742fb8b5c7
If we have a store of a load with no other uses in between it, it's considered dead and is removed. So sometimes when legalizing a fixed length vector store of an insert, we end up producing better code through scalarization than without. An example is the follow below: %a = load <4 x i64>, ptr %x %b = insertelement <4 x i64> %a, i64 %y, i32 2 store <4 x i64> %b, ptr %x If this is scalarized, then DAGCombine successfully removes 3 of the 4 stores which are considered dead, and on RISC-V we get: sd a1, 16(a0) However if we make the vector type legal (-mattr=+v), then we lose the optimisation because we don't scalarize it. This patch attempts to recover the optimisation for vectors by identifying patterns where we store a load with a single insert inbetween, replacing it with a scalar store of the inserted element. Reviewed By: RKSimon Differential Revision: https://reviews.llvm.org/D152276
17 lines
1.1 KiB
LLVM
17 lines
1.1 KiB
LLVM
; RUN: llc -march=hexagon < %s | FileCheck %s
|
|
|
|
; Check that we generate a proper vinsert instruction for f16 types.
|
|
; CHECK: vinsert
|
|
target datalayout = "e-m:e-p:32:32:32-a:0-n16:32-i64:64:64-i32:32:32-i16:16:16-i1:8:8-f32:32:32-f64:64:64-v32:32:32-v64:64:64-v512:512:512-v1024:1024:1024-v2048:2048:2048"
|
|
target triple = "hexagon"
|
|
|
|
define ptr @fred(ptr %v0) local_unnamed_addr #0 {
|
|
b0:
|
|
%v1 = load <64 x half>, ptr %v0, align 2
|
|
%v2 = insertelement <64 x half> %v1, half 0xH4170, i32 17
|
|
store volatile <64 x half> %v2, ptr %v0, align 2
|
|
ret ptr %v0
|
|
}
|
|
|
|
attributes #0 = { norecurse nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="hexagonv69" "target-features"="+hvx-length128b,+hvxv69,+v69,+hvx-qfloat,-long-calls" "unsafe-fp-math"="false" "use-soft-float"="false" }
|