6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2026-04-26 12:20:42 +00:00
Code Issues Projects Releases Wiki Activity

[SLPVectorize] Basic ephemeral-value awareness

Browse Source 
The SLP vectorizer should not vectorize ephemeral values. These are used to
express information to the optimizer, and vectorizing them does not lead to
faster code (because the ephemeral values are dropped prior to code generation,
vectorized or not), and obscures the information the instructions are
attempting to communicate (the logic that interprets the arguments to
@llvm.assume generically does not understand vectorized conditions).

Also, uses by ephemeral values are free (because they, and the necessary
extractelement instructions, will be dropped prior to code generation).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@219816 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Hal Finkel
2014-10-15 17:35:01 +00:00
parent 9819bcf7f1
commit 6c15862fd3
2 changed files with 73 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
+43
View File
@@ -35,6 +35,49 @@ define <4 x float> @simple_select(<4 x float> %a, <4 x float> %b, <4 x i32> %c)
ret <4 x float> %rd
}
declare void @llvm.assume(i1) nounwind
; This entire tree is ephemeral, don't vectorize any of it.
define <4 x float> @simple_select_eph(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
; CHECK-LABEL: @simple_select_eph(
; CHECK-NOT: icmp ne <4 x i32>
; CHECK-NOT: select <4 x i1>
%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1
%c2 = extractelement <4 x i32> %c, i32 2
%c3 = extractelement <4 x i32> %c, i32 3
%a0 = extractelement <4 x float> %a, i32 0
%a1 = extractelement <4 x float> %a, i32 1
%a2 = extractelement <4 x float> %a, i32 2
%a3 = extractelement <4 x float> %a, i32 3
%b0 = extractelement <4 x float> %b, i32 0
%b1 = extractelement <4 x float> %b, i32 1
%b2 = extractelement <4 x float> %b, i32 2
%b3 = extractelement <4 x float> %b, i32 3
%cmp0 = icmp ne i32 %c0, 0
%cmp1 = icmp ne i32 %c1, 0
%cmp2 = icmp ne i32 %c2, 0
%cmp3 = icmp ne i32 %c3, 0
%s0 = select i1 %cmp0, float %a0, float %b0
%s1 = select i1 %cmp1, float %a1, float %b1
%s2 = select i1 %cmp2, float %a2, float %b2
%s3 = select i1 %cmp3, float %a3, float %b3
%ra = insertelement <4 x float> undef, float %s0, i32 0
%rb = insertelement <4 x float> %ra, float %s1, i32 1
%rc = insertelement <4 x float> %rb, float %s2, i32 2
%rd = insertelement <4 x float> %rc, float %s3, i32 3
%q0 = extractelement <4 x float> %rd, i32 0
%q1 = extractelement <4 x float> %rd, i32 1
%q2 = extractelement <4 x float> %rd, i32 2
%q3 = extractelement <4 x float> %rd, i32 3
%q4 = fadd float %q0, %q1
%q5 = fadd float %q2, %q3
%q6 = fadd float %q4, %q5
%qi = fcmp olt float %q6, %q5
call void @llvm.assume(i1 %qi)
ret <4 x float> undef
}
; Insert in an order different from the vector indices to make sure it
; doesn't matter
define <4 x float> @simple_select_insert_out_of_order(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {