From: Alex Bennée <alex.bennee@linaro.org>

Balton discovered that asserts for the extract/deposit calls had a
significant impact on a lame benchmark on qemu-ppc. Replicating with:

  ./qemu-ppc64 ~/lsrc/tests/lame.git-svn/builds/ppc64/frontend/lame \
    -h pts-trondheim-3.wav pts-trondheim-3.mp3

showed up the pack/unpack routines not eliding the assert checks as it
should have done causing them to prominently figure in the profile:

  11.44%  qemu-ppc64  qemu-ppc64               [.] unpack_raw64.isra.0
  11.03%  qemu-ppc64  qemu-ppc64               [.] parts64_uncanon_normal
   8.26%  qemu-ppc64  qemu-ppc64               [.] helper_compute_fprf_float64
   6.75%  qemu-ppc64  qemu-ppc64               [.] do_float_check_status
   5.34%  qemu-ppc64  qemu-ppc64               [.] parts64_muladd
   4.75%  qemu-ppc64  qemu-ppc64               [.] pack_raw64.isra.0
   4.38%  qemu-ppc64  qemu-ppc64               [.] parts64_canonicalize
   3.62%  qemu-ppc64  qemu-ppc64               [.] float64r32_round_pack_canonical

After this patch the same test runs 31 seconds faster with a profile
where the generated code dominates more:

+   14.12%     0.00%  qemu-ppc64  [unknown]                [.] 0x0000004000619420
+   13.30%     0.00%  qemu-ppc64  [unknown]                [.] 0x0000004000616850
+   12.58%    12.19%  qemu-ppc64  qemu-ppc64               [.] parts64_uncanon_normal
+   10.62%     0.00%  qemu-ppc64  [unknown]                [.] 0x000000400061bf70
+    9.91%     9.73%  qemu-ppc64  qemu-ppc64               [.] helper_compute_fprf_float64
+    7.84%     7.82%  qemu-ppc64  qemu-ppc64               [.] do_float_check_status
+    6.47%     5.78%  qemu-ppc64  qemu-ppc64               [.] parts64_canonicalize.constprop.0
+    6.46%     0.00%  qemu-ppc64  [unknown]                [.] 0x0000004000620130
+    6.42%     0.00%  qemu-ppc64  [unknown]                [.] 0x0000004000619400
+    6.17%     6.04%  qemu-ppc64  qemu-ppc64               [.] parts64_muladd
+    5.85%     0.00%  qemu-ppc64  [unknown]                [.] 0x00000040006167e0
+    5.74%     0.00%  qemu-ppc64  [unknown]                [.] 0x0000b693fcffffd3
+    5.45%     4.78%  qemu-ppc64  qemu-ppc64               [.] float64r32_round_pack_canonical

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <ec9cfe5a-d5f2-466d-34dc-c35817e7e010@linaro.org>
[AJB: Patchified rth's suggestion]
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Cc: BALATON Zoltan <balaton@eik.bme.hu>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Tested-by: BALATON Zoltan <balaton@eik.bme.hu>
Message-Id: <20230523131107.3680641-1-alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 fpu/softfloat.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index 108f9cb224..42e6c188b4 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -593,27 +593,27 @@ static void unpack_raw64(FloatParts64 *r, const FloatFmt *fmt, uint64_t raw)
     };
 }
 
-static inline void float16_unpack_raw(FloatParts64 *p, float16 f)
+static void QEMU_FLATTEN float16_unpack_raw(FloatParts64 *p, float16 f)
 {
     unpack_raw64(p, &float16_params, f);
 }
 
-static inline void bfloat16_unpack_raw(FloatParts64 *p, bfloat16 f)
+static void QEMU_FLATTEN bfloat16_unpack_raw(FloatParts64 *p, bfloat16 f)
 {
     unpack_raw64(p, &bfloat16_params, f);
 }
 
-static inline void float32_unpack_raw(FloatParts64 *p, float32 f)
+static void QEMU_FLATTEN float32_unpack_raw(FloatParts64 *p, float32 f)
 {
     unpack_raw64(p, &float32_params, f);
 }
 
-static inline void float64_unpack_raw(FloatParts64 *p, float64 f)
+static void QEMU_FLATTEN float64_unpack_raw(FloatParts64 *p, float64 f)
 {
     unpack_raw64(p, &float64_params, f);
 }
 
-static void floatx80_unpack_raw(FloatParts128 *p, floatx80 f)
+static void QEMU_FLATTEN floatx80_unpack_raw(FloatParts128 *p, floatx80 f)
 {
     *p = (FloatParts128) {
         .cls = float_class_unclassified,
@@ -623,7 +623,7 @@ static void floatx80_unpack_raw(FloatParts128 *p, floatx80 f)
     };
 }
 
-static void float128_unpack_raw(FloatParts128 *p, float128 f)
+static void QEMU_FLATTEN float128_unpack_raw(FloatParts128 *p, float128 f)
 {
     const int f_size = float128_params.frac_size - 64;
     const int e_size = float128_params.exp_size;
@@ -650,27 +650,27 @@ static uint64_t pack_raw64(const FloatParts64 *p, const FloatFmt *fmt)
     return ret;
 }
 
-static inline float16 float16_pack_raw(const FloatParts64 *p)
+static float16 QEMU_FLATTEN float16_pack_raw(const FloatParts64 *p)
 {
     return make_float16(pack_raw64(p, &float16_params));
 }
 
-static inline bfloat16 bfloat16_pack_raw(const FloatParts64 *p)
+static bfloat16 QEMU_FLATTEN bfloat16_pack_raw(const FloatParts64 *p)
 {
     return pack_raw64(p, &bfloat16_params);
 }
 
-static inline float32 float32_pack_raw(const FloatParts64 *p)
+static float32 QEMU_FLATTEN float32_pack_raw(const FloatParts64 *p)
 {
     return make_float32(pack_raw64(p, &float32_params));
 }
 
-static inline float64 float64_pack_raw(const FloatParts64 *p)
+static float64 QEMU_FLATTEN float64_pack_raw(const FloatParts64 *p)
 {
     return make_float64(pack_raw64(p, &float64_params));
 }
 
-static float128 float128_pack_raw(const FloatParts128 *p)
+static float128 QEMU_FLATTEN float128_pack_raw(const FloatParts128 *p)
 {
     const int f_size = float128_params.frac_size - 64;
     const int e_size = float128_params.exp_size;
-- 
2.34.1