Merge remote-tracking branch 'remotes/rth-gitlab/tags/pull-fpu-20210603' into staging

Finish conversion of float128 and floatx80 to FloatParts.
Implement float128_muladd and float128_{min,max}*.
Optimize int-to-float conversion with hard-float.

# gpg: Signature made Thu 03 Jun 2021 22:13:10 BST
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth-gitlab/tags/pull-fpu-20210603: (29 commits)
  softfloat: Use hard-float for {u}int64_to_float{32,64}
  tests/fp: Enable more tests
  softfloat: Convert modrem operations to FloatParts
  softfloat: Move floatN_log2 to softfloat-parts.c.inc
  softfloat: Convert float32_exp2 to FloatParts
  softfloat: Convert floatx80 compare to FloatParts
  softfloat: Convert floatx80_scalbn to FloatParts
  softfloat: Convert floatx80 to integer to FloatParts
  softfloat: Convert floatx80 float conversions to FloatParts
  softfloat: Convert integer to floatx80 to FloatParts
  softfloat: Convert floatx80_round_to_int to FloatParts
  softfloat: Convert floatx80_round to FloatParts
  softfloat: Convert floatx80_sqrt to FloatParts
  softfloat: Convert floatx80_div to FloatParts
  softfloat: Convert floatx80_mul to FloatParts
  softfloat: Convert floatx80_add/sub to FloatParts
  tests/fp/fp-test: Reverse order of floatx80 precision tests
  softfloat: Adjust parts_uncanon_normal for floatx80
  softfloat: Introduce Floatx80RoundPrec
  softfloat: Reduce FloatFmt
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 143 insertions, 13 deletions

diff --git a/tests/fp/fp-test-log2.c b/tests/fp/fp-test-log2.c
new file mode 100644
index 0000000000..4eae93eb7c
--- /dev/null
+++ b/tests/fp/fp-test-log2.c
@@ -0,0 +1,118 @@
+/*
+ * fp-test-log2.c - test QEMU's softfloat log2
+ *
+ * Copyright (C) 2020, Linaro, Ltd.
+ *
+ * License: GNU GPL, version 2 or later.
+ *   See the COPYING file in the top-level directory.
+ */
+#ifndef HW_POISON_H
+#error Must define HW_POISON_H to work around TARGET_* poisoning
+#endif
+
+#include "qemu/osdep.h"
+#include "qemu/cutils.h"
+#include <math.h>
+#include "fpu/softfloat.h"
+
+typedef union {
+    double d;
+    float64 i;
+} ufloat64;
+
+static int errors;
+
+static void compare(ufloat64 test, ufloat64 real, ufloat64 soft, bool exact)
+{
+    int msb;
+    uint64_t ulp = UINT64_MAX;
+
+    if (real.i == soft.i) {
+        return;
+    }
+    msb = 63 - __builtin_clzll(real.i ^ soft.i);
+
+    if (msb < 52) {
+        if (real.i > soft.i) {
+            ulp = real.i - soft.i;
+        } else {
+            ulp = soft.i - real.i;
+        }
+    }
+
+    /* glibc allows 3 ulp error in its libm-test-ulps; allow 4 here */
+    if (!exact && ulp <= 4) {
+        return;
+    }
+
+    printf("test: %016" PRIx64 "  %+.13a\n"
+           "  sf: %016" PRIx64 "  %+.13a\n"
+           "libm: %016" PRIx64 "  %+.13a\n",
+           test.i, test.d, soft.i, soft.d, real.i, real.d);
+
+    if (msb == 63) {
+        printf("Error in sign!\n\n");
+    } else if (msb >= 52) {
+        printf("Error in exponent: %d\n\n",
+               (int)(soft.i >> 52) - (int)(real.i >> 52));
+    } else {
+        printf("Error in fraction: %" PRIu64 " ulp\n\n", ulp);
+    }
+
+    if (++errors == 20) {
+        exit(1);
+    }
+}
+
+int main(int ac, char **av)
+{
+    ufloat64 test, real, soft;
+    float_status qsf = {0};
+    int i;
+
+    set_float_rounding_mode(float_round_nearest_even, &qsf);
+
+    test.d = 0.0;
+    real.d = -__builtin_inf();
+    soft.i = float64_log2(test.i, &qsf);
+    compare(test, real, soft, true);
+
+    test.d = 1.0;
+    real.d = 0.0;
+    soft.i = float64_log2(test.i, &qsf);
+    compare(test, real, soft, true);
+
+    test.d = 2.0;
+    real.d = 1.0;
+    soft.i = float64_log2(test.i, &qsf);
+    compare(test, real, soft, true);
+
+    test.d = 4.0;
+    real.d = 2.0;
+    soft.i = float64_log2(test.i, &qsf);
+    compare(test, real, soft, true);
+
+    test.d = 0x1p64;
+    real.d = 64.0;
+    soft.i = float64_log2(test.i, &qsf);
+    compare(test, real, soft, true);
+
+    test.d = __builtin_inf();
+    real.d = __builtin_inf();
+    soft.i = float64_log2(test.i, &qsf);
+    compare(test, real, soft, true);
+
+    for (i = 0; i < 10000; ++i) {
+        test.d = drand48() + 1.0;    /* [1.0, 2.0) */
+        real.d = log2(test.d);
+        soft.i = float64_log2(test.i, &qsf);
+        compare(test, real, soft, false);
+
+        test.d = drand48() * 100;    /* [0.0, 100) */
+        real.d = log2(test.d);
+        soft.i = float64_log2(test.i, &qsf);
+        compare(test, real, soft, false);
+    }
+
+    return 0;
+}
diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c
index ff131afbde..352dd71c44 100644
--- a/tests/fp/fp-test.c
+++ b/tests/fp/fp-test.c
@@ -963,18 +963,21 @@ static void QEMU_NORETURN run_test(void)
             verCases_usesExact = !!(attrs & FUNC_ARG_EXACT);
 
             for (k = 0; k < 3; k++) {
-                int prec80 = 32;
+                FloatX80RoundPrec qsf_prec80 = floatx80_precision_x;
+                int prec80 = 80;
                 int l;
 
                 if (k == 1) {
                     prec80 = 64;
+                    qsf_prec80 = floatx80_precision_d;
                 } else if (k == 2) {
-                    prec80 = 80;
+                    prec80 = 32;
+                    qsf_prec80 = floatx80_precision_s;
                 }
 
                 verCases_roundingPrecision = 0;
                 slow_extF80_roundingPrecision = prec80;
-                qsf.floatx80_rounding_precision = prec80;
+                qsf.floatx80_rounding_precision = qsf_prec80;
 
                 if (attrs & FUNC_EFF_ROUNDINGPRECISION) {
                     verCases_roundingPrecision = prec80;
diff --git a/tests/fp/meson.build b/tests/fp/meson.build
index 1c3eee9955..07e2cdc8d2 100644
--- a/tests/fp/meson.build
+++ b/tests/fp/meson.build
@@ -556,7 +556,9 @@ softfloat_conv_tests = {
                       'extF80_to_f64 extF80_to_f128 ' +
                       'f128_to_f16',
     'int-to-float': 'i32_to_f16 i64_to_f16 i32_to_f32 i64_to_f32 ' +
-                    'i32_to_f64 i64_to_f64 i32_to_f128 i64_to_f128',
+                    'i32_to_f64 i64_to_f64 ' +
+                    'i32_to_extF80 i64_to_extF80 ' +
+                    'i32_to_f128 i64_to_f128',
     'uint-to-float': 'ui32_to_f16 ui64_to_f16 ui32_to_f32 ui64_to_f32 ' +
                      'ui32_to_f64 ui64_to_f64 ui64_to_f128 ' +
                      'ui32_to_extF80 ui64_to_extF80',
@@ -581,7 +583,7 @@ softfloat_conv_tests = {
                      'extF80_to_ui64 extF80_to_ui64_r_minMag ' +
                      'f128_to_ui64 f128_to_ui64_r_minMag',
     'round-to-integer': 'f16_roundToInt f32_roundToInt ' +
-                        'f64_roundToInt f128_roundToInt'
+                        'f64_roundToInt extF80_roundToInt f128_roundToInt'
 }
 softfloat_tests = {
     'eq_signaling' : 'compare',
@@ -602,24 +604,20 @@ fptest_args = ['-s', '-l', '1']
 fptest_rounding_args = ['-r', 'all']
 
 # Conversion Routines:
-# FIXME: i32_to_extF80 (broken), i64_to_extF80 (broken)
-#        extF80_roundToInt (broken)
 foreach k, v : softfloat_conv_tests
   test('fp-test-' + k, fptest,
        args: fptest_args + fptest_rounding_args + v.split(),
        suite: ['softfloat', 'softfloat-conv'])
 endforeach
 
-# FIXME: extF80_{lt_quiet, rem} (broken),
-#        extF80_{mulAdd} (missing)
 foreach k, v : softfloat_tests
-  extF80_broken = ['lt_quiet', 'rem'].contains(k)
   test('fp-test-' + k, fptest,
        args: fptest_args + fptest_rounding_args +
-             ['f16_' + k, 'f32_' + k, 'f64_' + k, 'f128_' + k] +
-             (extF80_broken ? [] : ['extF80_' + k]),
+             ['f16_' + k, 'f32_' + k, 'f64_' + k, 'f128_' + k, 'extF80_' + k],
        suite: ['softfloat', 'softfloat-' + v])
 endforeach
+
+# FIXME: extF80_{mulAdd} (missing)
 test('fp-test-mulAdd', fptest,
      # no fptest_rounding_args
      args: fptest_args +
@@ -634,3 +632,14 @@ fpbench = executable(
   include_directories: [sfinc, include_directories(tfdir)],
   c_args: fpcflags,
 )
+
+fptestlog2 = executable(
+  'fp-test-log2',
+  ['fp-test-log2.c', '../../fpu/softfloat.c'],
+  link_with: [libsoftfloat],
+  dependencies: [qemuutil],
+  include_directories: [sfinc],
+  c_args: fpcflags,
+)
+test('fp-test-log2', fptestlog2,
+     suite: ['softfloat', 'softfloat-ops'])
diff --git a/tests/fp/wrap.c.inc b/tests/fp/wrap.c.inc
index cb1bb77e4c..9ff884c140 100644
--- a/tests/fp/wrap.c.inc
+++ b/tests/fp/wrap.c.inc
@@ -643,7 +643,7 @@ WRAP_CMP80(qemu_extF80M_eq, floatx80_eq_quiet)
 WRAP_CMP80(qemu_extF80M_le, floatx80_le)
 WRAP_CMP80(qemu_extF80M_lt, floatx80_lt)
 WRAP_CMP80(qemu_extF80M_le_quiet, floatx80_le_quiet)
-WRAP_CMP80(qemu_extF80M_lt_quiet, floatx80_le_quiet)
+WRAP_CMP80(qemu_extF80M_lt_quiet, floatx80_lt_quiet)
 #undef WRAP_CMP80
 
 #define WRAP_CMP128(name, func)                                         \