caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
7d2b9fafabd6f1a67e05ab2fa0abb5f7c8a451e7
clang-p2996/llvm/test/CodeGen/RISCV/atomic-load-store.ll
Philip Reames be6fe95673 [RISCV] Implement a proposed mapping for Ztso 
This change implements a proposed lowering from LLVM's memory model to the TSO memory model defined by the Ztso extension. Selecting the proposed mapping turns out to be an involved conversation that really didn't fit within a review description, so let me refer you to https://github.com/preames/public-notes/blob/master/riscv-tso-mappings.rst. This review implements the WMO compatible variant (the proposed one in that document).

Ztso is currently accepted as an experimental extension in LLVM. Despite the fact the extension was recently ratified, I think we need to leave it as experimental until we have wide agreement on the chosen mapping for ABI purposes.

I need to note that the current in-tree implementation defaults to generating WMO compatible fences. This is entirely compatible with the proposed mapping in this patch, but is unfortunately not compatible with the major alternative. The in tree implementation is explicitly experimental so the impact of this is limited, but it is worth calling out that if settle on the alternative we will have a minor ABI break. My apologies for not calling this out in the original patch; I had not realized at the time that one of our realistic choices for mappings wouldn't be WMO compatible.

This patch only contains the changes for load/store and fence. That is, it does not change the lowering for atomicrmw operations. This is a sound thing to do under the proposed mapping since the existing WMO mappings remain compatible. I do plan to change these; I'm just working incrementally.

Differential Revision: https://reviews.llvm.org/D143076
2023-02-09 12:00:05 -08:00

1324 lines
40 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32I %s
; RUN: llc -mtriple=riscv32 -mattr=+a -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefixes=RV32IA,RV32IA-WMO %s
; RUN: llc -mtriple=riscv32 -mattr=+a,+experimental-ztso -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefixes=RV32IA,RV32IA-TSO %s
; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV64I %s
; RUN: llc -mtriple=riscv64 -mattr=+a -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-WMO %s
; RUN: llc -mtriple=riscv64 -mattr=+a,+experimental-ztso -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-TSO %s
define i8 @atomic_load_i8_unordered(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i8_unordered:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 0
; RV32I-NEXT: call __atomic_load_1@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i8_unordered:
; RV32IA: # %bb.0:
; RV32IA-NEXT: lb a0, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i8_unordered:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __atomic_load_1@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_load_i8_unordered:
; RV64IA: # %bb.0:
; RV64IA-NEXT: lb a0, 0(a0)
; RV64IA-NEXT: ret
%1 = load atomic i8, ptr %a unordered, align 1
ret i8 %1
}
define i8 @atomic_load_i8_monotonic(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i8_monotonic:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 0
; RV32I-NEXT: call __atomic_load_1@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i8_monotonic:
; RV32IA: # %bb.0:
; RV32IA-NEXT: lb a0, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i8_monotonic:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __atomic_load_1@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_load_i8_monotonic:
; RV64IA: # %bb.0:
; RV64IA-NEXT: lb a0, 0(a0)
; RV64IA-NEXT: ret
%1 = load atomic i8, ptr %a monotonic, align 1
ret i8 %1
}
define i8 @atomic_load_i8_acquire(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i8_acquire:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 2
; RV32I-NEXT: call __atomic_load_1@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_load_i8_acquire:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: lb a0, 0(a0)
; RV32IA-WMO-NEXT: fence r, rw
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_load_i8_acquire:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: lb a0, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_load_i8_acquire:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 2
; RV64I-NEXT: call __atomic_load_1@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_load_i8_acquire:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: lb a0, 0(a0)
; RV64IA-WMO-NEXT: fence r, rw
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_load_i8_acquire:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: lb a0, 0(a0)
; RV64IA-TSO-NEXT: ret
%1 = load atomic i8, ptr %a acquire, align 1
ret i8 %1
}
define i8 @atomic_load_i8_seq_cst(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i8_seq_cst:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 5
; RV32I-NEXT: call __atomic_load_1@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_load_i8_seq_cst:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: fence rw, rw
; RV32IA-WMO-NEXT: lb a0, 0(a0)
; RV32IA-WMO-NEXT: fence r, rw
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_load_i8_seq_cst:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: fence rw, rw
; RV32IA-TSO-NEXT: lb a0, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_load_i8_seq_cst:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 5
; RV64I-NEXT: call __atomic_load_1@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_load_i8_seq_cst:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, rw
; RV64IA-WMO-NEXT: lb a0, 0(a0)
; RV64IA-WMO-NEXT: fence r, rw
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_load_i8_seq_cst:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: fence rw, rw
; RV64IA-TSO-NEXT: lb a0, 0(a0)
; RV64IA-TSO-NEXT: ret
%1 = load atomic i8, ptr %a seq_cst, align 1
ret i8 %1
}
define i16 @atomic_load_i16_unordered(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i16_unordered:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 0
; RV32I-NEXT: call __atomic_load_2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i16_unordered:
; RV32IA: # %bb.0:
; RV32IA-NEXT: lh a0, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i16_unordered:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __atomic_load_2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_load_i16_unordered:
; RV64IA: # %bb.0:
; RV64IA-NEXT: lh a0, 0(a0)
; RV64IA-NEXT: ret
%1 = load atomic i16, ptr %a unordered, align 2
ret i16 %1
}
define i16 @atomic_load_i16_monotonic(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i16_monotonic:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 0
; RV32I-NEXT: call __atomic_load_2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i16_monotonic:
; RV32IA: # %bb.0:
; RV32IA-NEXT: lh a0, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i16_monotonic:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __atomic_load_2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_load_i16_monotonic:
; RV64IA: # %bb.0:
; RV64IA-NEXT: lh a0, 0(a0)
; RV64IA-NEXT: ret
%1 = load atomic i16, ptr %a monotonic, align 2
ret i16 %1
}
define i16 @atomic_load_i16_acquire(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i16_acquire:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 2
; RV32I-NEXT: call __atomic_load_2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_load_i16_acquire:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: lh a0, 0(a0)
; RV32IA-WMO-NEXT: fence r, rw
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_load_i16_acquire:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: lh a0, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_load_i16_acquire:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 2
; RV64I-NEXT: call __atomic_load_2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_load_i16_acquire:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: lh a0, 0(a0)
; RV64IA-WMO-NEXT: fence r, rw
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_load_i16_acquire:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: lh a0, 0(a0)
; RV64IA-TSO-NEXT: ret
%1 = load atomic i16, ptr %a acquire, align 2
ret i16 %1
}
define i16 @atomic_load_i16_seq_cst(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i16_seq_cst:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 5
; RV32I-NEXT: call __atomic_load_2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_load_i16_seq_cst:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: fence rw, rw
; RV32IA-WMO-NEXT: lh a0, 0(a0)
; RV32IA-WMO-NEXT: fence r, rw
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_load_i16_seq_cst:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: fence rw, rw
; RV32IA-TSO-NEXT: lh a0, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_load_i16_seq_cst:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 5
; RV64I-NEXT: call __atomic_load_2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_load_i16_seq_cst:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, rw
; RV64IA-WMO-NEXT: lh a0, 0(a0)
; RV64IA-WMO-NEXT: fence r, rw
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_load_i16_seq_cst:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: fence rw, rw
; RV64IA-TSO-NEXT: lh a0, 0(a0)
; RV64IA-TSO-NEXT: ret
%1 = load atomic i16, ptr %a seq_cst, align 2
ret i16 %1
}
define i32 @atomic_load_i32_unordered(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i32_unordered:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 0
; RV32I-NEXT: call __atomic_load_4@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i32_unordered:
; RV32IA: # %bb.0:
; RV32IA-NEXT: lw a0, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i32_unordered:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __atomic_load_4@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_load_i32_unordered:
; RV64IA: # %bb.0:
; RV64IA-NEXT: lw a0, 0(a0)
; RV64IA-NEXT: ret
%1 = load atomic i32, ptr %a unordered, align 4
ret i32 %1
}
define i32 @atomic_load_i32_monotonic(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i32_monotonic:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 0
; RV32I-NEXT: call __atomic_load_4@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i32_monotonic:
; RV32IA: # %bb.0:
; RV32IA-NEXT: lw a0, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i32_monotonic:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __atomic_load_4@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_load_i32_monotonic:
; RV64IA: # %bb.0:
; RV64IA-NEXT: lw a0, 0(a0)
; RV64IA-NEXT: ret
%1 = load atomic i32, ptr %a monotonic, align 4
ret i32 %1
}
define i32 @atomic_load_i32_acquire(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i32_acquire:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 2
; RV32I-NEXT: call __atomic_load_4@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_load_i32_acquire:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: lw a0, 0(a0)
; RV32IA-WMO-NEXT: fence r, rw
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_load_i32_acquire:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: lw a0, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_load_i32_acquire:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 2
; RV64I-NEXT: call __atomic_load_4@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_load_i32_acquire:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: lw a0, 0(a0)
; RV64IA-WMO-NEXT: fence r, rw
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_load_i32_acquire:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: lw a0, 0(a0)
; RV64IA-TSO-NEXT: ret
%1 = load atomic i32, ptr %a acquire, align 4
ret i32 %1
}
define i32 @atomic_load_i32_seq_cst(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i32_seq_cst:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 5
; RV32I-NEXT: call __atomic_load_4@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_load_i32_seq_cst:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: fence rw, rw
; RV32IA-WMO-NEXT: lw a0, 0(a0)
; RV32IA-WMO-NEXT: fence r, rw
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_load_i32_seq_cst:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: fence rw, rw
; RV32IA-TSO-NEXT: lw a0, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_load_i32_seq_cst:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 5
; RV64I-NEXT: call __atomic_load_4@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_load_i32_seq_cst:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, rw
; RV64IA-WMO-NEXT: lw a0, 0(a0)
; RV64IA-WMO-NEXT: fence r, rw
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_load_i32_seq_cst:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: fence rw, rw
; RV64IA-TSO-NEXT: lw a0, 0(a0)
; RV64IA-TSO-NEXT: ret
%1 = load atomic i32, ptr %a seq_cst, align 4
ret i32 %1
}
define i64 @atomic_load_i64_unordered(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i64_unordered:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 0
; RV32I-NEXT: call __atomic_load_8@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i64_unordered:
; RV32IA: # %bb.0:
; RV32IA-NEXT: addi sp, sp, -16
; RV32IA-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IA-NEXT: li a1, 0
; RV32IA-NEXT: call __atomic_load_8@plt
; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IA-NEXT: addi sp, sp, 16
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i64_unordered:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __atomic_load_8@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_load_i64_unordered:
; RV64IA: # %bb.0:
; RV64IA-NEXT: ld a0, 0(a0)
; RV64IA-NEXT: ret
%1 = load atomic i64, ptr %a unordered, align 8
ret i64 %1
}
define i64 @atomic_load_i64_monotonic(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i64_monotonic:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 0
; RV32I-NEXT: call __atomic_load_8@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i64_monotonic:
; RV32IA: # %bb.0:
; RV32IA-NEXT: addi sp, sp, -16
; RV32IA-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IA-NEXT: li a1, 0
; RV32IA-NEXT: call __atomic_load_8@plt
; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IA-NEXT: addi sp, sp, 16
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i64_monotonic:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __atomic_load_8@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_load_i64_monotonic:
; RV64IA: # %bb.0:
; RV64IA-NEXT: ld a0, 0(a0)
; RV64IA-NEXT: ret
%1 = load atomic i64, ptr %a monotonic, align 8
ret i64 %1
}
define i64 @atomic_load_i64_acquire(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i64_acquire:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 2
; RV32I-NEXT: call __atomic_load_8@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i64_acquire:
; RV32IA: # %bb.0:
; RV32IA-NEXT: addi sp, sp, -16
; RV32IA-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IA-NEXT: li a1, 2
; RV32IA-NEXT: call __atomic_load_8@plt
; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IA-NEXT: addi sp, sp, 16
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i64_acquire:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 2
; RV64I-NEXT: call __atomic_load_8@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_load_i64_acquire:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: ld a0, 0(a0)
; RV64IA-WMO-NEXT: fence r, rw
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_load_i64_acquire:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: ld a0, 0(a0)
; RV64IA-TSO-NEXT: ret
%1 = load atomic i64, ptr %a acquire, align 8
ret i64 %1
}
define i64 @atomic_load_i64_seq_cst(ptr %a) nounwind {
; RV32I-LABEL: atomic_load_i64_seq_cst:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a1, 5
; RV32I-NEXT: call __atomic_load_8@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_load_i64_seq_cst:
; RV32IA: # %bb.0:
; RV32IA-NEXT: addi sp, sp, -16
; RV32IA-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IA-NEXT: li a1, 5
; RV32IA-NEXT: call __atomic_load_8@plt
; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IA-NEXT: addi sp, sp, 16
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_load_i64_seq_cst:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a1, 5
; RV64I-NEXT: call __atomic_load_8@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_load_i64_seq_cst:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, rw
; RV64IA-WMO-NEXT: ld a0, 0(a0)
; RV64IA-WMO-NEXT: fence r, rw
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_load_i64_seq_cst:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: fence rw, rw
; RV64IA-TSO-NEXT: ld a0, 0(a0)
; RV64IA-TSO-NEXT: ret
%1 = load atomic i64, ptr %a seq_cst, align 8
ret i64 %1
}
define void @atomic_store_i8_unordered(ptr %a, i8 %b) nounwind {
; RV32I-LABEL: atomic_store_i8_unordered:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __atomic_store_1@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i8_unordered:
; RV32IA: # %bb.0:
; RV32IA-NEXT: sb a1, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i8_unordered:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 0
; RV64I-NEXT: call __atomic_store_1@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_store_i8_unordered:
; RV64IA: # %bb.0:
; RV64IA-NEXT: sb a1, 0(a0)
; RV64IA-NEXT: ret
store atomic i8 %b, ptr %a unordered, align 1
ret void
}
define void @atomic_store_i8_monotonic(ptr %a, i8 %b) nounwind {
; RV32I-LABEL: atomic_store_i8_monotonic:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __atomic_store_1@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i8_monotonic:
; RV32IA: # %bb.0:
; RV32IA-NEXT: sb a1, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i8_monotonic:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 0
; RV64I-NEXT: call __atomic_store_1@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_store_i8_monotonic:
; RV64IA: # %bb.0:
; RV64IA-NEXT: sb a1, 0(a0)
; RV64IA-NEXT: ret
store atomic i8 %b, ptr %a monotonic, align 1
ret void
}
define void @atomic_store_i8_release(ptr %a, i8 %b) nounwind {
; RV32I-LABEL: atomic_store_i8_release:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 3
; RV32I-NEXT: call __atomic_store_1@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_store_i8_release:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: fence rw, w
; RV32IA-WMO-NEXT: sb a1, 0(a0)
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_store_i8_release:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: sb a1, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_store_i8_release:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 3
; RV64I-NEXT: call __atomic_store_1@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_store_i8_release:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, w
; RV64IA-WMO-NEXT: sb a1, 0(a0)
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_store_i8_release:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: sb a1, 0(a0)
; RV64IA-TSO-NEXT: ret
store atomic i8 %b, ptr %a release, align 1
ret void
}
define void @atomic_store_i8_seq_cst(ptr %a, i8 %b) nounwind {
; RV32I-LABEL: atomic_store_i8_seq_cst:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 5
; RV32I-NEXT: call __atomic_store_1@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_store_i8_seq_cst:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: fence rw, w
; RV32IA-WMO-NEXT: sb a1, 0(a0)
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_store_i8_seq_cst:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: sb a1, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_store_i8_seq_cst:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 5
; RV64I-NEXT: call __atomic_store_1@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_store_i8_seq_cst:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, w
; RV64IA-WMO-NEXT: sb a1, 0(a0)
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_store_i8_seq_cst:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: sb a1, 0(a0)
; RV64IA-TSO-NEXT: ret
store atomic i8 %b, ptr %a seq_cst, align 1
ret void
}
define void @atomic_store_i16_unordered(ptr %a, i16 %b) nounwind {
; RV32I-LABEL: atomic_store_i16_unordered:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __atomic_store_2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i16_unordered:
; RV32IA: # %bb.0:
; RV32IA-NEXT: sh a1, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i16_unordered:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 0
; RV64I-NEXT: call __atomic_store_2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_store_i16_unordered:
; RV64IA: # %bb.0:
; RV64IA-NEXT: sh a1, 0(a0)
; RV64IA-NEXT: ret
store atomic i16 %b, ptr %a unordered, align 2
ret void
}
define void @atomic_store_i16_monotonic(ptr %a, i16 %b) nounwind {
; RV32I-LABEL: atomic_store_i16_monotonic:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __atomic_store_2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i16_monotonic:
; RV32IA: # %bb.0:
; RV32IA-NEXT: sh a1, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i16_monotonic:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 0
; RV64I-NEXT: call __atomic_store_2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_store_i16_monotonic:
; RV64IA: # %bb.0:
; RV64IA-NEXT: sh a1, 0(a0)
; RV64IA-NEXT: ret
store atomic i16 %b, ptr %a monotonic, align 2
ret void
}
define void @atomic_store_i16_release(ptr %a, i16 %b) nounwind {
; RV32I-LABEL: atomic_store_i16_release:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 3
; RV32I-NEXT: call __atomic_store_2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_store_i16_release:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: fence rw, w
; RV32IA-WMO-NEXT: sh a1, 0(a0)
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_store_i16_release:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: sh a1, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_store_i16_release:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 3
; RV64I-NEXT: call __atomic_store_2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_store_i16_release:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, w
; RV64IA-WMO-NEXT: sh a1, 0(a0)
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_store_i16_release:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: sh a1, 0(a0)
; RV64IA-TSO-NEXT: ret
store atomic i16 %b, ptr %a release, align 2
ret void
}
define void @atomic_store_i16_seq_cst(ptr %a, i16 %b) nounwind {
; RV32I-LABEL: atomic_store_i16_seq_cst:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 5
; RV32I-NEXT: call __atomic_store_2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_store_i16_seq_cst:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: fence rw, w
; RV32IA-WMO-NEXT: sh a1, 0(a0)
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_store_i16_seq_cst:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: sh a1, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_store_i16_seq_cst:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 5
; RV64I-NEXT: call __atomic_store_2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_store_i16_seq_cst:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, w
; RV64IA-WMO-NEXT: sh a1, 0(a0)
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_store_i16_seq_cst:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: sh a1, 0(a0)
; RV64IA-TSO-NEXT: ret
store atomic i16 %b, ptr %a seq_cst, align 2
ret void
}
define void @atomic_store_i32_unordered(ptr %a, i32 %b) nounwind {
; RV32I-LABEL: atomic_store_i32_unordered:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __atomic_store_4@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i32_unordered:
; RV32IA: # %bb.0:
; RV32IA-NEXT: sw a1, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i32_unordered:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 0
; RV64I-NEXT: call __atomic_store_4@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_store_i32_unordered:
; RV64IA: # %bb.0:
; RV64IA-NEXT: sw a1, 0(a0)
; RV64IA-NEXT: ret
store atomic i32 %b, ptr %a unordered, align 4
ret void
}
define void @atomic_store_i32_monotonic(ptr %a, i32 %b) nounwind {
; RV32I-LABEL: atomic_store_i32_monotonic:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __atomic_store_4@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i32_monotonic:
; RV32IA: # %bb.0:
; RV32IA-NEXT: sw a1, 0(a0)
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i32_monotonic:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 0
; RV64I-NEXT: call __atomic_store_4@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_store_i32_monotonic:
; RV64IA: # %bb.0:
; RV64IA-NEXT: sw a1, 0(a0)
; RV64IA-NEXT: ret
store atomic i32 %b, ptr %a monotonic, align 4
ret void
}
define void @atomic_store_i32_release(ptr %a, i32 %b) nounwind {
; RV32I-LABEL: atomic_store_i32_release:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 3
; RV32I-NEXT: call __atomic_store_4@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_store_i32_release:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: fence rw, w
; RV32IA-WMO-NEXT: sw a1, 0(a0)
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_store_i32_release:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: sw a1, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_store_i32_release:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 3
; RV64I-NEXT: call __atomic_store_4@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_store_i32_release:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, w
; RV64IA-WMO-NEXT: sw a1, 0(a0)
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_store_i32_release:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: sw a1, 0(a0)
; RV64IA-TSO-NEXT: ret
store atomic i32 %b, ptr %a release, align 4
ret void
}
define void @atomic_store_i32_seq_cst(ptr %a, i32 %b) nounwind {
; RV32I-LABEL: atomic_store_i32_seq_cst:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a2, 5
; RV32I-NEXT: call __atomic_store_4@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-WMO-LABEL: atomic_store_i32_seq_cst:
; RV32IA-WMO: # %bb.0:
; RV32IA-WMO-NEXT: fence rw, w
; RV32IA-WMO-NEXT: sw a1, 0(a0)
; RV32IA-WMO-NEXT: ret
;
; RV32IA-TSO-LABEL: atomic_store_i32_seq_cst:
; RV32IA-TSO: # %bb.0:
; RV32IA-TSO-NEXT: sw a1, 0(a0)
; RV32IA-TSO-NEXT: ret
;
; RV64I-LABEL: atomic_store_i32_seq_cst:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 5
; RV64I-NEXT: call __atomic_store_4@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_store_i32_seq_cst:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, w
; RV64IA-WMO-NEXT: sw a1, 0(a0)
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_store_i32_seq_cst:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: sw a1, 0(a0)
; RV64IA-TSO-NEXT: ret
store atomic i32 %b, ptr %a seq_cst, align 4
ret void
}
define void @atomic_store_i64_unordered(ptr %a, i64 %b) nounwind {
; RV32I-LABEL: atomic_store_i64_unordered:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a3, 0
; RV32I-NEXT: call __atomic_store_8@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i64_unordered:
; RV32IA: # %bb.0:
; RV32IA-NEXT: addi sp, sp, -16
; RV32IA-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IA-NEXT: li a3, 0
; RV32IA-NEXT: call __atomic_store_8@plt
; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IA-NEXT: addi sp, sp, 16
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i64_unordered:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 0
; RV64I-NEXT: call __atomic_store_8@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_store_i64_unordered:
; RV64IA: # %bb.0:
; RV64IA-NEXT: sd a1, 0(a0)
; RV64IA-NEXT: ret
store atomic i64 %b, ptr %a unordered, align 8
ret void
}
define void @atomic_store_i64_monotonic(ptr %a, i64 %b) nounwind {
; RV32I-LABEL: atomic_store_i64_monotonic:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a3, 0
; RV32I-NEXT: call __atomic_store_8@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i64_monotonic:
; RV32IA: # %bb.0:
; RV32IA-NEXT: addi sp, sp, -16
; RV32IA-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IA-NEXT: li a3, 0
; RV32IA-NEXT: call __atomic_store_8@plt
; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IA-NEXT: addi sp, sp, 16
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i64_monotonic:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 0
; RV64I-NEXT: call __atomic_store_8@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-LABEL: atomic_store_i64_monotonic:
; RV64IA: # %bb.0:
; RV64IA-NEXT: sd a1, 0(a0)
; RV64IA-NEXT: ret
store atomic i64 %b, ptr %a monotonic, align 8
ret void
}
define void @atomic_store_i64_release(ptr %a, i64 %b) nounwind {
; RV32I-LABEL: atomic_store_i64_release:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a3, 3
; RV32I-NEXT: call __atomic_store_8@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i64_release:
; RV32IA: # %bb.0:
; RV32IA-NEXT: addi sp, sp, -16
; RV32IA-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IA-NEXT: li a3, 3
; RV32IA-NEXT: call __atomic_store_8@plt
; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IA-NEXT: addi sp, sp, 16
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i64_release:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 3
; RV64I-NEXT: call __atomic_store_8@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_store_i64_release:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, w
; RV64IA-WMO-NEXT: sd a1, 0(a0)
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_store_i64_release:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: sd a1, 0(a0)
; RV64IA-TSO-NEXT: ret
store atomic i64 %b, ptr %a release, align 8
ret void
}
define void @atomic_store_i64_seq_cst(ptr %a, i64 %b) nounwind {
; RV32I-LABEL: atomic_store_i64_seq_cst:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: li a3, 5
; RV32I-NEXT: call __atomic_store_8@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IA-LABEL: atomic_store_i64_seq_cst:
; RV32IA: # %bb.0:
; RV32IA-NEXT: addi sp, sp, -16
; RV32IA-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IA-NEXT: li a3, 5
; RV32IA-NEXT: call __atomic_store_8@plt
; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IA-NEXT: addi sp, sp, 16
; RV32IA-NEXT: ret
;
; RV64I-LABEL: atomic_store_i64_seq_cst:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: li a2, 5
; RV64I-NEXT: call __atomic_store_8@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IA-WMO-LABEL: atomic_store_i64_seq_cst:
; RV64IA-WMO: # %bb.0:
; RV64IA-WMO-NEXT: fence rw, w
; RV64IA-WMO-NEXT: sd a1, 0(a0)
; RV64IA-WMO-NEXT: ret
;
; RV64IA-TSO-LABEL: atomic_store_i64_seq_cst:
; RV64IA-TSO: # %bb.0:
; RV64IA-TSO-NEXT: sd a1, 0(a0)
; RV64IA-TSO-NEXT: ret
store atomic i64 %b, ptr %a seq_cst, align 8
ret void
}
Reference in New Issue View Git Blame Copy Permalink