qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: alex.bennee@linaro.org, david@redhat.com
Subject: [PATCH 41/72] softfloat: Introduce sh[lr]_double primitives
Date: Fri,  7 May 2021 18:47:31 -0700	[thread overview]
Message-ID: <20210508014802.892561-42-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210508014802.892561-1-richard.henderson@linaro.org>

Have x86_64 assembly for them, with a fallback.
This avoids shuffling values through %cl in the x86 case.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 include/fpu/softfloat-macros.h |  36 ++++++++++++
 fpu/softfloat.c                | 102 +++++++++++++++++++++++++--------
 2 files changed, 115 insertions(+), 23 deletions(-)

diff --git a/include/fpu/softfloat-macros.h b/include/fpu/softfloat-macros.h
index 672c1db555..ec4e27a595 100644
--- a/include/fpu/softfloat-macros.h
+++ b/include/fpu/softfloat-macros.h
@@ -85,6 +85,42 @@ this code that are retained.
 #include "fpu/softfloat-types.h"
 #include "qemu/host-utils.h"
 
+/**
+ * shl_double: double-word merging left shift
+ * @l: left or most-significant word
+ * @r: right or least-significant word
+ * @c: shift count
+ *
+ * Shift @l left by @c bits, shifting in bits from @r.
+ */
+static inline uint64_t shl_double(uint64_t l, uint64_t r, int c)
+{
+#if defined(__x86_64__)
+    asm("shld %b2, %1, %0" : "+r"(l) : "r"(r), "ci"(c));
+    return l;
+#else
+    return c ? (l << c) | (r >> (64 - c)) : l;
+#endif
+}
+
+/**
+ * shr_double: double-word merging right shift
+ * @l: left or most-significant word
+ * @r: right or least-significant word
+ * @c: shift count
+ *
+ * Shift @r right by @c bits, shifting in bits from @l.
+ */
+static inline uint64_t shr_double(uint64_t l, uint64_t r, int c)
+{
+#if defined(__x86_64__)
+    asm("shrd %b2, %1, %0" : "+r"(r) : "r"(l), "ci"(c));
+    return r;
+#else
+    return c ? (r >> c) | (l << (64 - c)) : r;
+#endif
+}
+
 /*----------------------------------------------------------------------------
 | Shifts `a' right by the number of bits given in `count'.  If any nonzero
 | bits are shifted off, they are ``jammed'' into the least significant bit of
diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index a9ee8498ae..a42c297828 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -956,15 +956,12 @@ static int frac128_normalize(FloatParts128 *a)
 {
     if (a->frac_hi) {
         int shl = clz64(a->frac_hi);
-        if (shl) {
-            int shr = 64 - shl;
-            a->frac_hi = (a->frac_hi << shl) | (a->frac_lo >> shr);
-            a->frac_lo = (a->frac_lo << shl);
-        }
+        a->frac_hi = shl_double(a->frac_hi, a->frac_lo, shl);
+        a->frac_lo <<= shl;
         return shl;
     } else if (a->frac_lo) {
         int shl = clz64(a->frac_lo);
-        a->frac_hi = (a->frac_lo << shl);
+        a->frac_hi = a->frac_lo << shl;
         a->frac_lo = 0;
         return shl + 64;
     }
@@ -975,7 +972,7 @@ static int frac256_normalize(FloatParts256 *a)
 {
     uint64_t a0 = a->frac_hi, a1 = a->frac_hm;
     uint64_t a2 = a->frac_lm, a3 = a->frac_lo;
-    int ret, shl, shr;
+    int ret, shl;
 
     if (likely(a0)) {
         shl = clz64(a0);
@@ -1005,11 +1002,10 @@ static int frac256_normalize(FloatParts256 *a)
         ret += shl;
     }
 
-    shr = -shl & 63;
-    a0 = (a0 << shl) | (a1 >> shr);
-    a1 = (a1 << shl) | (a2 >> shr);
-    a2 = (a2 << shl) | (a3 >> shr);
-    a3 = (a3 << shl);
+    a0 = shl_double(a0, a1, shl);
+    a1 = shl_double(a1, a2, shl);
+    a2 = shl_double(a2, a3, shl);
+    a3 <<= shl;
 
  done:
     a->frac_hi = a0;
@@ -1028,7 +1024,20 @@ static void frac64_shl(FloatParts64 *a, int c)
 
 static void frac128_shl(FloatParts128 *a, int c)
 {
-    shift128Left(a->frac_hi, a->frac_lo, c, &a->frac_hi, &a->frac_lo);
+    uint64_t a0 = a->frac_hi, a1 = a->frac_lo;
+
+    if (c & 64) {
+        a0 = a1, a1 = 0;
+    }
+
+    c &= 63;
+    if (c) {
+        a0 = shl_double(a0, a1, c);
+        a1 = a1 << c;
+    }
+
+    a->frac_hi = a0;
+    a->frac_lo = a1;
 }
 
 #define frac_shl(A, C)  FRAC_GENERIC_64_128(shl, A)(A, C)
@@ -1040,19 +1049,68 @@ static void frac64_shr(FloatParts64 *a, int c)
 
 static void frac128_shr(FloatParts128 *a, int c)
 {
-    shift128Right(a->frac_hi, a->frac_lo, c, &a->frac_hi, &a->frac_lo);
+    uint64_t a0 = a->frac_hi, a1 = a->frac_lo;
+
+    if (c & 64) {
+        a1 = a0, a0 = 0;
+    }
+
+    c &= 63;
+    if (c) {
+        a1 = shr_double(a0, a1, c);
+        a0 = a0 >> c;
+    }
+
+    a->frac_hi = a0;
+    a->frac_lo = a1;
 }
 
 #define frac_shr(A, C)  FRAC_GENERIC_64_128(shr, A)(A, C)
 
 static void frac64_shrjam(FloatParts64 *a, int c)
 {
-    shift64RightJamming(a->frac, c, &a->frac);
+    uint64_t a0 = a->frac;
+
+    if (likely(c != 0)) {
+        if (likely(c < 64)) {
+            a0 = (a0 >> c) | (shr_double(a0, 0, c) != 0);
+        } else {
+            a0 = a0 != 0;
+        }
+        a->frac = a0;
+    }
 }
 
 static void frac128_shrjam(FloatParts128 *a, int c)
 {
-    shift128RightJamming(a->frac_hi, a->frac_lo, c, &a->frac_hi, &a->frac_lo);
+    uint64_t a0 = a->frac_hi, a1 = a->frac_lo;
+    uint64_t sticky = 0;
+
+    if (unlikely(c == 0)) {
+        return;
+    } else if (likely(c < 64)) {
+        /* nothing */
+    } else if (likely(c < 128)) {
+        sticky = a1;
+        a1 = a0;
+        a0 = 0;
+        c &= 63;
+        if (c == 0) {
+            goto done;
+        }
+    } else {
+        sticky = a0 | a1;
+        a0 = a1 = 0;
+        goto done;
+    }
+
+    sticky |= shr_double(a1, 0, c);
+    a1 = shr_double(a0, a1, c);
+    a0 = a0 >> c;
+
+ done:
+    a->frac_lo = a1 | (sticky != 0);
+    a->frac_hi = a0;
 }
 
 static void frac256_shrjam(FloatParts256 *a, int c)
@@ -1060,7 +1118,6 @@ static void frac256_shrjam(FloatParts256 *a, int c)
     uint64_t a0 = a->frac_hi, a1 = a->frac_hm;
     uint64_t a2 = a->frac_lm, a3 = a->frac_lo;
     uint64_t sticky = 0;
-    int invc;
 
     if (unlikely(c == 0)) {
         return;
@@ -1085,12 +1142,11 @@ static void frac256_shrjam(FloatParts256 *a, int c)
         goto done;
     }
 
-    invc = -c & 63;
-    sticky |= a3 << invc;
-    a3 = (a3 >> c) | (a2 << invc);
-    a2 = (a2 >> c) | (a1 << invc);
-    a1 = (a1 >> c) | (a0 << invc);
-    a0 = (a0 >> c);
+    sticky |= shr_double(a3, 0, c);
+    a3 = shr_double(a2, a3, c);
+    a2 = shr_double(a1, a2, c);
+    a1 = shr_double(a0, a1, c);
+    a0 = a0 >> c;
 
  done:
     a->frac_lo = a3 | (sticky != 0);
-- 
2.25.1



  parent reply	other threads:[~2021-05-08  2:24 UTC|newest]

Thread overview: 151+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-08  1:46 [PATCH 00/72] Convert floatx80 and float128 to FloatParts Richard Henderson
2021-05-08  1:46 ` [PATCH 01/72] qemu/host-utils: Use __builtin_bitreverseN Richard Henderson
2021-05-10  9:59   ` Alex Bennée
2021-05-11  9:41   ` David Hildenbrand
2021-05-08  1:46 ` [PATCH 02/72] qemu/host-utils: Add wrappers for overflow builtins Richard Henderson
2021-05-10 10:22   ` Alex Bennée
2021-05-08  1:46 ` [PATCH 03/72] qemu/host-utils: Add wrappers for carry builtins Richard Henderson
2021-05-10 12:57   ` Alex Bennée
2021-05-11 20:10     ` Richard Henderson
2021-05-12 11:17       ` Alex Bennée
2021-05-08  1:46 ` [PATCH 04/72] accel/tcg: Use add/sub overflow routines in tcg-runtime-gvec.c Richard Henderson
2021-05-09  8:43   ` Philippe Mathieu-Daudé
2021-05-10 13:02   ` Alex Bennée
2021-05-11  9:46   ` David Hildenbrand
2021-05-08  1:46 ` [PATCH 05/72] tests/fp: add quad support to the benchmark utility Richard Henderson
2021-05-11 10:01   ` David Hildenbrand
2021-05-08  1:46 ` [PATCH 06/72] softfloat: Move the binary point to the msb Richard Henderson
2021-05-10 13:36   ` Alex Bennée
2021-05-08  1:46 ` [PATCH 07/72] softfloat: Inline float_raise Richard Henderson
2021-05-09  8:32   ` Philippe Mathieu-Daudé
2021-05-11 10:04   ` David Hildenbrand
2021-05-08  1:46 ` [PATCH 08/72] softfloat: Use float_raise in more places Richard Henderson
2021-05-09  8:34   ` Philippe Mathieu-Daudé
2021-05-11 10:06   ` David Hildenbrand
2021-05-08  1:46 ` [PATCH 09/72] softfloat: Tidy a * b + inf return Richard Henderson
2021-05-08  1:47 ` [PATCH 10/72] softfloat: Add float_cmask and constants Richard Henderson
2021-05-08  1:47 ` [PATCH 11/72] softfloat: Use return_nan in float_to_float Richard Henderson
2021-05-10 15:10   ` Alex Bennée
2021-05-11 10:10   ` David Hildenbrand
2021-05-08  1:47 ` [PATCH 12/72] softfloat: fix return_nan vs default_nan_mode Richard Henderson
2021-05-10 15:12   ` Alex Bennée
2021-05-11 10:12   ` David Hildenbrand
2021-05-08  1:47 ` [PATCH 13/72] target/mips: Set set_default_nan_mode with set_snan_bit_is_one Richard Henderson
2021-05-11  9:37   ` Alex Bennée
2021-05-11 10:16   ` David Hildenbrand
2021-05-08  1:47 ` [PATCH 14/72] softfloat: Do not produce a default_nan from parts_silence_nan Richard Henderson
2021-05-11 10:16   ` David Hildenbrand
2021-05-11 10:32   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 15/72] softfloat: Rename FloatParts to FloatParts64 Richard Henderson
2021-05-09  8:45   ` Philippe Mathieu-Daudé
2021-05-11 10:16   ` David Hildenbrand
2021-05-08  1:47 ` [PATCH 16/72] softfloat: Move type-specific pack/unpack routines Richard Henderson
2021-05-09  8:46   ` Philippe Mathieu-Daudé
2021-05-11 10:17   ` David Hildenbrand
2021-05-08  1:47 ` [PATCH 17/72] softfloat: Use pointers with parts_default_nan Richard Henderson
2021-05-11 10:22   ` David Hildenbrand
2021-05-11 20:19     ` Richard Henderson
2021-05-08  1:47 ` [PATCH 18/72] softfloat: Use pointers with unpack_raw Richard Henderson
2021-05-09  8:48   ` Philippe Mathieu-Daudé
2021-05-12 12:58   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 19/72] softfloat: Use pointers with ftype_unpack_raw Richard Henderson
2021-05-11 11:31   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 20/72] softfloat: Use pointers with pack_raw Richard Henderson
2021-05-11 11:32   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 21/72] softfloat: Use pointers with ftype_pack_raw Richard Henderson
2021-05-11 11:32   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 22/72] softfloat: Use pointers with ftype_unpack_canonical Richard Henderson
2021-05-11 13:54   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 23/72] softfloat: Use pointers with ftype_round_pack_canonical Richard Henderson
2021-05-11 13:55   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 24/72] softfloat: Use pointers with parts_silence_nan Richard Henderson
2021-05-11 13:56   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 25/72] softfloat: Rearrange FloatParts64 Richard Henderson
2021-05-11 13:57   ` Alex Bennée
2021-05-11 15:04     ` Richard Henderson
2021-05-12 11:08       ` Alex Bennée
2021-05-08  1:47 ` [PATCH 26/72] softfloat: Convert float128_silence_nan to parts Richard Henderson
2021-05-13  8:34   ` Alex Bennée
2021-05-13 12:25     ` Richard Henderson
2021-05-08  1:47 ` [PATCH 27/72] softfloat: Convert float128_default_nan " Richard Henderson
2021-05-13  8:56   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 28/72] softfloat: Move return_nan to softfloat-parts.c.inc Richard Henderson
2021-05-12 18:10   ` David Hildenbrand
2021-05-08  1:47 ` [PATCH 29/72] softfloat: Move pick_nan " Richard Henderson
2021-05-12 18:16   ` David Hildenbrand
2021-05-13 12:28     ` Richard Henderson
2021-05-08  1:47 ` [PATCH 30/72] softfloat: Move pick_nan_muladd " Richard Henderson
2021-05-12 18:18   ` David Hildenbrand
2021-05-08  1:47 ` [PATCH 31/72] softfloat: Move sf_canonicalize " Richard Henderson
2021-05-13  9:45   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 32/72] softfloat: Move round_canonical " Richard Henderson
2021-05-13  9:53   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 33/72] softfloat: Use uadd64_carry, usub64_borrow in softfloat-macros.h Richard Henderson
2021-05-13 10:00   ` Alex Bennée
2021-05-13 12:38     ` Richard Henderson
2021-05-08  1:47 ` [PATCH 34/72] softfloat: Move addsub_floats to softfloat-parts.c.inc Richard Henderson
2021-05-13 10:03   ` Alex Bennée
2021-05-13 10:05   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 35/72] softfloat: Implement float128_add/sub via parts Richard Henderson
2021-05-13 10:06   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 36/72] softfloat: Move mul_floats to softfloat-parts.c.inc Richard Henderson
2021-05-13 10:08   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 37/72] softfloat: Move muladd_floats " Richard Henderson
2021-05-13 10:43   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 38/72] softfloat: Use mulu64 for mul64To128 Richard Henderson
2021-05-08  1:47 ` [PATCH 39/72] softfloat: Use add192 in mul128To256 Richard Henderson
2021-05-13 10:49   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 40/72] softfloat: Tidy mul128By64To192 Richard Henderson
2021-05-13 10:50   ` Alex Bennée
2021-05-08  1:47 ` Richard Henderson [this message]
2021-05-13 10:59   ` [PATCH 41/72] softfloat: Introduce sh[lr]_double primitives Alex Bennée
2021-05-08  1:47 ` [PATCH 42/72] softfloat: Move div_floats to softfloat-parts.c.inc Richard Henderson
2021-05-13 11:02   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 43/72] softfloat: Split float_to_float Richard Henderson
2021-05-13 11:04   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 44/72] softfloat: Convert float-to-float conversions with float128 Richard Henderson
2021-05-13 11:17   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 45/72] softfloat: Move round_to_int to softfloat-parts.c.inc Richard Henderson
2021-05-13 14:10   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 46/72] softfloat: Move rount_to_int_and_pack " Richard Henderson
2021-05-13 14:11   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 47/72] softfloat: Move rount_to_uint_and_pack " Richard Henderson
2021-05-08  1:47 ` [PATCH 48/72] softfloat: Move int_to_float " Richard Henderson
2021-05-08  1:47 ` [PATCH 49/72] softfloat: Move uint_to_float " Richard Henderson
2021-05-08  1:47 ` [PATCH 50/72] softfloat: Move minmax_flags " Richard Henderson
2021-05-17 13:14   ` David Hildenbrand
2021-05-17 15:57     ` Richard Henderson
2021-05-08  1:47 ` [PATCH 51/72] softfloat: Move compare_floats " Richard Henderson
2021-05-08  1:47 ` [PATCH 52/72] softfloat: Move scalbn_decomposed " Richard Henderson
2021-05-08  1:47 ` [PATCH 53/72] softfloat: Move sqrt_float " Richard Henderson
2021-05-08  1:47 ` [PATCH 54/72] softfloat: Split out parts_uncanon_normal Richard Henderson
2021-05-08  1:47 ` [PATCH 55/72] softfloat: Reduce FloatFmt Richard Henderson
2021-05-08  1:47 ` [PATCH 56/72] softfloat: Introduce Floatx80RoundPrec Richard Henderson
2021-05-08  1:47 ` [PATCH 57/72] softfloat: Adjust parts_uncanon_normal for floatx80 Richard Henderson
2021-05-08  1:47 ` [PATCH 58/72] tests/fp/fp-test: Reverse order of floatx80 precision tests Richard Henderson
2021-05-13 14:12   ` Alex Bennée
2021-05-08  1:47 ` [PATCH 59/72] softfloat: Convert floatx80_add/sub to FloatParts Richard Henderson
2021-05-08  1:47 ` [PATCH 60/72] softfloat: Convert floatx80_mul " Richard Henderson
2021-05-08  1:47 ` [PATCH 61/72] softfloat: Convert floatx80_div " Richard Henderson
2021-05-08  1:47 ` [PATCH 62/72] softfloat: Convert floatx80_sqrt " Richard Henderson
2021-05-08  1:47 ` [PATCH 63/72] softfloat: Convert floatx80_round " Richard Henderson
2021-05-08  1:47 ` [PATCH 64/72] softfloat: Convert floatx80_round_to_int " Richard Henderson
2021-05-08  1:47 ` [PATCH 65/72] softfloat: Convert integer to floatx80 " Richard Henderson
2021-05-08  1:47 ` [PATCH 66/72] softfloat: Convert floatx80 float conversions " Richard Henderson
2021-05-08  1:47 ` [PATCH 67/72] softfloat: Convert floatx80 to integer " Richard Henderson
2021-05-08  1:47 ` [PATCH 68/72] softfloat: Convert floatx80_scalbn " Richard Henderson
2021-05-08  1:47 ` [PATCH 69/72] softfloat: Convert floatx80 compare " Richard Henderson
2021-05-08  1:48 ` [PATCH 70/72] softfloat: Convert float32_exp2 " Richard Henderson
2021-05-08  1:48 ` [PATCH 71/72] softfloat: Move floatN_log2 to softfloat-parts.c.inc Richard Henderson
2021-05-08  1:48 ` [PATCH 72/72] softfloat: Convert modrem operations to FloatParts Richard Henderson
2021-05-08  2:52 ` [PATCH 00/72] Convert floatx80 and float128 " no-reply
2021-05-10 13:36 ` Alex Bennée
2021-05-12  1:52   ` Richard Henderson
2021-05-12 11:22     ` Alex Bennée
2021-05-12 15:28       ` Richard Henderson
2021-05-12 16:47 ` Alex Bennée
2021-05-12 19:23 ` Alex Bennée
2021-05-13 11:49   ` Richard Henderson
2021-05-13 13:33     ` Alex Bennée
2021-05-13 23:54       ` Richard Henderson
2021-05-13 14:13 ` Alex Bennée

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=20210508014802.892561-42-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=alex.bennee@linaro.org \
    --cc=david@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --subject='Re: [PATCH 41/72] softfloat: Introduce sh[lr]_double primitives' \
    /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

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox