f803e463f9
This PR implements parts of https://github.com/llvm/llvm-project/issues/162376 - **Broader equivalence than constant index deltas**: - Add Base-delta and Stride-delta matching for Add and GEP forms using ScalarEvolution deltas. - Reuse enabled for both constant and variable deltas when an available IR value dominates the user. - **Dominance-aware dictionary instead of linear scans**: - Tuple-keyed candidate dictionary grouped by basic block. - Walk the immediate-dominator chain to find the nearest dominating basis quickly and deterministically. - **Simple cost model and best-rewrite selection**: - Score candidate expressions and rewrites; select the highest-profit rewrite per instruction. - Skip rewriting when expressions are already foldable or high-efficiency. - **Path compression for better ILP**: - Compress chains of rewrites to a deeper dominating basis when a constant delta exists along the path, reducing dependent bumps on critical paths. - **Dependency-aware rewrite ordering**: - Build a dependency graph (basis, stride, variable delta producers) and rewrite in topological order. - This dependency graph will be needed by the next PR that adds partial strength reduction. - **Correctness enhencment** - Fix a correctness issue that reusing instructions with the same SCEV may introduce poison. --------- Co-authored-by: Kazu Hirata <kazu@google.com>
20 lines
931 B
LLVM
20 lines
931 B
LLVM
; RUN: opt < %s -passes=slsr -S | FileCheck %s
|
|
; RUN: opt < %s -passes='slsr' -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-p24:64:64-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
|
|
target triple = "amdgcn--"
|
|
|
|
%struct.Matrix4x4 = type { [4 x [4 x float]] }
|
|
|
|
; Function Attrs: nounwind
|
|
define fastcc void @Accelerator_Intersect(ptr addrspace(1) nocapture readonly %leafTransformations) {
|
|
; CHECK-LABEL: @Accelerator_Intersect(
|
|
entry:
|
|
%tmp = sext i32 undef to i64
|
|
%arrayidx114 = getelementptr inbounds %struct.Matrix4x4, ptr addrspace(1) %leafTransformations, i64 %tmp
|
|
%tmp1 = getelementptr %struct.Matrix4x4, ptr addrspace(1) %leafTransformations, i64 %tmp, i32 0, i64 0, i64 1
|
|
; CHECK: %tmp1 = getelementptr i8, ptr addrspace(1) %arrayidx114, i64 4
|
|
%tmp2 = load <4 x float>, ptr addrspace(1) undef, align 4
|
|
ret void
|
|
}
|