[llvm] [RISCV] Refine pattern (select_cc seteq (and x, C), 0, 0, A) with Zbs. (PR #73746)

[Yeting Kuo via llvm-commits]

https://github.com/yetingk created https://github.com/llvm/llvm-project/pull/73746

PR #72978 disabled transformation (select_cc seteq (and x, C), 0, 0, A) -> (and (sra(shl x)), A) for better Zicond codegen. It still enables the combine when C is not fit into 12-bits. This patch disables the combine when Zbs enabled.

>From 90f8be4217567252156eba1073fa869a2788b226 Mon Sep 17 00:00:00 2001
From: Yeting Kuo <yeting.kuo at sifive.com>
Date: Tue, 28 Nov 2023 20:12:08 -0800
Subject: [PATCH] [RISCV] Refine pattern (select_cc seteq (and x, C), 0, 0, A)
 with Zbs.

PR #72978 disabled transformation (select_cc seteq (and x, C), 0, 0, A) -> (and (sra(shl x)), A)
for better Zicond codegen. It still enables the combine when C is not
fit into 12-bits. This patch disables the combine when Zbs enabled.
---
 llvm/lib/Target/RISCV/RISCVISelLowering.cpp |  2 +-
 llvm/test/CodeGen/RISCV/condops.ll          | 35 +++++++++------------
 2 files changed, 15 insertions(+), 22 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 17f555bffd01881..18c6ca5348b6213 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -19808,7 +19808,7 @@ RISCVTargetLowering::BuildSDIVPow2(SDNode *N, const APInt &Divisor,
 bool RISCVTargetLowering::shouldFoldSelectWithSingleBitTest(
     EVT VT, const APInt &AndMask) const {
   if (Subtarget.hasStdExtZicond() || Subtarget.hasVendorXVentanaCondOps())
-    return AndMask.ugt(1024);
+    return !Subtarget.hasStdExtZbs() && AndMask.ugt(1024);
   return TargetLowering::shouldFoldSelectWithSingleBitTest(VT, AndMask);
 }
 
diff --git a/llvm/test/CodeGen/RISCV/condops.ll b/llvm/test/CodeGen/RISCV/condops.ll
index 70185636ee62f00..bce6707781c079f 100644
--- a/llvm/test/CodeGen/RISCV/condops.ll
+++ b/llvm/test/CodeGen/RISCV/condops.ll
@@ -129,7 +129,6 @@ define i64 @zero_singlebit1(i64 %rs1, i64 %rs2) {
   ret i64 %sel
 }
 
-; TODO: Optimize Zicond case.
 define i64 @zero_singlebit2(i64 %rs1, i64 %rs2) {
 ; RV32I-LABEL: zero_singlebit2:
 ; RV32I:       # %bb.0:
@@ -148,9 +147,8 @@ define i64 @zero_singlebit2(i64 %rs1, i64 %rs2) {
 ;
 ; RV64XVENTANACONDOPS-LABEL: zero_singlebit2:
 ; RV64XVENTANACONDOPS:       # %bb.0:
-; RV64XVENTANACONDOPS-NEXT:    slli a1, a1, 51
-; RV64XVENTANACONDOPS-NEXT:    srai a1, a1, 63
-; RV64XVENTANACONDOPS-NEXT:    and a0, a1, a0
+; RV64XVENTANACONDOPS-NEXT:    bexti a1, a1, 12
+; RV64XVENTANACONDOPS-NEXT:    vt.maskc a0, a0, a1
 ; RV64XVENTANACONDOPS-NEXT:    ret
 ;
 ; RV64XTHEADCONDMOV-LABEL: zero_singlebit2:
@@ -162,17 +160,15 @@ define i64 @zero_singlebit2(i64 %rs1, i64 %rs2) {
 ;
 ; RV32ZICOND-LABEL: zero_singlebit2:
 ; RV32ZICOND:       # %bb.0:
-; RV32ZICOND-NEXT:    slli a2, a2, 19
-; RV32ZICOND-NEXT:    srai a2, a2, 31
-; RV32ZICOND-NEXT:    and a0, a2, a0
-; RV32ZICOND-NEXT:    and a1, a2, a1
+; RV32ZICOND-NEXT:    bexti a2, a2, 12
+; RV32ZICOND-NEXT:    czero.eqz a0, a0, a2
+; RV32ZICOND-NEXT:    czero.eqz a1, a1, a2
 ; RV32ZICOND-NEXT:    ret
 ;
 ; RV64ZICOND-LABEL: zero_singlebit2:
 ; RV64ZICOND:       # %bb.0:
-; RV64ZICOND-NEXT:    slli a1, a1, 51
-; RV64ZICOND-NEXT:    srai a1, a1, 63
-; RV64ZICOND-NEXT:    and a0, a1, a0
+; RV64ZICOND-NEXT:    bexti a1, a1, 12
+; RV64ZICOND-NEXT:    czero.eqz a0, a0, a1
 ; RV64ZICOND-NEXT:    ret
   %and = and i64 %rs2, 4096
   %rc = icmp eq i64 %and, 0
@@ -3694,9 +3690,8 @@ define i64 @single_bit2(i64 %x) {
 ;
 ; RV64XVENTANACONDOPS-LABEL: single_bit2:
 ; RV64XVENTANACONDOPS:       # %bb.0: # %entry
-; RV64XVENTANACONDOPS-NEXT:    slli a1, a0, 52
-; RV64XVENTANACONDOPS-NEXT:    srai a1, a1, 63
-; RV64XVENTANACONDOPS-NEXT:    and a0, a1, a0
+; RV64XVENTANACONDOPS-NEXT:    bexti a1, a0, 11
+; RV64XVENTANACONDOPS-NEXT:    vt.maskc a0, a0, a1
 ; RV64XVENTANACONDOPS-NEXT:    ret
 ;
 ; RV64XTHEADCONDMOV-LABEL: single_bit2:
@@ -3708,17 +3703,15 @@ define i64 @single_bit2(i64 %x) {
 ;
 ; RV32ZICOND-LABEL: single_bit2:
 ; RV32ZICOND:       # %bb.0: # %entry
-; RV32ZICOND-NEXT:    slli a2, a0, 20
-; RV32ZICOND-NEXT:    srai a2, a2, 31
-; RV32ZICOND-NEXT:    and a0, a2, a0
-; RV32ZICOND-NEXT:    and a1, a2, a1
+; RV32ZICOND-NEXT:    bexti a2, a0, 11
+; RV32ZICOND-NEXT:    czero.eqz a0, a0, a2
+; RV32ZICOND-NEXT:    czero.eqz a1, a1, a2
 ; RV32ZICOND-NEXT:    ret
 ;
 ; RV64ZICOND-LABEL: single_bit2:
 ; RV64ZICOND:       # %bb.0: # %entry
-; RV64ZICOND-NEXT:    slli a1, a0, 52
-; RV64ZICOND-NEXT:    srai a1, a1, 63
-; RV64ZICOND-NEXT:    and a0, a1, a0
+; RV64ZICOND-NEXT:    bexti a1, a0, 11
+; RV64ZICOND-NEXT:    czero.eqz a0, a0, a1
 ; RV64ZICOND-NEXT:    ret
 entry:
   %and = and i64 %x, 2048