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 03/27] x86/fpu: Add file for common data used across svml_s_*_avx512.S files Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 04/27] x86/fpu: Add file for common data used across svml_s_*_sse4.S files Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 05/27] x86/fpu: Build common data files for svml_s_*_{avx512,avx2,sse4}.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 06/27] x86/fpu: Update rodata usage in svml_s_tanhf_*_{avx2,sse4} Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 07/27] x86/fpu: Update rodata usage in svml_s_tanhf16_core_avx512.S Noah Goldstein
2022-12-16 17:05 ` H.J. Lu
2022-12-16 18:17 ` Noah Goldstein
2022-12-16 21:37 ` H.J. Lu
2022-12-16 21:51 ` Noah Goldstein
2022-12-16 22:01 ` H.J. Lu
2022-12-16 22:54 ` Sunil Pandey
2023-06-27 18:23 ` Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 08/27] x86/fpu: Update rodata usage in svml_s_atanhf16_core_avx512.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 09/27] x86/fpu: Update rodata usage in svml_s_atanhf4_core_sse4.S Noah Goldstein
2022-12-07 8:52 ` Noah Goldstein [this message]
2022-12-07 8:52 ` [PATCH v1 11/27] x86/fpu: Optimize svml_s_atanf16_core_avx512.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 12/27] x86/fpu: Optimize svml_s_atanf4_core_sse4.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 13/27] x86/fpu: Optimize svml_s_atanf8_core_avx2.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 14/27] x86/fpu: Add common rodata file for svml_s_tanf_*_{avx512,avx2,sse4}.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 15/27] x86/fpu: Optimize svml_s_tanf16_core_avx512.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 16/27] x86/fpu: Optimize svml_s_tanf4_core_sse4.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 17/27] x86/fpu: Optimize svml_s_tanf8_core_avx2.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 18/27] x86/fpu: Optimize svml_s_log10f16_core_avx512.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 19/27] x86/fpu: Optimize svml_s_log10f4_core_sse4.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 20/27] x86/fpu: Optimize svml_s_log10f8_core_avx2.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 21/27] x86/fpu: Optimize svml_s_log2f16_core_avx512.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 22/27] x86/fpu: Optimize svml_s_log2f4_core_sse4.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 23/27] x86/fpu: Optimize svml_s_log2f8_core_avx2.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 24/27] x86/fpu: Optimize svml_s_logf16_core_avx512.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 25/27] x86/fpu: Optimize svml_s_logf4_core_sse4.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 26/27] x86/fpu: Optimize svml_s_logf8_core_avx2.S Noah Goldstein
2022-12-07 8:52 ` [PATCH v1 27/27] x86/fpu: Remove unused svml_s_logf_data.S file Noah Goldstein
2022-12-07 23:53 ` [PATCH v1 01/27] x86/fpu: Create helper file for common data macros H.J. Lu
2022-12-08 0:13 ` Noah Goldstein
2022-12-08 0:22 ` H.J. Lu
2022-12-08 0:46 ` Noah Goldstein
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=20221207085236.1424424-10-goldstein.w.n@gmail.com \
--to=goldstein.w.n@gmail.com \
--cc=andrey.kolesov@intel.com \
--cc=carlos@systemhalted.org \
--cc=hjl.tools@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).