[AArch64][GlobalISel] Widen G_PHI before clamping it during legalization

This allows us to handle weird types like s88; we first widen to s128, then
clamp back down to s64.

https://godbolt.org/z/9xqbP46Mz

Also this makes it possible for GISel to legalize the case in pr48188.ll. It
now does the same thing as SDAG, although regalloc chooses different registers.

Differential Revision: https://reviews.llvm.org/D107417

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

@@ -97,8 +97,8 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
 
   getActionDefinitionsBuilder(G_PHI).legalFor({p0, s16, s32, s64})
       .legalFor(PackedVectorAllTypeList)
-      .clampScalar(0, s16, s64)
+      .widenScalarToNextPow2(0)
-      .widenScalarToNextPow2(0);
+      .clampScalar(0, s16, s64);
 
   getActionDefinitionsBuilder(G_BSWAP)
       .legalFor({s32, s64, v4s32, v2s32, v2s64})

llvm/test/CodeGen/AArch64/GlobalISel/legalize-phi.mir

@@ -624,3 +624,44 @@ body:             |
     $q0 = COPY %3(<16 x s8>)
     RET_ReallyLR
 ...
+---
+name:             s88
+tracksRegLiveness: true
+liveins:
+body:             |
+  ; CHECK-LABEL: name: s88
+  ; CHECK: bb.0:
+  ; CHECK:   successors: %bb.1(0x40000000), %bb.2(0x40000000)
+  ; CHECK:   liveins: $x0
+  ; CHECK:   %cond:_(s1) = G_IMPLICIT_DEF
+  ; CHECK:   G_BRCOND %cond(s1), %bb.1
+  ; CHECK:   G_BR %bb.2
+  ; CHECK: bb.1:
+  ; CHECK:   successors: %bb.3(0x80000000)
+  ; CHECK:   [[DEF:%[0-9]+]]:_(s64) = G_IMPLICIT_DEF
+  ; CHECK:   G_BR %bb.3
+  ; CHECK: bb.2:
+  ; CHECK:   successors: %bb.3(0x80000000)
+  ; CHECK:   [[DEF1:%[0-9]+]]:_(s64) = G_IMPLICIT_DEF
+  ; CHECK: bb.3:
+  ; CHECK:   [[PHI:%[0-9]+]]:_(s64) = G_PHI [[DEF]](s64), %bb.1, [[DEF1]](s64), %bb.2
+  ; CHECK:   $x0 = COPY [[PHI]](s64)
+  ; CHECK:   RET_ReallyLR implicit $x0
+  bb.0:
+    successors: %bb.1(0x40000000), %bb.2(0x40000000)
+    liveins: $x0
+    %cond:_(s1) = G_IMPLICIT_DEF
+    G_BRCOND %cond(s1), %bb.1
+    G_BR %bb.2
+  bb.1:
+    successors: %bb.3(0x80000000)
+    %imp_1:_(s88) = G_IMPLICIT_DEF
+    G_BR %bb.3
+  bb.2:
+    successors: %bb.3(0x80000000)
+    %imp_2:_(s88) = G_IMPLICIT_DEF
+  bb.3:
+    %phi:_(s88) = G_PHI %imp_1:_(s88), %bb.1, %imp_2:_(s88), %bb.2
+    %trunc:_(s64) = G_TRUNC %phi
+    $x0 = COPY %trunc
+    RET_ReallyLR implicit $x0

llvm/test/CodeGen/AArch64/pr48188.ll

@@ -1,23 +1,40 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -O0 -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s
+; RUN: llc -O0 -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s --check-prefix=GISEL
+; RUN: llc -O0 -global-isel=0 -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s --check-prefix=SDAG
 
-; GlobalISel cannot legalize this phi, so we fall back to SDAG.
+; Verify that GISel and SDAG do the same thing for this phi (modulo regalloc)
 define void @test() nounwind {
-; CHECK-LABEL: test:
+; GISEL-LABEL: test:
-; CHECK:       // %bb.0: // %entry
+; GISEL:       // %bb.0: // %entry
-; CHECK-NEXT:    sub sp, sp, #16
+; GISEL-NEXT:    sub sp, sp, #16
-; CHECK-NEXT:    mov x1, xzr
+; GISEL-NEXT:    mov x8, xzr
-; CHECK-NEXT:    mov x0, x1
+; GISEL-NEXT:    mov x9, x8
-; CHECK-NEXT:    str x1, [sp] // 8-byte Folded Spill
+; GISEL-NEXT:    str x9, [sp] // 8-byte Folded Spill
-; CHECK-NEXT:    str x0, [sp, #8] // 8-byte Folded Spill
+; GISEL-NEXT:    str x8, [sp, #8] // 8-byte Folded Spill
-; CHECK-NEXT:    b .LBB0_1
+; GISEL-NEXT:    b .LBB0_1
-; CHECK-NEXT:  .LBB0_1: // %loop
+; GISEL-NEXT:  .LBB0_1: // %loop
-; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
+; GISEL-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    ldr x0, [sp, #8] // 8-byte Folded Reload
+; GISEL-NEXT:    ldr x8, [sp, #8] // 8-byte Folded Reload
-; CHECK-NEXT:    ldr x1, [sp] // 8-byte Folded Reload
+; GISEL-NEXT:    ldr x9, [sp] // 8-byte Folded Reload
-; CHECK-NEXT:    str x1, [sp] // 8-byte Folded Spill
+; GISEL-NEXT:    str x9, [sp] // 8-byte Folded Spill
-; CHECK-NEXT:    str x0, [sp, #8] // 8-byte Folded Spill
+; GISEL-NEXT:    str x8, [sp, #8] // 8-byte Folded Spill
-; CHECK-NEXT:    b .LBB0_1
+; GISEL-NEXT:    b .LBB0_1
+;
+; SDAG-LABEL: test:
+; SDAG:       // %bb.0: // %entry
+; SDAG-NEXT:    sub sp, sp, #16
+; SDAG-NEXT:    mov x1, xzr
+; SDAG-NEXT:    mov x0, x1
+; SDAG-NEXT:    str x1, [sp] // 8-byte Folded Spill
+; SDAG-NEXT:    str x0, [sp, #8] // 8-byte Folded Spill
+; SDAG-NEXT:    b .LBB0_1
+; SDAG-NEXT:  .LBB0_1: // %loop
+; SDAG-NEXT:    // =>This Inner Loop Header: Depth=1
+; SDAG-NEXT:    ldr x0, [sp, #8] // 8-byte Folded Reload
+; SDAG-NEXT:    ldr x1, [sp] // 8-byte Folded Reload
+; SDAG-NEXT:    str x1, [sp] // 8-byte Folded Spill
+; SDAG-NEXT:    str x0, [sp, #8] // 8-byte Folded Spill
+; SDAG-NEXT:    b .LBB0_1
 entry:
   br label %loop