[llvm] [RISCV][ISel] Add codegen support for the experimental zabha extension (PR #80192)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Jan 31 12:31:59 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-risc-v
Author: Yingwei Zheng (dtcxzyw)
<details>
<summary>Changes</summary>
This patch implements the codegen support of zabha (Byte and Halfword Atomic Memory Operations) v1.0-rc1 extension.
See also https://github.com/riscv/riscv-zabha/blob/v1.0-rc1/zabha.adoc.
---
Patch is 437.87 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/80192.diff
7 Files Affected:
- (modified) llvm/docs/RISCVUsage.rst (+1-1)
- (modified) llvm/docs/ReleaseNotes.rst (+1-1)
- (modified) llvm/lib/Target/RISCV/RISCVISelLowering.cpp (+19-4)
- (modified) llvm/lib/Target/RISCV/RISCVInstrInfoZa.td (+27)
- (modified) llvm/test/CodeGen/RISCV/atomic-cmpxchg-branch-on-result.ll (+22)
- (modified) llvm/test/CodeGen/RISCV/atomic-cmpxchg.ll (+942-180)
- (modified) llvm/test/CodeGen/RISCV/atomic-rmw.ll (+6451-850)
``````````diff
diff --git a/llvm/docs/RISCVUsage.rst b/llvm/docs/RISCVUsage.rst
index 5caf2fee197f2..156db36638984 100644
--- a/llvm/docs/RISCVUsage.rst
+++ b/llvm/docs/RISCVUsage.rst
@@ -227,7 +227,7 @@ LLVM supports (to various degrees) a number of experimental extensions. All exp
The primary goal of experimental support is to assist in the process of ratification by providing an existence proof of an implementation, and simplifying efforts to validate the value of a proposed extension against large code bases. Experimental extensions are expected to either transition to ratified status, or be eventually removed. The decision on whether to accept an experimental extension is currently done on an entirely case by case basis; if you want to propose one, attending the bi-weekly RISC-V sync-up call is strongly advised.
``experimental-zabha``
- LLVM implements assembler support for the `v1.0-rc1 draft specification <https://github.com/riscv/riscv-zabha/tree/v1.0-rc1>`_.
+ LLVM implements the `v1.0-rc1 draft specification <https://github.com/riscv/riscv-zabha/tree/v1.0-rc1>`_.
``experimental-zacas``
LLVM implements the `1.0-rc1 draft specification <https://github.com/riscv/riscv-zacas/releases/tag/v1.0-rc1>`_.
diff --git a/llvm/docs/ReleaseNotes.rst b/llvm/docs/ReleaseNotes.rst
index ad5b2ec1219e0..9810c02e78fd3 100644
--- a/llvm/docs/ReleaseNotes.rst
+++ b/llvm/docs/ReleaseNotes.rst
@@ -93,7 +93,7 @@ Changes to the RISC-V Backend
-----------------------------
* Support for the Zicond extension is no longer experimental.
-* Added assembler/disassembler support for the experimental Zabha (Byte and Halfword Atomic Memory Operations) extension.
+* Added full support for the experimental Zabha (Byte and Halfword Atomic Memory Operations) extension.
Changes to the WebAssembly Backend
----------------------------------
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index b8994e7b7bdb2..789acfce56810 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -629,7 +629,10 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
if (Subtarget.hasStdExtA()) {
setMaxAtomicSizeInBitsSupported(Subtarget.getXLen());
- setMinCmpXchgSizeInBits(32);
+ if (Subtarget.hasStdExtZabha())
+ setMinCmpXchgSizeInBits(8);
+ else
+ setMinCmpXchgSizeInBits(32);
} else if (Subtarget.hasForcedAtomics()) {
setMaxAtomicSizeInBitsSupported(Subtarget.getXLen());
} else {
@@ -19519,8 +19522,14 @@ RISCVTargetLowering::shouldExpandAtomicRMWInIR(AtomicRMWInst *AI) const {
return AtomicExpansionKind::None;
unsigned Size = AI->getType()->getPrimitiveSizeInBits();
- if (Size == 8 || Size == 16)
- return AtomicExpansionKind::MaskedIntrinsic;
+ if (Size == 8 || Size == 16) {
+ if (!Subtarget.hasStdExtZabha())
+ return AtomicExpansionKind::MaskedIntrinsic;
+ else if (AI->getOperation() == AtomicRMWInst::Nand)
+ return Subtarget.hasStdExtZacas() ? AtomicExpansionKind::CmpXChg
+ : AtomicExpansionKind::MaskedIntrinsic;
+ }
+
return AtomicExpansionKind::None;
}
@@ -19629,6 +19638,8 @@ Value *RISCVTargetLowering::emitMaskedAtomicRMWIntrinsic(
Builder.CreateCall(LrwOpScwLoop, {AlignedAddr, Incr, Mask, Ordering});
}
+ if (Subtarget.hasStdExtZabha())
+ return Builder.CreateTrunc(Result, AI->getValOperand()->getType());
if (XLen == 64)
Result = Builder.CreateTrunc(Result, Builder.getInt32Ty());
return Result;
@@ -19642,7 +19653,8 @@ RISCVTargetLowering::shouldExpandAtomicCmpXchgInIR(
return AtomicExpansionKind::None;
unsigned Size = CI->getCompareOperand()->getType()->getPrimitiveSizeInBits();
- if (Size == 8 || Size == 16)
+ if (!(Subtarget.hasStdExtZabha() && Subtarget.hasStdExtZacas()) &&
+ (Size == 8 || Size == 16))
return AtomicExpansionKind::MaskedIntrinsic;
return AtomicExpansionKind::None;
}
@@ -19664,6 +19676,9 @@ Value *RISCVTargetLowering::emitMaskedAtomicCmpXchgIntrinsic(
Intrinsic::getDeclaration(CI->getModule(), CmpXchgIntrID, Tys);
Value *Result = Builder.CreateCall(
MaskedCmpXchg, {AlignedAddr, CmpVal, NewVal, Mask, Ordering});
+
+ if (Subtarget.hasStdExtZabha())
+ return Builder.CreateTrunc(Result, CI->getCompareOperand()->getType());
if (XLen == 64)
Result = Builder.CreateTrunc(Result, Builder.getInt32Ty());
return Result;
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoZa.td b/llvm/lib/Target/RISCV/RISCVInstrInfoZa.td
index fa918d90ad160..0cd41cac218f9 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoZa.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoZa.td
@@ -185,3 +185,30 @@ let Predicates = [HasStdExtZabha, HasStdExtZacas] in {
defm AMOCAS_B : AMO_cas_aq_rl<0b00101, 0b000, "amocas.b", GPR>;
defm AMOCAS_H : AMO_cas_aq_rl<0b00101, 0b001, "amocas.h", GPR>;
}
+
+/// AMOs
+
+defm : AMOPat<"atomic_swap_8", "AMOSWAP_B", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_add_8", "AMOADD_B", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_and_8", "AMOAND_B", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_or_8", "AMOOR_B", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_xor_8", "AMOXOR_B", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_max_8", "AMOMAX_B", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_min_8", "AMOMIN_B", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_umax_8", "AMOMAXU_B", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_umin_8", "AMOMINU_B", XLenVT, [HasStdExtZabha]>;
+
+defm : AMOPat<"atomic_swap_16", "AMOSWAP_H", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_add_16", "AMOADD_H", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_and_16", "AMOAND_H", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_or_16", "AMOOR_H", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_xor_16", "AMOXOR_H", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_max_16", "AMOMAX_H", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_min_16", "AMOMIN_H", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_umax_16", "AMOMAXU_H", XLenVT, [HasStdExtZabha]>;
+defm : AMOPat<"atomic_load_umin_16", "AMOMINU_H", XLenVT, [HasStdExtZabha]>;
+
+/// AMOCAS
+
+defm : AMOCASPat<"atomic_cmp_swap_8", "AMOCAS_B", XLenVT, [HasStdExtZabha]>;
+defm : AMOCASPat<"atomic_cmp_swap_16", "AMOCAS_H", XLenVT, [HasStdExtZabha]>;
diff --git a/llvm/test/CodeGen/RISCV/atomic-cmpxchg-branch-on-result.ll b/llvm/test/CodeGen/RISCV/atomic-cmpxchg-branch-on-result.ll
index a8477cc550fe6..90d78779b764d 100644
--- a/llvm/test/CodeGen/RISCV/atomic-cmpxchg-branch-on-result.ll
+++ b/llvm/test/CodeGen/RISCV/atomic-cmpxchg-branch-on-result.ll
@@ -7,6 +7,8 @@
; RUN: | FileCheck -check-prefixes=NOZACAS,RV64IA %s
; RUN: llc -mtriple=riscv64 -mattr=+a,+experimental-zacas -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefixes=ZACAS,RV64IA-ZACAS %s
+; RUN: llc -mtriple=riscv64 -mattr=+a,+experimental-zacas,+experimental-zabha -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefixes=ZACAS,RV64IA-ZABHA %s
; Test cmpxchg followed by a branch on the cmpxchg success value to see if the
; branch is folded into the cmpxchg expansion.
@@ -209,6 +211,16 @@ define void @cmpxchg_masked_and_branch1(ptr %ptr, i8 signext %cmp, i8 signext %v
; RV64IA-ZACAS-NEXT: # %bb.5: # %do_cmpxchg
; RV64IA-ZACAS-NEXT: # %bb.2: # %exit
; RV64IA-ZACAS-NEXT: ret
+;
+; RV64IA-ZABHA-LABEL: cmpxchg_masked_and_branch1:
+; RV64IA-ZABHA: # %bb.0: # %entry
+; RV64IA-ZABHA-NEXT: .LBB2_1: # %do_cmpxchg
+; RV64IA-ZABHA-NEXT: # =>This Inner Loop Header: Depth=1
+; RV64IA-ZABHA-NEXT: mv a3, a1
+; RV64IA-ZABHA-NEXT: amocas.b.aqrl a3, a2, (a0)
+; RV64IA-ZABHA-NEXT: bne a3, a1, .LBB2_1
+; RV64IA-ZABHA-NEXT: # %bb.2: # %exit
+; RV64IA-ZABHA-NEXT: ret
entry:
br label %do_cmpxchg
do_cmpxchg:
@@ -351,6 +363,16 @@ define void @cmpxchg_masked_and_branch2(ptr %ptr, i8 signext %cmp, i8 signext %v
; RV64IA-ZACAS-NEXT: beq a1, a4, .LBB3_1
; RV64IA-ZACAS-NEXT: # %bb.2: # %exit
; RV64IA-ZACAS-NEXT: ret
+;
+; RV64IA-ZABHA-LABEL: cmpxchg_masked_and_branch2:
+; RV64IA-ZABHA: # %bb.0: # %entry
+; RV64IA-ZABHA-NEXT: .LBB3_1: # %do_cmpxchg
+; RV64IA-ZABHA-NEXT: # =>This Inner Loop Header: Depth=1
+; RV64IA-ZABHA-NEXT: mv a3, a1
+; RV64IA-ZABHA-NEXT: amocas.b.aqrl a3, a2, (a0)
+; RV64IA-ZABHA-NEXT: beq a3, a1, .LBB3_1
+; RV64IA-ZABHA-NEXT: # %bb.2: # %exit
+; RV64IA-ZABHA-NEXT: ret
entry:
br label %do_cmpxchg
do_cmpxchg:
diff --git a/llvm/test/CodeGen/RISCV/atomic-cmpxchg.ll b/llvm/test/CodeGen/RISCV/atomic-cmpxchg.ll
index 5b3e5789e8d91..8df37bf40975c 100644
--- a/llvm/test/CodeGen/RISCV/atomic-cmpxchg.ll
+++ b/llvm/test/CodeGen/RISCV/atomic-cmpxchg.ll
@@ -15,10 +15,14 @@
; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-WMO %s
; RUN: llc -mtriple=riscv64 -mattr=+a,+experimental-zacas -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-ZACAS,RV64IA-WMO-ZACAS %s
+; RUN: llc -mtriple=riscv64 -mattr=+a,+experimental-zacas,+experimental-zabha -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-ZABHA,RV64IA-WMO-ZABHA %s
; RUN: llc -mtriple=riscv64 -mattr=+a,+experimental-ztso -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-TSO %s
; RUN: llc -mtriple=riscv64 -mattr=+a,+experimental-ztso,+experimental-zacas -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-ZACAS,RV64IA-TSO-ZACAS %s
+; RUN: llc -mtriple=riscv64 -mattr=+a,+experimental-ztso,+experimental-zacas,+experimental-zabha -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-ZABHA,RV64IA-TSO-ZABHA %s
define void @cmpxchg_i8_monotonic_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV32I-LABEL: cmpxchg_i8_monotonic_monotonic:
@@ -70,28 +74,79 @@ define void @cmpxchg_i8_monotonic_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
-; RV64IA-LABEL: cmpxchg_i8_monotonic_monotonic:
-; RV64IA: # %bb.0:
-; RV64IA-NEXT: andi a3, a0, -4
-; RV64IA-NEXT: slli a0, a0, 3
-; RV64IA-NEXT: li a4, 255
-; RV64IA-NEXT: sllw a4, a4, a0
-; RV64IA-NEXT: andi a1, a1, 255
-; RV64IA-NEXT: sllw a1, a1, a0
-; RV64IA-NEXT: andi a2, a2, 255
-; RV64IA-NEXT: sllw a0, a2, a0
-; RV64IA-NEXT: .LBB0_1: # =>This Inner Loop Header: Depth=1
-; RV64IA-NEXT: lr.w a2, (a3)
-; RV64IA-NEXT: and a5, a2, a4
-; RV64IA-NEXT: bne a5, a1, .LBB0_3
-; RV64IA-NEXT: # %bb.2: # in Loop: Header=BB0_1 Depth=1
-; RV64IA-NEXT: xor a5, a2, a0
-; RV64IA-NEXT: and a5, a5, a4
-; RV64IA-NEXT: xor a5, a2, a5
-; RV64IA-NEXT: sc.w a5, a5, (a3)
-; RV64IA-NEXT: bnez a5, .LBB0_1
-; RV64IA-NEXT: .LBB0_3:
-; RV64IA-NEXT: ret
+; RV64IA-WMO-LABEL: cmpxchg_i8_monotonic_monotonic:
+; RV64IA-WMO: # %bb.0:
+; RV64IA-WMO-NEXT: andi a3, a0, -4
+; RV64IA-WMO-NEXT: slli a0, a0, 3
+; RV64IA-WMO-NEXT: li a4, 255
+; RV64IA-WMO-NEXT: sllw a4, a4, a0
+; RV64IA-WMO-NEXT: andi a1, a1, 255
+; RV64IA-WMO-NEXT: sllw a1, a1, a0
+; RV64IA-WMO-NEXT: andi a2, a2, 255
+; RV64IA-WMO-NEXT: sllw a0, a2, a0
+; RV64IA-WMO-NEXT: .LBB0_1: # =>This Inner Loop Header: Depth=1
+; RV64IA-WMO-NEXT: lr.w a2, (a3)
+; RV64IA-WMO-NEXT: and a5, a2, a4
+; RV64IA-WMO-NEXT: bne a5, a1, .LBB0_3
+; RV64IA-WMO-NEXT: # %bb.2: # in Loop: Header=BB0_1 Depth=1
+; RV64IA-WMO-NEXT: xor a5, a2, a0
+; RV64IA-WMO-NEXT: and a5, a5, a4
+; RV64IA-WMO-NEXT: xor a5, a2, a5
+; RV64IA-WMO-NEXT: sc.w a5, a5, (a3)
+; RV64IA-WMO-NEXT: bnez a5, .LBB0_1
+; RV64IA-WMO-NEXT: .LBB0_3:
+; RV64IA-WMO-NEXT: ret
+;
+; RV64IA-ZACAS-LABEL: cmpxchg_i8_monotonic_monotonic:
+; RV64IA-ZACAS: # %bb.0:
+; RV64IA-ZACAS-NEXT: andi a3, a0, -4
+; RV64IA-ZACAS-NEXT: slli a0, a0, 3
+; RV64IA-ZACAS-NEXT: li a4, 255
+; RV64IA-ZACAS-NEXT: sllw a4, a4, a0
+; RV64IA-ZACAS-NEXT: andi a1, a1, 255
+; RV64IA-ZACAS-NEXT: sllw a1, a1, a0
+; RV64IA-ZACAS-NEXT: andi a2, a2, 255
+; RV64IA-ZACAS-NEXT: sllw a0, a2, a0
+; RV64IA-ZACAS-NEXT: .LBB0_1: # =>This Inner Loop Header: Depth=1
+; RV64IA-ZACAS-NEXT: lr.w a2, (a3)
+; RV64IA-ZACAS-NEXT: and a5, a2, a4
+; RV64IA-ZACAS-NEXT: bne a5, a1, .LBB0_3
+; RV64IA-ZACAS-NEXT: # %bb.2: # in Loop: Header=BB0_1 Depth=1
+; RV64IA-ZACAS-NEXT: xor a5, a2, a0
+; RV64IA-ZACAS-NEXT: and a5, a5, a4
+; RV64IA-ZACAS-NEXT: xor a5, a2, a5
+; RV64IA-ZACAS-NEXT: sc.w a5, a5, (a3)
+; RV64IA-ZACAS-NEXT: bnez a5, .LBB0_1
+; RV64IA-ZACAS-NEXT: .LBB0_3:
+; RV64IA-ZACAS-NEXT: ret
+;
+; RV64IA-ZABHA-LABEL: cmpxchg_i8_monotonic_monotonic:
+; RV64IA-ZABHA: # %bb.0:
+; RV64IA-ZABHA-NEXT: amocas.b a1, a2, (a0)
+; RV64IA-ZABHA-NEXT: ret
+;
+; RV64IA-TSO-LABEL: cmpxchg_i8_monotonic_monotonic:
+; RV64IA-TSO: # %bb.0:
+; RV64IA-TSO-NEXT: andi a3, a0, -4
+; RV64IA-TSO-NEXT: slli a0, a0, 3
+; RV64IA-TSO-NEXT: li a4, 255
+; RV64IA-TSO-NEXT: sllw a4, a4, a0
+; RV64IA-TSO-NEXT: andi a1, a1, 255
+; RV64IA-TSO-NEXT: sllw a1, a1, a0
+; RV64IA-TSO-NEXT: andi a2, a2, 255
+; RV64IA-TSO-NEXT: sllw a0, a2, a0
+; RV64IA-TSO-NEXT: .LBB0_1: # =>This Inner Loop Header: Depth=1
+; RV64IA-TSO-NEXT: lr.w a2, (a3)
+; RV64IA-TSO-NEXT: and a5, a2, a4
+; RV64IA-TSO-NEXT: bne a5, a1, .LBB0_3
+; RV64IA-TSO-NEXT: # %bb.2: # in Loop: Header=BB0_1 Depth=1
+; RV64IA-TSO-NEXT: xor a5, a2, a0
+; RV64IA-TSO-NEXT: and a5, a5, a4
+; RV64IA-TSO-NEXT: xor a5, a2, a5
+; RV64IA-TSO-NEXT: sc.w a5, a5, (a3)
+; RV64IA-TSO-NEXT: bnez a5, .LBB0_1
+; RV64IA-TSO-NEXT: .LBB0_3:
+; RV64IA-TSO-NEXT: ret
%res = cmpxchg ptr %ptr, i8 %cmp, i8 %val monotonic monotonic
ret void
}
@@ -261,6 +316,11 @@ define void @cmpxchg_i8_acquire_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-WMO-ZACAS-NEXT: .LBB1_3:
; RV64IA-WMO-ZACAS-NEXT: ret
;
+; RV64IA-WMO-ZABHA-LABEL: cmpxchg_i8_acquire_monotonic:
+; RV64IA-WMO-ZABHA: # %bb.0:
+; RV64IA-WMO-ZABHA-NEXT: amocas.b.aq a1, a2, (a0)
+; RV64IA-WMO-ZABHA-NEXT: ret
+;
; RV64IA-TSO-LABEL: cmpxchg_i8_acquire_monotonic:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: andi a3, a0, -4
@@ -306,6 +366,11 @@ define void @cmpxchg_i8_acquire_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-TSO-ZACAS-NEXT: bnez a5, .LBB1_1
; RV64IA-TSO-ZACAS-NEXT: .LBB1_3:
; RV64IA-TSO-ZACAS-NEXT: ret
+;
+; RV64IA-TSO-ZABHA-LABEL: cmpxchg_i8_acquire_monotonic:
+; RV64IA-TSO-ZABHA: # %bb.0:
+; RV64IA-TSO-ZABHA-NEXT: amocas.b a1, a2, (a0)
+; RV64IA-TSO-ZABHA-NEXT: ret
%res = cmpxchg ptr %ptr, i8 %cmp, i8 %val acquire monotonic
ret void
}
@@ -475,6 +540,11 @@ define void @cmpxchg_i8_acquire_acquire(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-WMO-ZACAS-NEXT: .LBB2_3:
; RV64IA-WMO-ZACAS-NEXT: ret
;
+; RV64IA-WMO-ZABHA-LABEL: cmpxchg_i8_acquire_acquire:
+; RV64IA-WMO-ZABHA: # %bb.0:
+; RV64IA-WMO-ZABHA-NEXT: amocas.b.aq a1, a2, (a0)
+; RV64IA-WMO-ZABHA-NEXT: ret
+;
; RV64IA-TSO-LABEL: cmpxchg_i8_acquire_acquire:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: andi a3, a0, -4
@@ -520,6 +590,11 @@ define void @cmpxchg_i8_acquire_acquire(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-TSO-ZACAS-NEXT: bnez a5, .LBB2_1
; RV64IA-TSO-ZACAS-NEXT: .LBB2_3:
; RV64IA-TSO-ZACAS-NEXT: ret
+;
+; RV64IA-TSO-ZABHA-LABEL: cmpxchg_i8_acquire_acquire:
+; RV64IA-TSO-ZABHA: # %bb.0:
+; RV64IA-TSO-ZABHA-NEXT: amocas.b a1, a2, (a0)
+; RV64IA-TSO-ZABHA-NEXT: ret
%res = cmpxchg ptr %ptr, i8 %cmp, i8 %val acquire acquire
ret void
}
@@ -689,6 +764,11 @@ define void @cmpxchg_i8_release_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-WMO-ZACAS-NEXT: .LBB3_3:
; RV64IA-WMO-ZACAS-NEXT: ret
;
+; RV64IA-WMO-ZABHA-LABEL: cmpxchg_i8_release_monotonic:
+; RV64IA-WMO-ZABHA: # %bb.0:
+; RV64IA-WMO-ZABHA-NEXT: amocas.b.rl a1, a2, (a0)
+; RV64IA-WMO-ZABHA-NEXT: ret
+;
; RV64IA-TSO-LABEL: cmpxchg_i8_release_monotonic:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: andi a3, a0, -4
@@ -734,6 +814,11 @@ define void @cmpxchg_i8_release_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-TSO-ZACAS-NEXT: bnez a5, .LBB3_1
; RV64IA-TSO-ZACAS-NEXT: .LBB3_3:
; RV64IA-TSO-ZACAS-NEXT: ret
+;
+; RV64IA-TSO-ZABHA-LABEL: cmpxchg_i8_release_monotonic:
+; RV64IA-TSO-ZABHA: # %bb.0:
+; RV64IA-TSO-ZABHA-NEXT: amocas.b a1, a2, (a0)
+; RV64IA-TSO-ZABHA-NEXT: ret
%res = cmpxchg ptr %ptr, i8 %cmp, i8 %val release monotonic
ret void
}
@@ -903,6 +988,11 @@ define void @cmpxchg_i8_release_acquire(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-WMO-ZACAS-NEXT: .LBB4_3:
; RV64IA-WMO-ZACAS-NEXT: ret
;
+; RV64IA-WMO-ZABHA-LABEL: cmpxchg_i8_release_acquire:
+; RV64IA-WMO-ZABHA: # %bb.0:
+; RV64IA-WMO-ZABHA-NEXT: amocas.b.aqrl a1, a2, (a0)
+; RV64IA-WMO-ZABHA-NEXT: ret
+;
; RV64IA-TSO-LABEL: cmpxchg_i8_release_acquire:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: andi a3, a0, -4
@@ -948,6 +1038,11 @@ define void @cmpxchg_i8_release_acquire(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-TSO-ZACAS-NEXT: bnez a5, .LBB4_1
; RV64IA-TSO-ZACAS-NEXT: .LBB4_3:
; RV64IA-TSO-ZACAS-NEXT: ret
+;
+; RV64IA-TSO-ZABHA-LABEL: cmpxchg_i8_release_acquire:
+; RV64IA-TSO-ZABHA: # %bb.0:
+; RV64IA-TSO-ZABHA-NEXT: amocas.b a1, a2, (a0)
+; RV64IA-TSO-ZABHA-NEXT: ret
%res = cmpxchg ptr %ptr, i8 %cmp, i8 %val release acquire
ret void
}
@@ -1117,6 +1212,11 @@ define void @cmpxchg_i8_acq_rel_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-WMO-ZACAS-NEXT: .LBB5_3:
; RV64IA-WMO-ZACAS-NEXT: ret
;
+; RV64IA-WMO-ZABHA-LABEL: cmpxchg_i8_acq_rel_monotonic:
+; RV64IA-WMO-ZABHA: # %bb.0:
+; RV64IA-WMO-ZABHA-NEXT: amocas.b.aqrl a1, a2, (a0)
+; RV64IA-WMO-ZABHA-NEXT: ret
+;
; RV64IA-TSO-LABEL: cmpxchg_i8_acq_rel_monotonic:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: andi a3, a0, -4
@@ -1162,6 +1262,11 @@ define void @cmpxchg_i8_acq_rel_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-TSO-ZACAS-NEXT: bnez a5, .LBB5_1
; RV64IA-TSO-ZACAS-NEXT: .LBB5_3:
; RV64IA-TSO-ZACAS-NEXT: ret
+;
+; RV64IA-TSO-ZABHA-LABEL: cmpxchg_i8_acq_rel_monotonic:
+; RV64IA-TSO-ZABHA: # %bb.0:
+; RV64IA-TSO-ZABHA-NEXT: amocas.b a1, a2, (a0)
+; RV64IA-TSO-ZABHA-NEXT: ret
%res = cmpxchg ptr %ptr, i8 %cmp, i8 %val acq_rel monotonic
ret void
}
@@ -1331,6 +1436,11 @@ define void @cmpxchg_i8_acq_rel_acquire(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-WMO-ZACAS-NEXT: .LBB6_3:
; RV64IA-WMO-ZACAS-NEXT: ret
;
+; RV64IA-WMO-ZABHA-LABEL: cmpxchg_i8_acq_rel_acquire:
+; RV64IA-WMO-ZABHA: # %bb.0:
+; RV64IA-WMO-ZABHA-NEXT: amocas.b.aqrl a1, a2, (a0)
+; RV64IA-WMO-ZABHA-NEXT: ret
+;
; RV64IA-TSO-LABEL: cmpxchg_i8_acq_rel_acquire:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: andi a3, a0, -4
@@ -1376,6 +1486,11 @@ define void @cmpxchg_i8_acq_rel_acquire(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64IA-TSO-ZACAS-NEXT: bnez a5, .LBB6_1
; RV64IA-TSO-ZACAS-NEXT: .LBB6_3:
; RV64IA-TSO-ZACAS-NEXT: ret
+;
+; RV64IA-TSO-ZABHA-LABEL: cmpxchg_i8_acq_rel_acquire:
+; RV64IA-TSO-ZABHA: # %bb.0:
+; RV64IA-TSO-ZABHA-NEXT: amocas.b a1, a2, (a0)
+; RV64IA-TSO-ZABHA-NEXT: ret
%res = cmpxchg ptr %ptr, i8 %cmp, i8 %val acq_rel acquire
ret void
}
@@ -1430,28 +1545,84 @@ define void @cmpxchg_i8_seq_cst_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
-; RV64IA-LABEL: cmpxchg_i8_seq_cst_monotonic:
-; RV64IA: # %bb.0:
-; RV64IA-NEXT: andi a3, a0, -4
-; RV64IA-NEXT: slli a0, a0, 3
-; RV64IA-NEXT: li a4, 255
-; RV64IA-NEXT: sllw a4, a4, a0
-; RV64IA-NEXT: andi a1, a1, 255
-; RV64IA-NEXT: sllw a1, a1, a0
-; RV64IA-NEXT: andi a2, a2, 255
-; RV64IA-NEXT: sllw a0, a2, a0
-; RV64IA-NEXT: .LBB7_1: # =>This Inner Loop Header: Depth=1
-; RV64IA-NEXT: lr.w.aqrl a2, (a3)
-; RV64IA-NEXT: and a5, a2, a4
-; RV64IA-NEXT: bne a5, a1, .LBB7_3
-; RV64IA-NEXT: # %bb.2: # in Loop: Header=BB7_1 Depth=1
-; RV64IA-NEXT: xor a5, a2, a0
-; RV64IA-NEXT: and a5, a5, a4
-; RV64IA-NEXT: xor a5, a2, a5
-; RV64IA-NEXT: sc.w.rl a5, a5, (a3)
-; ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/80192
More information about the llvm-commits
mailing list