https://llvm.org/bugs/show_bug.cgi?id=31143
Bug ID: 31143
Summary: False dependence breaking fails for ROUNDSSr
Product: libraries
Version: trunk
Hardware: PC
OS: Linux
Status: NEW
Severity: normal
Priority: P
Component: Backend: X86
Assignee: unassignedb...@nondot.org
Reporter: mku...@google.com
CC: llvm-bugs@lists.llvm.org
Classification: Unclassified
target triple = "x86_64-pc-linux-gnu"
define void @test(float* nocapture %a, <4 x float>* nocapture %b, i32 %k) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds float, float* %a, i64 %indvars.iv
%v = load float, float* %arrayidx, align 4
%floor = call float @floorf(float %v)
%sub = fsub float %floor, %v
%v1 = insertelement <4 x float> undef, float %sub, i32 0
%br = shufflevector <4 x float> %v1, <4 x float> undef, <4 x i32> <i32 0, i32
0, i32 0, i32 0>
store volatile <4 x float> %br, <4 x float>* %b, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %k
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
declare float @floorf(float) nounwind readnone
When compiled with -msse4.1 (to emit a roundss for the floorf) we get:
.LBB0_1: # %for.body
# =>This Inner Loop Header: Depth=1
movss (%rdi), %xmm0 # xmm0 = mem[0],zero,zero,zero
roundss $9, %xmm0, %xmm1
subss %xmm0, %xmm1
shufps $0, %xmm1, %xmm1 # xmm1 = xmm1[0,0,0,0]
movups %xmm1, (%rsi)
addq $4, %rdi
decl %edx
jne .LBB0_1
# BB#2: # %for.end
retq
The false dependence on %xmm1 is not broken.
As expected, adding the requires xorps makes this loop about 3 times faster.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
