Skip to content

AArch64: Enable terminal rule #165959

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wants to merge 1 commit into
base: users/arsenm/arm/enable-terminal-rule
Choose a base branch
from
Open

AArch64: Enable terminal rule #165959

wants to merge 1 commit into from
+177 −204

Conversation

@arsenm
Copy link
Contributor

@arsenm arsenm commented Nov 1, 2025

No description provided.

This was referenced Nov 1, 2025
Open
Open
Open
@arsenm Graphite App
Copy link
Contributor Author

arsenm commented Nov 1, 2025 •
edited
Loading

Warning

This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
Learn more

This stack of pull requests is managed by Graphite. Learn more about stacking.

This was referenced Nov 1, 2025
Open
Draft
Draft
@arsenm arsenm marked this pull request as ready for review November 1, 2025 02:52
@llvmbot
Copy link
Member

llvmbot commented Nov 1, 2025 •
edited
Loading

@llvm/pr-subscribers-backend-aarch64

@llvm/pr-subscribers-llvm-regalloc

Author: Matt Arsenault (arsenm)

Changes

Patch is 37.09 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/165959.diff

12 Files Affected:

  • (modified) llvm/lib/Target/AArch64/AArch64Subtarget.h (+1-1)
  • (modified) llvm/test/CodeGen/AArch64/build-vector-two-dup.ll (+5-5)
  • (modified) llvm/test/CodeGen/AArch64/machine-licm-sink-instr.ll (+15-24)
  • (modified) llvm/test/CodeGen/AArch64/machine-sink-kill-flags.ll (+2-3)
  • (modified) llvm/test/CodeGen/AArch64/sme-pstate-sm-changing-call-disable-coalescing.ll (+34-51)
  • (modified) llvm/test/CodeGen/AArch64/sme-streaming-compatible-interface.ll (+2-3)
  • (modified) llvm/test/CodeGen/AArch64/sve-extract-fixed-from-scalable-vector.ll (+6-6)
  • (modified) llvm/test/CodeGen/AArch64/sve-extract-fixed-vector.ll (+20-19)
  • (modified) llvm/test/CodeGen/AArch64/sve-fixed-length-reshuffle.ll (+6-6)
  • (modified) llvm/test/CodeGen/AArch64/sve-fixed-length-shuffles.ll (+36-36)
  • (modified) llvm/test/CodeGen/AArch64/sve-ptest-removal-sink.ll (+4-4)
  • (modified) llvm/test/CodeGen/AArch64/zext-to-tbl.ll (+46-46)
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
index 8974965c41fe3..ab4004e30f629 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -157,7 +157,7 @@ class AArch64Subtarget final : public AArch64GenSubtargetInfo {
   bool enableMachineScheduler() const override { return true; }
   bool enablePostRAScheduler() const override { return usePostRAScheduler(); }
   bool enableSubRegLiveness() const override { return EnableSubregLiveness; }
-
+  bool enableTerminalRule() const override { return true; }
   bool enableMachinePipeliner() const override;
   bool useDFAforSMS() const override { return false; }
 
diff --git a/llvm/test/CodeGen/AArch64/build-vector-two-dup.ll b/llvm/test/CodeGen/AArch64/build-vector-two-dup.ll
index dbbfbea9176f6..f725c19081deb 100644
--- a/llvm/test/CodeGen/AArch64/build-vector-two-dup.ll
+++ b/llvm/test/CodeGen/AArch64/build-vector-two-dup.ll
@@ -188,11 +188,11 @@ entry:
 define <8 x i8> @test11(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b) {
 ; CHECK-LABEL: test11:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    ld1r { v1.8b }, [x0]
-; CHECK-NEXT:    ld1r { v2.8b }, [x1]
-; CHECK-NEXT:    mov v0.16b, v1.16b
-; CHECK-NEXT:    mov v0.h[2], v2.h[0]
-; CHECK-NEXT:    mov v0.h[3], v1.h[0]
+; CHECK-NEXT:    ld1r { v0.8b }, [x0]
+; CHECK-NEXT:    ld1r { v1.8b }, [x1]
+; CHECK-NEXT:    fmov d2, d0
+; CHECK-NEXT:    mov v0.h[2], v1.h[0]
+; CHECK-NEXT:    mov v0.h[3], v2.h[0]
 ; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
 ; CHECK-NEXT:    ret
 entry:
diff --git a/llvm/test/CodeGen/AArch64/machine-licm-sink-instr.ll b/llvm/test/CodeGen/AArch64/machine-licm-sink-instr.ll
index 3230c9e946da7..b3a7ec961b736 100644
--- a/llvm/test/CodeGen/AArch64/machine-licm-sink-instr.ll
+++ b/llvm/test/CodeGen/AArch64/machine-licm-sink-instr.ll
@@ -20,20 +20,17 @@ define i32 @sink_load_and_copy(i32 %n) {
 ; CHECK-NEXT:    b.lt .LBB0_3
 ; CHECK-NEXT:  // %bb.1: // %for.body.preheader
 ; CHECK-NEXT:    adrp x8, A
-; CHECK-NEXT:    mov w20, w19
-; CHECK-NEXT:    ldr w21, [x8, :lo12:A]
+; CHECK-NEXT:    mov w21, w19
+; CHECK-NEXT:    ldr w20, [x8, :lo12:A]
 ; CHECK-NEXT:  .LBB0_2: // %for.body
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    mov w0, w21
+; CHECK-NEXT:    mov w0, w20
 ; CHECK-NEXT:    bl _Z3usei
-; CHECK-NEXT:    sdiv w20, w20, w0
-; CHECK-NEXT:    subs w19, w19, #1
+; CHECK-NEXT:    sdiv w19, w19, w0
+; CHECK-NEXT:    subs w21, w21, #1
 ; CHECK-NEXT:    b.ne .LBB0_2
-; CHECK-NEXT:    b .LBB0_4
-; CHECK-NEXT:  .LBB0_3:
-; CHECK-NEXT:    mov w20, w19
-; CHECK-NEXT:  .LBB0_4: // %for.cond.cleanup
-; CHECK-NEXT:    mov w0, w20
+; CHECK-NEXT:  .LBB0_3: // %for.cond.cleanup
+; CHECK-NEXT:    mov w0, w19
 ; CHECK-NEXT:    ldp x20, x19, [sp, #16] // 16-byte Folded Reload
 ; CHECK-NEXT:    ldp x30, x21, [sp], #32 // 16-byte Folded Reload
 ; CHECK-NEXT:    ret
@@ -82,15 +79,12 @@ define i32 @cant_sink_successive_call(i32 %n) {
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    mov w0, w20
 ; CHECK-NEXT:    bl _Z3usei
-; CHECK-NEXT:    sdiv w21, w21, w0
-; CHECK-NEXT:    subs w19, w19, #1
+; CHECK-NEXT:    sdiv w19, w19, w0
+; CHECK-NEXT:    subs w21, w21, #1
 ; CHECK-NEXT:    b.ne .LBB1_2
-; CHECK-NEXT:    b .LBB1_4
-; CHECK-NEXT:  .LBB1_3:
-; CHECK-NEXT:    mov w21, w19
-; CHECK-NEXT:  .LBB1_4: // %for.cond.cleanup
+; CHECK-NEXT:  .LBB1_3: // %for.cond.cleanup
+; CHECK-NEXT:    mov w0, w19
 ; CHECK-NEXT:    ldp x20, x19, [sp, #16] // 16-byte Folded Reload
-; CHECK-NEXT:    mov w0, w21
 ; CHECK-NEXT:    ldp x30, x21, [sp], #32 // 16-byte Folded Reload
 ; CHECK-NEXT:    ret
 entry:
@@ -139,15 +133,12 @@ define i32 @cant_sink_successive_store(ptr nocapture readnone %store, i32 %n) {
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    mov w0, w20
 ; CHECK-NEXT:    bl _Z3usei
-; CHECK-NEXT:    sdiv w21, w21, w0
-; CHECK-NEXT:    subs w19, w19, #1
+; CHECK-NEXT:    sdiv w19, w19, w0
+; CHECK-NEXT:    subs w21, w21, #1
 ; CHECK-NEXT:    b.ne .LBB2_2
-; CHECK-NEXT:    b .LBB2_4
-; CHECK-NEXT:  .LBB2_3:
-; CHECK-NEXT:    mov w21, w19
-; CHECK-NEXT:  .LBB2_4: // %for.cond.cleanup
+; CHECK-NEXT:  .LBB2_3: // %for.cond.cleanup
+; CHECK-NEXT:    mov w0, w19
 ; CHECK-NEXT:    ldp x20, x19, [sp, #16] // 16-byte Folded Reload
-; CHECK-NEXT:    mov w0, w21
 ; CHECK-NEXT:    ldp x30, x21, [sp], #32 // 16-byte Folded Reload
 ; CHECK-NEXT:    ret
 entry:
diff --git a/llvm/test/CodeGen/AArch64/machine-sink-kill-flags.ll b/llvm/test/CodeGen/AArch64/machine-sink-kill-flags.ll
index e7e109170d6a1..338084295fc7f 100644
--- a/llvm/test/CodeGen/AArch64/machine-sink-kill-flags.ll
+++ b/llvm/test/CodeGen/AArch64/machine-sink-kill-flags.ll
@@ -16,13 +16,12 @@ define i32 @test(ptr %ptr) {
 ; CHECK-NEXT:    mov w9, wzr
 ; CHECK-NEXT:  LBB0_1: ; %.thread
 ; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    lsr w11, w9, #1
 ; CHECK-NEXT:    sub w10, w9, #1
-; CHECK-NEXT:    mov w9, w11
+; CHECK-NEXT:    lsr w9, w9, #1
 ; CHECK-NEXT:    tbnz w10, #0, LBB0_1
 ; CHECK-NEXT:  ; %bb.2: ; %bb343
 ; CHECK-NEXT:    and w9, w10, #0x1
-; CHECK-NEXT:    mov w0, #-1
+; CHECK-NEXT:    mov w0, #-1 ; =0xffffffff
 ; CHECK-NEXT:    str w9, [x8]
 ; CHECK-NEXT:    ret
 bb:
diff --git a/llvm/test/CodeGen/AArch64/sme-pstate-sm-changing-call-disable-coalescing.ll b/llvm/test/CodeGen/AArch64/sme-pstate-sm-changing-call-disable-coalescing.ll
index b947c943ba448..72f6646930624 100644
--- a/llvm/test/CodeGen/AArch64/sme-pstate-sm-changing-call-disable-coalescing.ll
+++ b/llvm/test/CodeGen/AArch64/sme-pstate-sm-changing-call-disable-coalescing.ll
@@ -151,12 +151,11 @@ define void @dont_coalesce_arg_f16(half %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $h0 killed $h0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $h0 killed $h0 killed $z0
 ; CHECK-NEXT:    str h0, [sp, #14] // 2-byte Folded Spill
+; CHECK-NEXT:    // kill: def $h0 killed $h0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr h0, [sp, #14] // 2-byte Folded Reload
 ; CHECK-NEXT:    bl use_f16
@@ -190,12 +189,11 @@ define void @dont_coalesce_arg_f32(float %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $s0 killed $s0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $s0 killed $s0 killed $z0
 ; CHECK-NEXT:    str s0, [sp, #12] // 4-byte Folded Spill
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr s0, [sp, #12] // 4-byte Folded Reload
 ; CHECK-NEXT:    bl use_f32
@@ -229,12 +227,11 @@ define void @dont_coalesce_arg_f64(double %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
 ; CHECK-NEXT:    str d0, [sp, #8] // 8-byte Folded Spill
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr d0, [sp, #8] // 8-byte Folded Reload
 ; CHECK-NEXT:    bl use_f64
@@ -273,12 +270,11 @@ define void @dont_coalesce_arg_v1i8(<1 x i8> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
 ; CHECK-NEXT:    str d0, [sp, #8] // 8-byte Folded Spill
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr d0, [sp, #8] // 8-byte Folded Reload
 ; CHECK-NEXT:    bl use_v16i8
@@ -313,12 +309,11 @@ define void @dont_coalesce_arg_v1i16(<1 x i16> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
 ; CHECK-NEXT:    str d0, [sp, #8] // 8-byte Folded Spill
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr d0, [sp, #8] // 8-byte Folded Reload
 ; CHECK-NEXT:    bl use_v8i16
@@ -353,12 +348,11 @@ define void @dont_coalesce_arg_v1i32(<1 x i32> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
 ; CHECK-NEXT:    str d0, [sp, #8] // 8-byte Folded Spill
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr d0, [sp, #8] // 8-byte Folded Reload
 ; CHECK-NEXT:    bl use_v4i32
@@ -393,12 +387,11 @@ define void @dont_coalesce_arg_v1i64(<1 x i64> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
 ; CHECK-NEXT:    str d0, [sp, #8] // 8-byte Folded Spill
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr d0, [sp, #8] // 8-byte Folded Reload
 ; CHECK-NEXT:    bl use_v2i64
@@ -433,12 +426,11 @@ define void @dont_coalesce_arg_v1f16(<1 x half> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $h0 killed $h0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $h0 killed $h0 killed $z0
 ; CHECK-NEXT:    str h0, [sp, #14] // 2-byte Folded Spill
+; CHECK-NEXT:    // kill: def $h0 killed $h0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr h0, [sp, #14] // 2-byte Folded Reload
 ; CHECK-NEXT:    bl use_v8f16
@@ -513,12 +505,11 @@ define void @dont_coalesce_arg_v1f64(<1 x double> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
 ; CHECK-NEXT:    str d0, [sp, #8] // 8-byte Folded Spill
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr d0, [sp, #8] // 8-byte Folded Reload
 ; CHECK-NEXT:    bl use_v2f64
@@ -557,12 +548,11 @@ define void @dont_coalesce_arg_v16i8(<16 x i8> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
 ; CHECK-NEXT:    bl use_v16i8
@@ -596,12 +586,11 @@ define void @dont_coalesce_arg_v8i16(<8 x i16> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
 ; CHECK-NEXT:    bl use_v8i16
@@ -635,12 +624,11 @@ define void @dont_coalesce_arg_v4i32(<4 x i32> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
 ; CHECK-NEXT:    bl use_v4i32
@@ -674,12 +662,11 @@ define void @dont_coalesce_arg_v2i64(<2 x i64> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
 ; CHECK-NEXT:    bl use_v2i64
@@ -713,12 +700,11 @@ define void @dont_coalesce_arg_v8f16(<8 x half> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
 ; CHECK-NEXT:    bl use_v8f16
@@ -752,12 +738,11 @@ define void @dont_coalesce_arg_v8bf16(<8 x bfloat> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
 ; CHECK-NEXT:    bl use_v8bf16
@@ -791,12 +776,11 @@ define void @dont_coalesce_arg_v4f32(<4 x float> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
 ; CHECK-NEXT:    bl use_v4f32
@@ -830,12 +814,11 @@ define void @dont_coalesce_arg_v2f64(<2 x double> %arg, ptr %ptr) #0 {
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    mov x19, x0
-; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
+; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
 ; CHECK-NEXT:    smstop sm
 ; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
 ; CHECK-NEXT:    bl use_v2f64
diff --git a/llvm/test/CodeGen/AArch64/sme-streaming-compatible-interface.ll b/llvm/test/CodeGen/AArch64/sme-streaming-compatible-interface.ll
index f2163ad15bafc..df88f37195ed6 100644
--- a/llvm/test/CodeGen/AArch64/sme-streaming-compatible-interface.ll
+++ b/llvm/test/CodeGen/AArch64/sme-streaming-compatible-interface.ll
@@ -129,12 +129,11 @@ define <2 x double> @streaming_compatible_with_neon_vectors(<2 x double> %arg) "
 ; CHECK-NEXT:    stp x30, x19, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    sub sp, sp, #16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    mrs x19, SVCR
 ; CHECK-NEXT:    add x8, sp, #16
 ; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
 ; CHECK-NEXT:    str z0, [x8] // 16-byte Folded Spill
-; CHECK-NEXT:    mrs x19, SVCR
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
-; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
 ; CHECK-NEXT:    tbz w19, #0, .LBB4_2
 ; CHECK-NEXT:  // %bb.1:
 ; CHECK-NEXT:    smstop sm
diff --git a/llvm/test/CodeGen/AArch64/sve-extract-fixed-from-scalable-vector.ll b/llvm/test/CodeGen/AArch64/sve-extract-fixed-from-scalable-vector.ll
index 6c6a691760af3..52a77cb396909 100644
--- a/llvm/test/CodeGen/AArch64/sve-extract-fixed-from-scalable-vector.ll
+++ b/llvm/test/CodeGen/AArch64/sve-extract-fixed-from-scalable-vector.ll
@@ -147,15 +147,15 @@ define <2 x float> @extract_v2f32_nxv16f32_2(<vscale x 16 x float> %arg) {
 define <4 x i1> @extract_v4i1_nxv32i1_0(<vscale x 32 x i1> %arg) {
 ; CHECK-LABEL: extract_v4i1_nxv32i1_0:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.b, p0/z, #1 // =0x1
-; CHECK-NEXT:    umov w8, v1.b[1]
-; CHECK-NEXT:    mov v0.16b, v1.16b
-; CHECK-NEXT:    umov w9, v1.b[2]
+; CHECK-NEXT:    mov z0.b, p0/z, #1 // =0x1
+; CHECK-NEXT:    umov w8, v0.b[1]
+; CHECK-NEXT:    mov v1.16b, v0.16b
 ; CHECK-NEXT:    mov v0.h[1], w8
+; CHECK-NEXT:    umov w8, v1.b[2]
+; CHECK-NEXT:    mov v0.h[2], w8
 ; CHECK-NEXT:    umov w8, v1.b[3]
-; CHECK-NEXT:    mov v0.h[2], w9
 ; CHECK-NEXT:    mov v0.h[3], w8
-; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $z0
 ; CHECK-NEXT:    ...
[truncated]

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@androm3da androm3da Awaiting requested review from androm3da

@preames preames Awaiting requested review from preames

@qcolombet qcolombet Awaiting requested review from qcolombet

Assignees

No one assigned

Labels

backend:AArch64 llvm:regalloc

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@arsenm @llvmbot