diff options
| -rw-r--r-- | lib/Target/PowerPC/README.txt | 32 |
1 files changed, 9 insertions, 23 deletions
diff --git a/lib/Target/PowerPC/README.txt b/lib/Target/PowerPC/README.txt index c90343eeee..c9fba7fed4 100644 --- a/lib/Target/PowerPC/README.txt +++ b/lib/Target/PowerPC/README.txt @@ -552,34 +552,20 @@ When -ffast-math is on, we can use 0.0. float foo(float X) { return (int)(X); } -Currently produces +Currently produces: _foo: - lis r2, ha16(LCPI1_0) - lis r3, 17200 fctiwz f0, f1 stfd f0, -8(r1) - lwz r4, -4(r1) - xoris r4, r4, 32768 - stw r4, -12(r1) - stw r3, -16(r1) - lfs f0, lo16(LCPI1_0)(r2) - lfd f1, -16(r1) - fsub f0, f1, f0 + lwz r2, -4(r1) + extsw r2, r2 + std r2, -16(r1) + lfd f0, -16(r1) + fcfid f0, f0 frsp f1, f0 blr -When we have ppc64 working properly, it could produce the nicer code: - -_foo: - fctiwz f0, f1 - stfd f0, -8(r1) - lwz r4, -4(r1) - extsh r4, r4 - std r4, -16(r1) - lfd f1, -16(r1) - fcfid f0, f0 - frsp f0, f0 - blr +We could use a target dag combine to turn the lwz/extsw into an lwa when the +lwz has a single use. Since LWA is cracked anyway, this would be a codesize +win only. -Note: this would speed up SingleSource/Misc/pi by about 30% |