@@ -29,4 +29,6 @@ float64 float64_sqrt(float64 a, float_status *status);
int float64_compare(float64 a, float64 b, float_status *s);
int float64_compare_quiet(float64 a, float64 b, float_status *s);
+float64 float32_to_float64(float32, float_status *status);
+
#endif /* HOSTFLOAT_H */
@@ -334,7 +334,7 @@ int64_t float32_to_int64(float32, float_status *status);
uint64_t float32_to_uint64(float32, float_status *status);
uint64_t float32_to_uint64_round_to_zero(float32, float_status *status);
int64_t float32_to_int64_round_to_zero(float32, float_status *status);
-float64 float32_to_float64(float32, float_status *status);
+float64 soft_float32_to_float64(float32, float_status *status);
floatx80 float32_to_floatx80(float32, float_status *status);
float128 float32_to_float128(float32, float_status *status);
@@ -326,3 +326,17 @@ GEN_FPU_SQRT(float64_sqrt, float64, double, sqrt)
GEN_FPU_COMPARE(float32_compare, float32, float)
GEN_FPU_COMPARE(float64_compare, float64, double)
#undef GEN_FPU_COMPARE
+
+float64 float32_to_float64(float32 a, float_status *status)
+{
+ if (likely(float32_is_normal(a))) {
+ float f = *(float *)&a;
+ double r = f;
+
+ return *(float64 *)&r;
+ } else if (float32_is_zero(a)) {
+ return float64_set_sign(float64_zero, float32_is_neg(a));
+ } else {
+ return soft_float32_to_float64(a, status);
+ }
+}
@@ -3149,7 +3149,7 @@ float128 uint64_to_float128(uint64_t a, float_status *status)
| Arithmetic.
*----------------------------------------------------------------------------*/
-float64 float32_to_float64(float32 a, float_status *status)
+float64 soft_float32_to_float64(float32 a, float_status *status)
{
flag aSign;
int aExp;
Performance improvement for SPEC06fp for the last few commits: qemu-aarch64 SPEC06fp (test set) speedup over QEMU f6d81cdec8 Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz error bars: 95% confidence interval 5 +-+---+-----+----+-----+-----+-----+-----+----+-----+-----+-----+----+-----+-----+-----+-----+----+-----+---+-+ 4.5 +-+..........................+&&+...........................................................................+-+ 3.5 +-+................+++.......@@&...............+++............................................+++dsub +-+ 2 3 +-+....+++.++++++%%&=+......+@@&....+++...==+..&&=..........................................++&=+++++++ +-+ 2 +-+..%%@&+.%%@=++%%&=.......+%@&..%%@&+.%%@=++%%&=.++&&+.......++&=+.+++++.......+&&=.%%@&+.%%@= +%%@=++%%&=+-+ 1.5 +-+++$%@&+#$%@=+#$%&=##$%&**#$@&**#%@&**$%@=**$%&=##%@&**#+&&**#%@=**$%@=+++&&=##$@&**#%@&**#%@=*+f%@=*#$%&=+-+ 0 1 +-+**#%@&**$%@=**$%&=*#$%&**#$@&**#%@&**$%@=**$%&=*#$@&**#$@&**#%@=**$%@=*#$%&=*#$@&**#%@&**#%@=+sqr@=*#$%&=+-+ 0 +-+**#%@&**$%@=**$%&=*#$%&**#$@&**#%@&**$%@=**$%&=*#$@&**#$@&**#%@=**$%@=*#$%&=*#$@&**#%@&**#%@=*+cmp=*#$%&=+-+ 410.bw416.gam433.434.z435.436.cac437.lesli444.447.de450.so453454.ca459.GemsF465.tont470.lb4482.sph+f32f64ean png: https://imgur.com/5BErNz7 That is, a final geomean speedup of 2.21X. The floating point workloads from nbench show similar improvements: qemu-aarch64 NBench score; higher is better Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz 16 +-+-------------------+---------------------+----------------------+---------------------+-------------------+-+ 14 +-+..............................................====**............@@@&&&==**................................+-+ 12 +-+.........................................@@@@&&..=.*............@.@..&.=.*..................+before +-+ 10 +-+.........................................@..@.&..=.*............@.@..&.=.*............@@@&&&==***ub +-+ 8 +-+....................................$$$$%%..@.&..=.*............@.@..&.=.*............@.@..&+= +*ul +-+ 6 +-+...................@@@@&&===**..***##..$.%..@.&..=.*..++####$$%%%.@..&.=.*....####$$%%%.@..&+= +*iv +-+ 4 +-+............###$$$%%..@.&..=.*..*+*.#..$.%..@.&..=.*..***..#.$..%.@..&.=.*..***..#.$..%.@..&+= +*ma +-+ 2 +-+.........****.#..$.%..@.&..=.*..*.*.#..$.%..@.&..=.*..*.*..#.$..%.@..&.=.*..*.*..#.$..%.@..&+=+s*rt +-+ 0 +-+---------****##$$$%%@@@&&===**--***##$$$%%@@@&&===**--***###$$%%%@@&&&==**--***###$$%%%@@&&&==***mp-------+-+ FOURIER NEURAL NET LU DECOMPOSITION gmean +f32f64 png: https://imgur.com/KjLHumh That is, a ~2.6X speedup. [error bars here are just the standard deviation of just a few measurements; this explains the noisy results.] Results for the i386 target are very similar; the only major difference is that they're much more sensitive to the multiplication optimization, since the i386 target does not currently use floatX_muladd (aka fma). Below are the x86_64 SPEC06fp results, although note that they are from a development branch, so each bar does not match the patches in this, and the final numbers might be slightly different from those you'd get with these patches. qemu-x86_64 SPEC06fp (train set) speedup over QEMU f6d81cdec8 Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz error bars: 95% confidence interval 4 +-+---+-----+----+-----+-----+%%---+-----+----+-----+-----+-----+----+-----+-----+-----+-----+----+-----+---+-+ 3.5 +-+..........................$$%............................................................................+-+ 3 +-+............**$$$......+**#$%............**$$++..................................+add+sub++%%+sq+++ +-+ 2.5 +-+..+++.**##$%**#+$%......**#$%..+$$%..++%%**#$%%.............+++.**#$$%........$$%+**$$%+###$%is#$$% $$%%+-+ 1.5 +-+***#$%**.#$%**#.$%..$$%+**#$%***#$%**##$%**#$.%**#$%+++$$%***#$%**#+$%..$$++**#$%+fas$%path$%ul(0$%**#$ %+-+ 1 +-+*+*#$%**+#$%**#+$%**#$%+**#$%*+*#$%**+#$%**#$+%**#$%-**#$%*+*#$%**#+$%**#$%%**#$%+**+f%2 to %4+div%**#$+%+-+ 0.5 +-+*.*#$%**.#$%**#.$%**#$%.**#$%*.*#$%**.#$%**#$.%**#$%.**#$%*.*#$%**#.$%**#$.%**#$%.**#$%**.#$%**#.$%**#$.%+-+ 0 +-+***#$%**##$%**#$$%**#$%-**#$%***#$%**##$%**#$%%**#$%-**#$%***#$%**#$$%**#$%%**#$%-**#$%**##$%**#$$%**#$%%+-+ 410.bw416.gam433.434.z435.436.cac437.lesli444.447.de450.so453454.ca459.GemsF465.tont470.lb4482.sphinxgeomean png: https://imgur.com/MfvTb3H Two points are worth mentioning: - Special-casing 0-inputs for multiplication pays off handsomely (the same thing happens for FMA for targets that use it). I was surprised to see that some benchmarks (e.g. GemsFDTD) compute >99% of their multiplications with at least one operand being Zero (and this is without flush-to-zero!). - Avoiding comparisons via the host FPU (i.e. using soft_t ## _is_normal() instead of glibc's isnormal()) gives a small speedup. Finally, the same results using native execution time as the baseline, where we plot the slowdown instead of the speedup. We bring down the slowdown of SPEC06fp w.r.t. native from ~21X to ~10X: qemu-x86_64 SPEC06fp (train set) slowdown over native (lower is better) Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz error bars: 95% confidence interval 90 +-+---+-----+-----+----+-----+-----+-----+-----+-----+----+-----+-----+-----+-----+-----+----+-----+-----+---+-+ 80 +-+.......................+**................................................................................+-+ 70 +-+........................**........................................................+ before +-+ 50 +-+........................**........................................................+add+sub+mul+sqrt +-+ 40 +-+......+++...............**................................+++.....................+ +integer isinf +-+ 30 +-+**+...**+...............**#$%@**.........**+..............+**++.............**+...+fast path mul(0++** +-+ 10 +-+**#$%@**#$%@**$$@@**#$%@**#$%@**#$%**#$%+**#$%@**#$%@**#$%+**#$%@**#$%@*#$%@**#$%@**#+f@2 to @4+div@**#$%@+-+ 0 +-+**#$%@**#$%@**#$%@**#$%@**#$%@**#$%**#$%@**#$%@**#$%@**#$%@**#$%@**#$%@*#$%@**#$%@**#$%@**#$%@**#$%@**#$%@+-+ 410.bw416.game433434.z435.436.cac437.leslie444.447.d450.so453.454.ca459.GemsF465.tont470.l48482.sphinxgeomean png: https://imgur.com/iTmVkJL All png's shown above can be found here: https://imgur.com/a/YSxxR Signed-off-by: Emilio G. Cota <cota@braap.org> --- include/fpu/hostfloat.h | 2 ++ include/fpu/softfloat.h | 2 +- fpu/hostfloat.c | 14 ++++++++++++++ fpu/softfloat.c | 2 +- 4 files changed, 18 insertions(+), 2 deletions(-)