Simplify powl computation for small integral y [BZ #33411]

The powl implementation for x86_64 ends up multiplying X once more than
necessary and then throwing away that result.  This results in an
overflow flag being set in cases where there is no overflow.

Simplify the relevant portion by special casing the -3 to 3 range and
simply multiplying repetitively.

Resolves: BZ #33411
Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
Reviewed by: Paul Zimmermann <Paul.Zimmermann@inria.fr>

2 files changed, 68 insertions, 0 deletions

diff --git a/math/auto-libm-test-in b/math/auto-libm-test-in
index 1397d317fb..89a6760639 100644
--- a/math/auto-libm-test-in
+++ b/math/auto-libm-test-in
@@ -8372,6 +8372,9 @@ pow 0x1.059c76p+0 0x1.ff80bep+11
 pow 0x1.7ac7cp+5 23
 pow -0x1.7ac7cp+5 23
 
+# BZ33411.  xfail for binary32 due to BZ#33563.
+pow 0x1p+8192 1.0 xfail:binary32
+
 pown 0 0
 pown 0 -0
 pown -0 0
diff --git a/math/auto-libm-test-out-pow b/math/auto-libm-test-out-pow
index 09ec53e49e..cbca46cd0c 100644
--- a/math/auto-libm-test-out-pow
+++ b/math/auto-libm-test-out-pow
@@ -44221,3 +44221,68 @@ pow -0x1.7ac7cp+5 23
 = pow tonearest ibm128 -0x2.f58f8p+4 0x1.7p+4 : -0xf.fffff29cf02eeec4a7cde7b5a4p+124 : inexact-ok
 = pow towardzero ibm128 -0x2.f58f8p+4 0x1.7p+4 : -0xf.fffff29cf02eeec4a7cde7b5ap+124 : inexact-ok
 = pow upward ibm128 -0x2.f58f8p+4 0x1.7p+4 : -0xf.fffff29cf02eeec4a7cde7b5ap+124 : inexact-ok
+pow 0x1p+8192 1.0 xfail:binary32
+= pow downward binary32 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow tonearest binary32 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow towardzero binary32 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow upward binary32 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow downward binary64 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow tonearest binary64 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow towardzero binary64 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow upward binary64 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow downward intel96 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow tonearest intel96 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow towardzero intel96 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow upward intel96 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow downward m68k96 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow tonearest m68k96 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow towardzero m68k96 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow upward m68k96 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow downward binary128 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow tonearest binary128 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow towardzero binary128 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow upward binary128 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow downward ibm128 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow tonearest ibm128 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow towardzero ibm128 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow upward ibm128 0xf.fffffp+124 0x1p+0 : 0xf.fffffp+124 : xfail:binary32 inexact-ok
+= pow downward binary64 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow tonearest binary64 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow towardzero binary64 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow upward binary64 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow downward intel96 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow tonearest intel96 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow towardzero intel96 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow upward intel96 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow downward m68k96 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow tonearest m68k96 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow towardzero m68k96 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow upward m68k96 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow downward binary128 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow tonearest binary128 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow towardzero binary128 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow upward binary128 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow downward ibm128 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow tonearest ibm128 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow towardzero ibm128 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow upward ibm128 0xf.ffffffffffff8p+1020 0x1p+0 : 0xf.ffffffffffff8p+1020 : xfail:binary32 inexact-ok
+= pow downward intel96 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow tonearest intel96 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow towardzero intel96 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow upward intel96 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow downward m68k96 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow tonearest m68k96 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow towardzero m68k96 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow upward m68k96 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow downward binary128 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow tonearest binary128 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow towardzero binary128 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow upward binary128 0x1p+8192 0x1p+0 : 0x1p+8192 : xfail:binary32 inexact-ok
+= pow downward binary128 0xf.ffffffffffffbffffffffffffcp+1020 0x1p+0 : 0xf.ffffffffffffbffffffffffffcp+1020 : xfail:binary32 inexact-ok
+= pow tonearest binary128 0xf.ffffffffffffbffffffffffffcp+1020 0x1p+0 : 0xf.ffffffffffffbffffffffffffcp+1020 : xfail:binary32 inexact-ok
+= pow towardzero binary128 0xf.ffffffffffffbffffffffffffcp+1020 0x1p+0 : 0xf.ffffffffffffbffffffffffffcp+1020 : xfail:binary32 inexact-ok
+= pow upward binary128 0xf.ffffffffffffbffffffffffffcp+1020 0x1p+0 : 0xf.ffffffffffffbffffffffffffcp+1020 : xfail:binary32 inexact-ok
+= pow downward ibm128 0xf.ffffffffffffbffffffffffffcp+1020 0x1p+0 : 0xf.ffffffffffffbffffffffffffcp+1020 : xfail:binary32 inexact-ok
+= pow tonearest ibm128 0xf.ffffffffffffbffffffffffffcp+1020 0x1p+0 : 0xf.ffffffffffffbffffffffffffcp+1020 : xfail:binary32 inexact-ok
+= pow towardzero ibm128 0xf.ffffffffffffbffffffffffffcp+1020 0x1p+0 : 0xf.ffffffffffffbffffffffffffcp+1020 : xfail:binary32 inexact-ok
+= pow upward ibm128 0xf.ffffffffffffbffffffffffffcp+1020 0x1p+0 : 0xf.ffffffffffffbffffffffffffcp+1020 : xfail:binary32 inexact-ok