forked from llvm/llvm-project
-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[SelectionDAG] Handle VSCALE in isKnownNeverZero (llvm#97789)
VSCALE is by definition greater than zero, but this checks it via getVScaleRange anyway. The motivation for this is to be able to check if the EVL for a VP strided load is non-zero in llvm#97394. I added the tests to the RISC-V backend since the existing X86 known-never-zero.ll test crashed when trying to lower vscale for the +sse2 RUN line.
- Loading branch information
Showing
2 changed files
with
43 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,34 @@ | ||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5 | ||
; RUN: llc < %s -mtriple=riscv64 -mattr=+v -verify-machineinstrs | FileCheck %s | ||
|
||
; Use cttz to test if we properly prove never-zero. There is a very | ||
; simple transform from cttz -> cttz_zero_undef if its operand is | ||
; known never zero. | ||
|
||
; Even without vscale_range, vscale is always guaranteed to be non-zero. | ||
define i32 @vscale_known_nonzero() { | ||
; CHECK-LABEL: vscale_known_nonzero: | ||
; CHECK: # %bb.0: | ||
; CHECK-NEXT: addi sp, sp, -16 | ||
; CHECK-NEXT: .cfi_def_cfa_offset 16 | ||
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill | ||
; CHECK-NEXT: .cfi_offset ra, -8 | ||
; CHECK-NEXT: csrr a0, vlenb | ||
; CHECK-NEXT: srli a0, a0, 3 | ||
; CHECK-NEXT: neg a1, a0 | ||
; CHECK-NEXT: and a0, a0, a1 | ||
; CHECK-NEXT: lui a1, 30667 | ||
; CHECK-NEXT: addiw a1, a1, 1329 | ||
; CHECK-NEXT: call __muldi3 | ||
; CHECK-NEXT: srliw a0, a0, 27 | ||
; CHECK-NEXT: lui a1, %hi(.LCPI0_0) | ||
; CHECK-NEXT: addi a1, a1, %lo(.LCPI0_0) | ||
; CHECK-NEXT: add a0, a1, a0 | ||
; CHECK-NEXT: lbu a0, 0(a0) | ||
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload | ||
; CHECK-NEXT: addi sp, sp, 16 | ||
; CHECK-NEXT: ret | ||
%x = call i32 @llvm.vscale() | ||
%r = call i32 @llvm.cttz.i32(i32 %x, i1 false) | ||
ret i32 %r | ||
} |