[llvm] [WebAssembly] improve getRegForPromotedValue to avoid meanless value copy (PR #80469)

[Congcong Cai via llvm-commits]

https://github.com/HerrCai0907 created https://github.com/llvm/llvm-project/pull/80469

When promoted value, it is meaningless to copy value from reg to another reg with the same type.
This PR add additional check for this cases to reduce the code size.
Fixes: #80053.


>From 2607a7b6a00a28e36debd14e7e64c0c54e5290e4 Mon Sep 17 00:00:00 2001
From: Congcong Cai <congcongcai0907 at 163.com>
Date: Sat, 3 Feb 2024 01:51:10 +0800
Subject: [PATCH] [WebAssembly] improve getRegForPromotedValue to avoid
 meanless value copy

---
 .../WebAssembly/WebAssemblyFastISel.cpp       |  4 ++
 .../CodeGen/WebAssembly/suboptimal-compare.ll | 43 +++++++++++++++++++
 2 files changed, 47 insertions(+)
 create mode 100644 llvm/test/CodeGen/WebAssembly/suboptimal-compare.ll

diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp
index 7f0140a5e8c66..1c62290704fe4 100644
--- a/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp
@@ -559,6 +559,8 @@ unsigned WebAssemblyFastISel::getRegForUnsignedValue(const Value *V) {
   Register VReg = getRegForValue(V);
   if (VReg == 0)
     return 0;
+  if (From == To)
+    return VReg;
   return zeroExtend(VReg, V, From, To);
 }
 
@@ -568,6 +570,8 @@ unsigned WebAssemblyFastISel::getRegForSignedValue(const Value *V) {
   Register VReg = getRegForValue(V);
   if (VReg == 0)
     return 0;
+  if (From == To)
+    return VReg;
   return signExtend(VReg, V, From, To);
 }
 
diff --git a/llvm/test/CodeGen/WebAssembly/suboptimal-compare.ll b/llvm/test/CodeGen/WebAssembly/suboptimal-compare.ll
new file mode 100644
index 0000000000000..243494cee320c
--- /dev/null
+++ b/llvm/test/CodeGen/WebAssembly/suboptimal-compare.ll
@@ -0,0 +1,43 @@
+; RUN: llc < %s -fast-isel -O0 | FileCheck %s
+
+target triple = "wasm32-unknown-unknown"
+
+; CHECK-LABEL: gh_80052:                               # @gh_80052
+; CHECK-NEXT: .functype	gh_80052 (i32) -> (i32)
+; CHECK-NEXT: .local  	i32, i32, i32, i32, i32, i32
+; CHECK:      i32.const	0
+; CHECK-NEXT: local.set	1
+; CHECK-NEXT: local.get	0
+; CHECK-NEXT: local.get	1
+; CHECK-NEXT: i32.eq  
+; CHECK-NEXT: local.set	2
+; CHECK-NEXT: i32.const	1
+; CHECK-NEXT: local.set	3
+; CHECK-NEXT: local.get	2
+; CHECK-NEXT: local.get	3
+; CHECK-NEXT: i32.and 
+; CHECK-NEXT: local.set	4
+; CHECK-NEXT: block   	
+; CHECK-NEXT:   local.get	4
+; CHECK-NEXT:   i32.eqz
+; CHECK-NEXT:   br_if   	0                               # 0: down to label0
+; CHECK:        i32.const	0
+; CHECK-NEXT:   local.set	5
+; CHECK-NEXT:   local.get	5
+; CHECK-NEXT:   return
+; CHECK-NEXT: .LBB0_2:                                # %BB03
+; CHECK-NEXT: end_block                               # label0:
+; CHECK-NEXT: i32.const	1
+; CHECK-NEXT: local.set	6
+; CHECK-NEXT: local.get	6
+; CHECK-NEXT: return
+; CHECK-NEXT: end_function
+define i1 @gh_80052(ptr) {
+BB01:
+    %eq = icmp eq ptr %0, null
+    br i1 %eq, label %BB02, label %BB03
+BB02:
+    ret i1 0
+BB03:
+    ret i1 1
+}