mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 04:32:44 +01:00
6b1ea2f1ff
Similar to fsub, fdiv can also be vectorized using fmul. Also http://llvm.org/viewvc/llvm-project?view=revision&revision=215200 Differential Revision: https://reviews.llvm.org/D34078 Co-authored-by: Jameson Nash <jameson@juliacomputing.com>
91 lines
3.6 KiB
LLVM
91 lines
3.6 KiB
LLVM
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
;CHECK-LABEL: @foo(
|
|
;CHECK: fadd fast <4 x float>
|
|
;CHECK: ret
|
|
define float @foo(float* nocapture %A, i32* nocapture %n) nounwind uwtable readonly ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%sum.04 = phi float [ 0.000000e+00, %entry ], [ %add, %for.body ]
|
|
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx, align 4
|
|
%add = fadd fast float %sum.04, %0
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 200
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret float %add
|
|
}
|
|
|
|
;CHECK-LABEL: @foosub(
|
|
;CHECK: fsub fast <4 x float>
|
|
;CHECK: ret
|
|
define float @foosub(float* nocapture %A, i32* nocapture %n) nounwind uwtable readonly ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%sum.04 = phi float [ 0.000000e+00, %entry ], [ %sub, %for.body ]
|
|
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx, align 4
|
|
%sub = fsub fast float %sum.04, %0
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 200
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret float %sub
|
|
}
|
|
|
|
;CHECK-LABEL: @foodiv(
|
|
;CHECK: fdiv fast <4 x float>
|
|
;CHECK: ret
|
|
define float @foodiv(float* nocapture %A, i32* nocapture %n) nounwind uwtable readonly ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%sum.04 = phi float [ 1.000000e+00, %entry ], [ %sub, %for.body ]
|
|
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx, align 4
|
|
%sub = fdiv fast float %sum.04, %0
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 200
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret float %sub
|
|
}
|
|
|
|
;CHECK-LABEL: @foonodiv(
|
|
;CHECK-NOT: fdiv fast <4 x float>
|
|
;CHECK: ret
|
|
define float @foonodiv(float* nocapture %A, i32* nocapture %n) nounwind uwtable readonly ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%sum.04 = phi float [ 1.000000e+00, %entry ], [ %sub, %for.body ]
|
|
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx, align 4
|
|
%sub = fdiv fast float %0, %sum.04
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 200
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret float %sub
|
|
}
|