[llvm] a71147d - [WebAssembly] improve getRegForPromotedValue to avoid meanless value copy (#80469)

[via llvm-commits]

Author: Congcong Cai
Date: 2024-02-06T09:07:58+08:00
New Revision: a71147dd28c6676fc46e4ec0a5d6e0b0823cced5

URL: https://github.com/llvm/llvm-project/commit/a71147dd28c6676fc46e4ec0a5d6e0b0823cced5
DIFF: https://github.com/llvm/llvm-project/commit/a71147dd28c6676fc46e4ec0a5d6e0b0823cced5.diff

LOG: [WebAssembly] improve getRegForPromotedValue to avoid meanless value copy (#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.

Added: 
    llvm/test/CodeGen/WebAssembly/suboptimal-compare.ll

Modified: 
    llvm/lib/Target/WebAssembly/WebAssemblyFastISel.cpp

Removed: 
    


################################################################################
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..fadeb397a884c
--- /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_80053:                               # @gh_80053
+; CHECK-NEXT: .functype	gh_80053 (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_80053(ptr) {
+BB01:
+    %eq = icmp eq ptr %0, null
+    br i1 %eq, label %BB02, label %BB03
+BB02:
+    ret i1 0
+BB03:
+    ret i1 1
+}