[llvm-branch-commits] [llvm] [Sparc] limit MaxAtomicSizeInBitsSupported to 32 for 32-bit Sparc. (#81655) (PR #81713)
Brad Smith via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Tue Feb 13 23:15:58 PST 2024
https://github.com/brad0 created https://github.com/llvm/llvm-project/pull/81713
When in 32-bit mode, the backend doesn't currently implement 64-bit atomics, even though the hardware is capable if you have specified a V9 CPU. Thus, limit the width to 32-bit, for now, leaving behind a TODO.
This fixes a regression triggered by PR #73176.
(cherry picked from commit c1a99b2c77499176362f24f09a39850867122ea4)
>From 564fbdef0327af0fb24939171b891955e1062ffc Mon Sep 17 00:00:00 2001
From: Brad Smith <brad at comstyle.com>
Date: Wed, 14 Feb 2024 02:11:56 -0500
Subject: [PATCH] [Sparc] limit MaxAtomicSizeInBitsSupported to 32 for 32-bit
Sparc. (#81655)
When in 32-bit mode, the backend doesn't currently implement 64-bit
atomics, even though the hardware is capable if you have specified a V9
CPU. Thus, limit the width to 32-bit, for now, leaving behind a TODO.
This fixes a regression triggered by PR #73176.
(cherry picked from commit c1a99b2c77499176362f24f09a39850867122ea4)
---
llvm/lib/Target/Sparc/SparcISelLowering.cpp | 11 +-
llvm/test/CodeGen/SPARC/64atomics.ll | 54 ++++----
.../CodeGen/SPARC/atomicrmw-uinc-udec-wrap.ll | 120 +++++++++---------
3 files changed, 96 insertions(+), 89 deletions(-)
diff --git a/llvm/lib/Target/Sparc/SparcISelLowering.cpp b/llvm/lib/Target/Sparc/SparcISelLowering.cpp
index bdefb0841a124b..13184a1eb0b101 100644
--- a/llvm/lib/Target/Sparc/SparcISelLowering.cpp
+++ b/llvm/lib/Target/Sparc/SparcISelLowering.cpp
@@ -1764,9 +1764,14 @@ SparcTargetLowering::SparcTargetLowering(const TargetMachine &TM,
// Atomics are supported on SparcV9. 32-bit atomics are also
// supported by some Leon SparcV8 variants. Otherwise, atomics
// are unsupported.
- if (Subtarget->isV9())
- setMaxAtomicSizeInBitsSupported(64);
- else if (Subtarget->hasLeonCasa())
+ if (Subtarget->isV9()) {
+ // TODO: we _ought_ to be able to support 64-bit atomics on 32-bit sparcv9,
+ // but it hasn't been implemented in the backend yet.
+ if (Subtarget->is64Bit())
+ setMaxAtomicSizeInBitsSupported(64);
+ else
+ setMaxAtomicSizeInBitsSupported(32);
+ } else if (Subtarget->hasLeonCasa())
setMaxAtomicSizeInBitsSupported(32);
else
setMaxAtomicSizeInBitsSupported(0);
diff --git a/llvm/test/CodeGen/SPARC/64atomics.ll b/llvm/test/CodeGen/SPARC/64atomics.ll
index 89175b6242e639..b11c0498fbbb46 100644
--- a/llvm/test/CodeGen/SPARC/64atomics.ll
+++ b/llvm/test/CodeGen/SPARC/64atomics.ll
@@ -1,12 +1,14 @@
-; RUN: llc < %s -march=sparcv9 -verify-machineinstrs | FileCheck %s
+; RUN: llc < %s -march=sparc -mcpu=v9 -verify-machineinstrs | FileCheck %s --check-prefixes=SPARC,SPARC32
+; RUN: llc < %s -march=sparcv9 -verify-machineinstrs | FileCheck %s --check-prefixes=SPARC,SPARC64
-; CHECK-LABEL: test_atomic_i64
-; CHECK: ldx [%o0]
-; CHECK: membar
-; CHECK: ldx [%o1]
-; CHECK: membar
-; CHECK: membar
-; CHECK: stx {{.+}}, [%o2]
+; SPARC-LABEL: test_atomic_i64
+; SPARC32: __atomic_load_8
+; SPARC64: ldx [%o0]
+; SPARC64: membar
+; SPARC64: ldx [%o1]
+; SPARC64: membar
+; SPARC64: membar
+; SPARC64: stx {{.+}}, [%o2]
define i64 @test_atomic_i64(i64* %ptr1, i64* %ptr2, i64* %ptr3) {
entry:
%0 = load atomic i64, i64* %ptr1 acquire, align 8
@@ -16,9 +18,10 @@ entry:
ret i64 %2
}
-; CHECK-LABEL: test_cmpxchg_i64
-; CHECK: mov 123, [[R:%[gilo][0-7]]]
-; CHECK: casx [%o1], %o0, [[R]]
+; SPARC-LABEL: test_cmpxchg_i64
+; SPARC32: __atomic_compare_exchange_8
+; SPARC64: mov 123, [[R:%[gilo][0-7]]]
+; SPARC64: casx [%o1], %o0, [[R]]
define i64 @test_cmpxchg_i64(i64 %a, i64* %ptr) {
entry:
@@ -27,8 +30,9 @@ entry:
ret i64 %b
}
-; CHECK-LABEL: test_swap_i64
-; CHECK: casx [%o1],
+; SPARC-LABEL: test_swap_i64
+; SPARC32: __atomic_exchange_8
+; SPARC64: casx [%o1],
define i64 @test_swap_i64(i64 %a, i64* %ptr) {
entry:
@@ -36,23 +40,25 @@ entry:
ret i64 %b
}
-; CHECK-LABEL: test_load_sub_64
-; CHECK: membar
-; CHECK: sub
-; CHECK: casx [%o0]
-; CHECK: membar
+; SPARC-LABEL: test_load_sub_64
+; SPARC32: __atomic_fetch_sub_8
+; SPARC64: membar
+; SPARC64: sub
+; SPARC64: casx [%o0]
+; SPARC64: membar
define zeroext i64 @test_load_sub_64(i64* %p, i64 zeroext %v) {
entry:
%0 = atomicrmw sub i64* %p, i64 %v seq_cst
ret i64 %0
}
-; CHECK-LABEL: test_load_max_64
-; CHECK: membar
-; CHECK: cmp
-; CHECK: movg %xcc
-; CHECK: casx [%o0]
-; CHECK: membar
+; SPARC-LABEL: test_load_max_64
+; SPARC32: __atomic_compare_exchange_8
+; SPARC64: membar
+; SPARC64: cmp
+; SPARC64: movg %xcc
+; SPARC64: casx [%o0]
+; SPARC64: membar
define zeroext i64 @test_load_max_64(i64* %p, i64 zeroext %v) {
entry:
%0 = atomicrmw max i64* %p, i64 %v seq_cst
diff --git a/llvm/test/CodeGen/SPARC/atomicrmw-uinc-udec-wrap.ll b/llvm/test/CodeGen/SPARC/atomicrmw-uinc-udec-wrap.ll
index 9b49035c460407..0f9feeb17716af 100644
--- a/llvm/test/CodeGen/SPARC/atomicrmw-uinc-udec-wrap.ll
+++ b/llvm/test/CodeGen/SPARC/atomicrmw-uinc-udec-wrap.ll
@@ -117,43 +117,41 @@ define i64 @atomicrmw_uinc_wrap_i64(ptr %ptr, i64 %val) {
; CHECK-LABEL: atomicrmw_uinc_wrap_i64:
; CHECK: .cfi_startproc
; CHECK-NEXT: ! %bb.0:
-; CHECK-NEXT: save %sp, -96, %sp
+; CHECK-NEXT: save %sp, -104, %sp
; CHECK-NEXT: .cfi_def_cfa_register %fp
; CHECK-NEXT: .cfi_window_save
; CHECK-NEXT: .cfi_register %o7, %i7
-; CHECK-NEXT: membar #LoadLoad | #StoreLoad | #LoadStore | #StoreStore
-; CHECK-NEXT: ldd [%i0], %i4
+; CHECK-NEXT: ldd [%i0], %g2
+; CHECK-NEXT: add %fp, -8, %i3
+; CHECK-NEXT: mov 5, %i4
; CHECK-NEXT: .LBB3_1: ! %atomicrmw.start
; CHECK-NEXT: ! =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: mov %g0, %i3
-; CHECK-NEXT: mov %g0, %g2
-; CHECK-NEXT: addcc %i5, 1, %o4
-; CHECK-NEXT: addxcc %i4, 0, %o3
-; CHECK-NEXT: cmp %i4, %i1
-; CHECK-NEXT: movcc %icc, 1, %i3
-; CHECK-NEXT: cmp %i5, %i2
-; CHECK-NEXT: movcc %icc, 1, %g2
-; CHECK-NEXT: cmp %i4, %i1
-; CHECK-NEXT: move %icc, %g2, %i3
-; CHECK-NEXT: cmp %i3, 0
+; CHECK-NEXT: mov %g0, %i5
+; CHECK-NEXT: mov %g0, %g4
+; CHECK-NEXT: addcc %g3, 1, %o3
+; CHECK-NEXT: addxcc %g2, 0, %o2
+; CHECK-NEXT: cmp %g2, %i1
+; CHECK-NEXT: movcc %icc, 1, %i5
+; CHECK-NEXT: cmp %g3, %i2
+; CHECK-NEXT: movcc %icc, 1, %g4
+; CHECK-NEXT: cmp %g2, %i1
+; CHECK-NEXT: move %icc, %g4, %i5
+; CHECK-NEXT: cmp %i5, 0
+; CHECK-NEXT: movne %icc, 0, %o2
; CHECK-NEXT: movne %icc, 0, %o3
-; CHECK-NEXT: movne %icc, 0, %o4
+; CHECK-NEXT: std %g2, [%fp+-8]
; CHECK-NEXT: mov %i0, %o0
-; CHECK-NEXT: mov %i4, %o1
-; CHECK-NEXT: call __sync_val_compare_and_swap_8
-; CHECK-NEXT: mov %i5, %o2
-; CHECK-NEXT: xor %o0, %i4, %i3
-; CHECK-NEXT: xor %o1, %i5, %i4
-; CHECK-NEXT: or %i4, %i3, %i3
-; CHECK-NEXT: mov %o1, %i5
-; CHECK-NEXT: cmp %i3, 0
-; CHECK-NEXT: bne %icc, .LBB3_1
-; CHECK-NEXT: mov %o0, %i4
+; CHECK-NEXT: mov %i3, %o1
+; CHECK-NEXT: mov %i4, %o4
+; CHECK-NEXT: call __atomic_compare_exchange_8
+; CHECK-NEXT: mov %i4, %o5
+; CHECK-NEXT: cmp %o0, 0
+; CHECK-NEXT: be %icc, .LBB3_1
+; CHECK-NEXT: ldd [%fp+-8], %g2
; CHECK-NEXT: ! %bb.2: ! %atomicrmw.end
-; CHECK-NEXT: membar #LoadLoad | #StoreLoad | #LoadStore | #StoreStore
-; CHECK-NEXT: mov %i4, %i0
+; CHECK-NEXT: mov %g2, %i0
; CHECK-NEXT: ret
-; CHECK-NEXT: restore %g0, %i5, %o1
+; CHECK-NEXT: restore %g0, %g3, %o1
%result = atomicrmw uinc_wrap ptr %ptr, i64 %val seq_cst
ret i64 %result
}
@@ -280,48 +278,46 @@ define i64 @atomicrmw_udec_wrap_i64(ptr %ptr, i64 %val) {
; CHECK-LABEL: atomicrmw_udec_wrap_i64:
; CHECK: .cfi_startproc
; CHECK-NEXT: ! %bb.0:
-; CHECK-NEXT: save %sp, -96, %sp
+; CHECK-NEXT: save %sp, -104, %sp
; CHECK-NEXT: .cfi_def_cfa_register %fp
; CHECK-NEXT: .cfi_window_save
; CHECK-NEXT: .cfi_register %o7, %i7
-; CHECK-NEXT: membar #LoadLoad | #StoreLoad | #LoadStore | #StoreStore
-; CHECK-NEXT: ldd [%i0], %i4
+; CHECK-NEXT: ldd [%i0], %g2
+; CHECK-NEXT: add %fp, -8, %i3
+; CHECK-NEXT: mov 5, %i4
; CHECK-NEXT: .LBB7_1: ! %atomicrmw.start
; CHECK-NEXT: ! =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: mov %g0, %i3
-; CHECK-NEXT: mov %g0, %g2
-; CHECK-NEXT: mov %g0, %g3
-; CHECK-NEXT: addcc %i5, -1, %o4
-; CHECK-NEXT: addxcc %i4, -1, %o3
-; CHECK-NEXT: or %i5, %i4, %g4
-; CHECK-NEXT: cmp %g4, 0
-; CHECK-NEXT: move %icc, 1, %i3
-; CHECK-NEXT: cmp %i4, %i1
-; CHECK-NEXT: movgu %icc, 1, %g2
-; CHECK-NEXT: cmp %i5, %i2
-; CHECK-NEXT: movgu %icc, 1, %g3
-; CHECK-NEXT: cmp %i4, %i1
-; CHECK-NEXT: move %icc, %g3, %g2
-; CHECK-NEXT: or %i3, %g2, %i3
-; CHECK-NEXT: cmp %i3, 0
-; CHECK-NEXT: movne %icc, %i1, %o3
-; CHECK-NEXT: movne %icc, %i2, %o4
+; CHECK-NEXT: mov %g0, %i5
+; CHECK-NEXT: mov %g0, %g4
+; CHECK-NEXT: mov %g0, %l0
+; CHECK-NEXT: addcc %g3, -1, %o3
+; CHECK-NEXT: addxcc %g2, -1, %o2
+; CHECK-NEXT: or %g3, %g2, %l1
+; CHECK-NEXT: cmp %l1, 0
+; CHECK-NEXT: move %icc, 1, %i5
+; CHECK-NEXT: cmp %g2, %i1
+; CHECK-NEXT: movgu %icc, 1, %g4
+; CHECK-NEXT: cmp %g3, %i2
+; CHECK-NEXT: movgu %icc, 1, %l0
+; CHECK-NEXT: cmp %g2, %i1
+; CHECK-NEXT: move %icc, %l0, %g4
+; CHECK-NEXT: or %i5, %g4, %i5
+; CHECK-NEXT: cmp %i5, 0
+; CHECK-NEXT: movne %icc, %i1, %o2
+; CHECK-NEXT: movne %icc, %i2, %o3
+; CHECK-NEXT: std %g2, [%fp+-8]
; CHECK-NEXT: mov %i0, %o0
-; CHECK-NEXT: mov %i4, %o1
-; CHECK-NEXT: call __sync_val_compare_and_swap_8
-; CHECK-NEXT: mov %i5, %o2
-; CHECK-NEXT: xor %o0, %i4, %i3
-; CHECK-NEXT: xor %o1, %i5, %i4
-; CHECK-NEXT: or %i4, %i3, %i3
-; CHECK-NEXT: mov %o1, %i5
-; CHECK-NEXT: cmp %i3, 0
-; CHECK-NEXT: bne %icc, .LBB7_1
-; CHECK-NEXT: mov %o0, %i4
+; CHECK-NEXT: mov %i3, %o1
+; CHECK-NEXT: mov %i4, %o4
+; CHECK-NEXT: call __atomic_compare_exchange_8
+; CHECK-NEXT: mov %i4, %o5
+; CHECK-NEXT: cmp %o0, 0
+; CHECK-NEXT: be %icc, .LBB7_1
+; CHECK-NEXT: ldd [%fp+-8], %g2
; CHECK-NEXT: ! %bb.2: ! %atomicrmw.end
-; CHECK-NEXT: membar #LoadLoad | #StoreLoad | #LoadStore | #StoreStore
-; CHECK-NEXT: mov %i4, %i0
+; CHECK-NEXT: mov %g2, %i0
; CHECK-NEXT: ret
-; CHECK-NEXT: restore %g0, %i5, %o1
+; CHECK-NEXT: restore %g0, %g3, %o1
%result = atomicrmw udec_wrap ptr %ptr, i64 %val seq_cst
ret i64 %result
}
More information about the llvm-branch-commits
mailing list