Add avg_{up,down}_int{8,16} routines to stdlib

These compute the average of two given values, rounding up and down,
respectively, if the result isn't exact.  When possible, these are
mapped to target-specific intrinsics (PADD[BW] on IA and VH[R]ADD[US]
on NEON.)

A subsequent commit will add pattern-matching to generate calls to
these intrinsincs when the corresponding patterns are detected in the
IR.)
This commit is contained in:
Matt Pharr
2013-08-03 20:44:25 -07:00
parent 4f48d3258a
commit 5b20b06bd9
23 changed files with 592 additions and 15 deletions

View File

@@ -277,3 +277,9 @@ define double @__max_uniform_double(double, double) nounwind readnone alwaysinli
sse_binary_scalar(ret, 2, double, @llvm.x86.sse2.max.sd, %0, %1)
ret double %ret
}
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; int8/int16 builtins
define_avgs()