Skip to content

[Hexagon] Add missing patterns to select PFALSE and PTRUE #138712

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 6, 2025
Merged

[Hexagon] Add missing patterns to select PFALSE and PTRUE #138712

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions llvm/lib/Target/Hexagon/HexagonPatterns.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,7 +109,12 @@ def pfalse: PatFrag<(ops), (HexagonPFALSE)>;
def pnot: PatFrag<(ops node:$Pu), (xor node:$Pu, ptrue)>;

def: Pat<(v8i1 (HexagonPFALSE)), (C2_tfrrp (A2_tfrsi (i32 0)))>;
def: Pat<(v4i1 (HexagonPFALSE)), (C2_tfrrp (A2_tfrsi (i32 0)))>;
def: Pat<(v2i1 (HexagonPFALSE)), (C2_tfrrp (A2_tfrsi (i32 0)))>;

def: Pat<(v8i1 (HexagonPTRUE)), (C2_tfrrp (A2_tfrsi (i32 -1)))>;
def: Pat<(v4i1 (HexagonPTRUE)), (C2_tfrrp (A2_tfrsi (i32 -1)))>;
def: Pat<(v2i1 (HexagonPTRUE)), (C2_tfrrp (A2_tfrsi (i32 -1)))>;

def valign: PatFrag<(ops node:$Vt, node:$Vs, node:$Ru),
(HexagonVALIGN node:$Vt, node:$Vs, node:$Ru)>;
Expand Down
29 changes: 29 additions & 0 deletions llvm/test/CodeGen/Hexagon/isel/pfalse-v4i1.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
; RUN: llc -march=hexagon -debug-only=isel 2>&1 < %s - | FileCheck %s

; CHECK: [[R0:%[0-9]+]]:intregs = A2_tfrsi 0
; CHECK-NEXT: predregs = C2_tfrrp killed [[R0]]:intregs

define fastcc i16 @test(ptr %0, { <4 x i32>, <4 x i1> } %1, <4 x i1> %2) {
Entry:
%3 = alloca [16 x i8], i32 0, align 16
%4 = alloca [16 x i8], i32 0, align 16
store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, ptr %4, align 16
store <4 x i32> <i32 5, i32 6, i32 7, i32 8>, ptr %3, align 16
%5 = load <4 x i32>, ptr %4, align 16
%6 = load <4 x i32>, ptr %3, align 16
%7 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> %5, <4 x i32> %6)
%8 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> %2)
br i1 %8, label %OverflowFail, label %OverflowOk

OverflowFail: ; preds = %Entry
store volatile i32 0, ptr null, align 4
unreachable

OverflowOk: ; preds = %Entry
%9 = extractvalue { <4 x i32>, <4 x i1> } %7, 0
store <4 x i32> %9, ptr %0, align 16
ret i16 0
}

declare { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32>, <4 x i32>) #0
declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>) #0