aaron/ispc
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Gather/scatter function improvements in builtins.

Browse Source 
More naming consistency: _i32 rather than i32, now.

Also improved the m4 macros to generate these sequences to not require as
many parameters.
This commit is contained in:
Matt Pharr
2012-06-07 14:18:06 -07:00
parent b86d40091a
commit 1ac3e03171
15 changed files with 420 additions and 423 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
builtins/target-avx.ll
View File

@@ -492,10 +492,10 @@ define void @__masked_store_blend_i64(<8 x i64>* nocapture %ptr, <8 x i64> %new,
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; scatter
gen_scatter(8, i8)
gen_scatter(8, i16)
gen_scatter(8, i32)
gen_scatter(8, i64)
gen_scatter(i8)
gen_scatter(i16)
gen_scatter(i32)
gen_scatter(i64)
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; double precision sqrt