[AArch64][GlobalISel] Alternative fix: widen atomic stores in legalizer

Per review suggestion from @xal-0, handle the atomic store issue in the
legalizer instead of copyPhysReg. This adds a widenScalarIf rule for
G_STORE that widens scalar types narrower than 32 bits to s32 for atomic
stores with release ordering or stronger.

This approach:
- Fixes the original bug (mrs instead of fmov for half->i16 atomic store)
- Enables stlurb/stlurh codegen for GISel (removes two TODOs)
- Is a more appropriate place to handle type legalization

Co-authored-by: Claude <noreply@anthropic.com>

Author: IanButterworth

llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp

@@ -568,6 +568,10 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
         return Query.Types[0] == s128 &&
                Query.MMODescrs[0].Ordering != AtomicOrdering::NotAtomic;
       })
+      .widenScalarIf(
+          all(scalarNarrowerThan(0, 32),
+              atomicOrderingAtLeastOrStrongerThan(0, AtomicOrdering::Release)),
+          changeTo(0, s32))
       .legalForTypesWithMemDesc(
           {{s8, p0, s8, 8},     {s16, p0, s8, 8},  // truncstorei8 from s16
            {s32, p0, s8, 8},                       // truncstorei8 from s32

llvm/test/CodeGen/AArch64/Atomics/aarch64-atomic-store-rcpc_immo.ll

@@ -357,12 +357,10 @@ define void @store_atomic_i128_unaligned_seq_cst(i128 %value, ptr %ptr) {
     ret void
 }
 
-; TODO: missed opportunity to emit a stlurb w/ GISel
 define void @store_atomic_i8_from_gep() {
 ; GISEL-LABEL: store_atomic_i8_from_gep:
 ; GISEL:    bl init
-; GISEL:    add x9, x8, #1
-; GISEL:    stlrb w8, [x9]
+; GISEL:    stlurb w8, [x9, #1]
 ;
 ; SDAG-LABEL: store_atomic_i8_from_gep:
 ; SDAG:    bl init
@@ -374,12 +372,10 @@ define void @store_atomic_i8_from_gep() {
   ret void
 }
 
-; TODO: missed opportunity to emit a stlurh w/ GISel
 define void @store_atomic_i16_from_gep() {
 ; GISEL-LABEL: store_atomic_i16_from_gep:
 ; GISEL:    bl init
-; GISEL:    add x9, x8, #2
-; GISEL:    stlrh w8, [x9]
+; GISEL:    stlurh w8, [x9, #2]
 ;
 ; SDAG-LABEL: store_atomic_i16_from_gep:
 ; SDAG:    bl init

llvm/test/CodeGen/AArch64/GlobalISel/arm64-atomic-store-fp16.ll

@@ -14,7 +14,7 @@ define void @atomic_store_half(ptr %addr, half %val) {
 ;
 ; CHECK-FP16-LABEL: atomic_store_half:
 ; CHECK-FP16:       ; %bb.0:
-; CHECK-FP16-NEXT:    fmov w8, h0
+; CHECK-FP16-NEXT:    fmov w8, s0
 ; CHECK-FP16-NEXT:    stlrh w8, [x0]
 ; CHECK-FP16-NEXT:    ret
   %ival = bitcast half %val to i16
@@ -50,7 +50,7 @@ define void @atomic_store_bfloat(ptr %addr, bfloat %val) {
 ;
 ; CHECK-FP16-LABEL: atomic_store_bfloat:
 ; CHECK-FP16:       ; %bb.0:
-; CHECK-FP16-NEXT:    fmov w8, h0
+; CHECK-FP16-NEXT:    fmov w8, s0
 ; CHECK-FP16-NEXT:    stlrh w8, [x0]
 ; CHECK-FP16-NEXT:    ret
   %ival = bitcast bfloat %val to i16