[RISCV][GISel] Force atomic G_LOAD/STORE to the GPR register bank. #162042
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
We don't have FPR isel patterns for G_LOAD/STORE so force to the GPR register bank.
|
@llvm/pr-subscribers-llvm-globalisel @llvm/pr-subscribers-backend-risc-v Author: Craig Topper (topperc) ChangesWe don't have FPR isel patterns for G_LOAD/STORE so force to the GPR register bank. Patch is 34.14 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/162042.diff 2 Files Affected:
diff --git a/llvm/lib/Target/RISCV/GISel/RISCVRegisterBankInfo.cpp b/llvm/lib/Target/RISCV/GISel/RISCVRegisterBankInfo.cpp
index 597dd1271d394..9f9ae2f5c6dc6 100644
--- a/llvm/lib/Target/RISCV/GISel/RISCVRegisterBankInfo.cpp
+++ b/llvm/lib/Target/RISCV/GISel/RISCVRegisterBankInfo.cpp
@@ -324,6 +324,10 @@ RISCVRegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
OpdsMapping[0] = GPRValueMapping;
+ // Atomics always use GPR destinations. Don't refine any further.
+ if (cast<GLoad>(MI).isAtomic())
+ break;
+
// Use FPR64 for s64 loads on rv32.
if (GPRSize == 32 && Size.getFixedValue() == 64) {
assert(MF.getSubtarget<RISCVSubtarget>().hasStdExtD());
@@ -358,6 +362,10 @@ RISCVRegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
OpdsMapping[0] = GPRValueMapping;
+ // Atomics always use GPR sources. Don't refine any further.
+ if (cast<GStore>(MI).isAtomic())
+ break;
+
// Use FPR64 for s64 stores on rv32.
if (GPRSize == 32 && Size.getFixedValue() == 64) {
assert(MF.getSubtarget<RISCVSubtarget>().hasStdExtD());
diff --git a/llvm/test/CodeGen/RISCV/GlobalISel/atomic-load-store-fp.ll b/llvm/test/CodeGen/RISCV/GlobalISel/atomic-load-store-fp.ll
new file mode 100644
index 0000000000000..4ad2d2cc3e845
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/GlobalISel/atomic-load-store-fp.ll
@@ -0,0 +1,950 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -global-isel -mattr=+d -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefix=RV32I %s
+; RUN: llc -mtriple=riscv32 -global-isel -mattr=+d,+a,+no-trailing-seq-cst-fence \
+; RUN: -verify-machineinstrs < %s | FileCheck -check-prefixes=RV32IA,RV32IA-WMO %s
+; RUN: llc -mtriple=riscv32 -global-isel -mattr=+d,+a,+ztso,+no-trailing-seq-cst-fence \
+; RUN: -verify-machineinstrs < %s | FileCheck -check-prefixes=RV32IA,RV32IA-TSO %s
+; RUN: llc -mtriple=riscv64 -global-isel -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefix=RV64I %s
+; RUN: llc -mtriple=riscv64 -global-isel -mattr=+d,+a,+no-trailing-seq-cst-fence \
+; RUN: -verify-machineinstrs < %s | FileCheck -check-prefixes=RV64IA,RV64IA-WMO %s
+; RUN: llc -mtriple=riscv64 -global-isel -mattr=+d,+a,+ztso,+no-trailing-seq-cst-fence \
+; RUN: -verify-machineinstrs < %s | FileCheck -check-prefixes=RV64IA,RV64IA-TSO %s
+
+
+; RUN: llc -mtriple=riscv32 -global-isel -mattr=+d,+a -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefixes=RV32IA,RV32IA-WMO-TRAILING-FENCE %s
+; RUN: llc -mtriple=riscv32 -global-isel -mattr=+d,+a,+ztso -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefixes=RV32IA,RV32IA-TSO-TRAILING-FENCE %s
+
+; RUN: llc -mtriple=riscv64 -global-isel -mattr=+d,+a -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-WMO-TRAILING-FENCE %s
+; RUN: llc -mtriple=riscv64 -global-isel -mattr=+d,+a,+ztso -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefixes=RV64IA,RV64IA-TSO-TRAILING-FENCE %s
+
+
+define float @atomic_load_f32_unordered(ptr %a) nounwind {
+; RV32I-LABEL: atomic_load_f32_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
+; RV32I-NEXT: fmv.w.x fa0, a0
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV32IA-LABEL: atomic_load_f32_unordered:
+; RV32IA: # %bb.0:
+; RV32IA-NEXT: lw a0, 0(a0)
+; RV32IA-NEXT: fmv.w.x fa0, a0
+; RV32IA-NEXT: ret
+;
+; RV64I-LABEL: atomic_load_f32_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
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV64IA-LABEL: atomic_load_f32_unordered:
+; RV64IA: # %bb.0:
+; RV64IA-NEXT: lw a0, 0(a0)
+; RV64IA-NEXT: fmv.w.x fa0, a0
+; RV64IA-NEXT: ret
+ %1 = load atomic float, ptr %a unordered, align 4
+ ret float %1
+}
+
+define float @atomic_load_f32_monotonic(ptr %a) nounwind {
+; RV32I-LABEL: atomic_load_f32_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
+; RV32I-NEXT: fmv.w.x fa0, a0
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV32IA-LABEL: atomic_load_f32_monotonic:
+; RV32IA: # %bb.0:
+; RV32IA-NEXT: lw a0, 0(a0)
+; RV32IA-NEXT: fmv.w.x fa0, a0
+; RV32IA-NEXT: ret
+;
+; RV64I-LABEL: atomic_load_f32_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
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV64IA-LABEL: atomic_load_f32_monotonic:
+; RV64IA: # %bb.0:
+; RV64IA-NEXT: lw a0, 0(a0)
+; RV64IA-NEXT: fmv.w.x fa0, a0
+; RV64IA-NEXT: ret
+ %1 = load atomic float, ptr %a monotonic, align 4
+ ret float %1
+}
+
+define float @atomic_load_f32_acquire(ptr %a) nounwind {
+; RV32I-LABEL: atomic_load_f32_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
+; RV32I-NEXT: fmv.w.x fa0, a0
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV32IA-WMO-LABEL: atomic_load_f32_acquire:
+; RV32IA-WMO: # %bb.0:
+; RV32IA-WMO-NEXT: lw a0, 0(a0)
+; RV32IA-WMO-NEXT: fence r, rw
+; RV32IA-WMO-NEXT: fmv.w.x fa0, a0
+; RV32IA-WMO-NEXT: ret
+;
+; RV32IA-TSO-LABEL: atomic_load_f32_acquire:
+; RV32IA-TSO: # %bb.0:
+; RV32IA-TSO-NEXT: lw a0, 0(a0)
+; RV32IA-TSO-NEXT: fmv.w.x fa0, a0
+; RV32IA-TSO-NEXT: ret
+;
+; RV64I-LABEL: atomic_load_f32_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
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV64IA-WMO-LABEL: atomic_load_f32_acquire:
+; RV64IA-WMO: # %bb.0:
+; RV64IA-WMO-NEXT: lw a0, 0(a0)
+; RV64IA-WMO-NEXT: fence r, rw
+; RV64IA-WMO-NEXT: fmv.w.x fa0, a0
+; RV64IA-WMO-NEXT: ret
+;
+; RV64IA-TSO-LABEL: atomic_load_f32_acquire:
+; RV64IA-TSO: # %bb.0:
+; RV64IA-TSO-NEXT: lw a0, 0(a0)
+; RV64IA-TSO-NEXT: fmv.w.x fa0, a0
+; RV64IA-TSO-NEXT: ret
+;
+; RV32IA-WMO-TRAILING-FENCE-LABEL: atomic_load_f32_acquire:
+; RV32IA-WMO-TRAILING-FENCE: # %bb.0:
+; RV32IA-WMO-TRAILING-FENCE-NEXT: lw a0, 0(a0)
+; RV32IA-WMO-TRAILING-FENCE-NEXT: fence r, rw
+; RV32IA-WMO-TRAILING-FENCE-NEXT: fmv.w.x fa0, a0
+; RV32IA-WMO-TRAILING-FENCE-NEXT: ret
+;
+; RV32IA-TSO-TRAILING-FENCE-LABEL: atomic_load_f32_acquire:
+; RV32IA-TSO-TRAILING-FENCE: # %bb.0:
+; RV32IA-TSO-TRAILING-FENCE-NEXT: lw a0, 0(a0)
+; RV32IA-TSO-TRAILING-FENCE-NEXT: fmv.w.x fa0, a0
+; RV32IA-TSO-TRAILING-FENCE-NEXT: ret
+;
+; RV64IA-WMO-TRAILING-FENCE-LABEL: atomic_load_f32_acquire:
+; RV64IA-WMO-TRAILING-FENCE: # %bb.0:
+; RV64IA-WMO-TRAILING-FENCE-NEXT: lw a0, 0(a0)
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fence r, rw
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fmv.w.x fa0, a0
+; RV64IA-WMO-TRAILING-FENCE-NEXT: ret
+;
+; RV64IA-TSO-TRAILING-FENCE-LABEL: atomic_load_f32_acquire:
+; RV64IA-TSO-TRAILING-FENCE: # %bb.0:
+; RV64IA-TSO-TRAILING-FENCE-NEXT: lw a0, 0(a0)
+; RV64IA-TSO-TRAILING-FENCE-NEXT: fmv.w.x fa0, a0
+; RV64IA-TSO-TRAILING-FENCE-NEXT: ret
+ %1 = load atomic float, ptr %a acquire, align 4
+ ret float %1
+}
+
+define float @atomic_load_f32_seq_cst(ptr %a) nounwind {
+; RV32I-LABEL: atomic_load_f32_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
+; RV32I-NEXT: fmv.w.x fa0, a0
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV32IA-WMO-LABEL: atomic_load_f32_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: fmv.w.x fa0, a0
+; RV32IA-WMO-NEXT: ret
+;
+; RV32IA-TSO-LABEL: atomic_load_f32_seq_cst:
+; RV32IA-TSO: # %bb.0:
+; RV32IA-TSO-NEXT: fence rw, rw
+; RV32IA-TSO-NEXT: lw a0, 0(a0)
+; RV32IA-TSO-NEXT: fmv.w.x fa0, a0
+; RV32IA-TSO-NEXT: ret
+;
+; RV64I-LABEL: atomic_load_f32_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
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV64IA-WMO-LABEL: atomic_load_f32_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: fmv.w.x fa0, a0
+; RV64IA-WMO-NEXT: ret
+;
+; RV64IA-TSO-LABEL: atomic_load_f32_seq_cst:
+; RV64IA-TSO: # %bb.0:
+; RV64IA-TSO-NEXT: fence rw, rw
+; RV64IA-TSO-NEXT: lw a0, 0(a0)
+; RV64IA-TSO-NEXT: fmv.w.x fa0, a0
+; RV64IA-TSO-NEXT: ret
+;
+; RV32IA-WMO-TRAILING-FENCE-LABEL: atomic_load_f32_seq_cst:
+; RV32IA-WMO-TRAILING-FENCE: # %bb.0:
+; RV32IA-WMO-TRAILING-FENCE-NEXT: fence rw, rw
+; RV32IA-WMO-TRAILING-FENCE-NEXT: lw a0, 0(a0)
+; RV32IA-WMO-TRAILING-FENCE-NEXT: fence r, rw
+; RV32IA-WMO-TRAILING-FENCE-NEXT: fmv.w.x fa0, a0
+; RV32IA-WMO-TRAILING-FENCE-NEXT: ret
+;
+; RV32IA-TSO-TRAILING-FENCE-LABEL: atomic_load_f32_seq_cst:
+; RV32IA-TSO-TRAILING-FENCE: # %bb.0:
+; RV32IA-TSO-TRAILING-FENCE-NEXT: fence rw, rw
+; RV32IA-TSO-TRAILING-FENCE-NEXT: lw a0, 0(a0)
+; RV32IA-TSO-TRAILING-FENCE-NEXT: fmv.w.x fa0, a0
+; RV32IA-TSO-TRAILING-FENCE-NEXT: ret
+;
+; RV64IA-WMO-TRAILING-FENCE-LABEL: atomic_load_f32_seq_cst:
+; RV64IA-WMO-TRAILING-FENCE: # %bb.0:
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fence rw, rw
+; RV64IA-WMO-TRAILING-FENCE-NEXT: lw a0, 0(a0)
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fence r, rw
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fmv.w.x fa0, a0
+; RV64IA-WMO-TRAILING-FENCE-NEXT: ret
+;
+; RV64IA-TSO-TRAILING-FENCE-LABEL: atomic_load_f32_seq_cst:
+; RV64IA-TSO-TRAILING-FENCE: # %bb.0:
+; RV64IA-TSO-TRAILING-FENCE-NEXT: fence rw, rw
+; RV64IA-TSO-TRAILING-FENCE-NEXT: lw a0, 0(a0)
+; RV64IA-TSO-TRAILING-FENCE-NEXT: fmv.w.x fa0, a0
+; RV64IA-TSO-TRAILING-FENCE-NEXT: ret
+ %1 = load atomic float, ptr %a seq_cst, align 4
+ ret float %1
+}
+
+define double @atomic_load_f64_unordered(ptr %a) nounwind {
+; RV32I-LABEL: atomic_load_f64_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
+; RV32I-NEXT: sw a0, 0(sp)
+; RV32I-NEXT: sw a1, 4(sp)
+; RV32I-NEXT: fld fa0, 0(sp)
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV32IA-LABEL: atomic_load_f64_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
+; RV32IA-NEXT: sw a0, 0(sp)
+; RV32IA-NEXT: sw a1, 4(sp)
+; RV32IA-NEXT: fld fa0, 0(sp)
+; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32IA-NEXT: addi sp, sp, 16
+; RV32IA-NEXT: ret
+;
+; RV64I-LABEL: atomic_load_f64_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
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV64IA-LABEL: atomic_load_f64_unordered:
+; RV64IA: # %bb.0:
+; RV64IA-NEXT: ld a0, 0(a0)
+; RV64IA-NEXT: fmv.d.x fa0, a0
+; RV64IA-NEXT: ret
+ %1 = load atomic double, ptr %a unordered, align 8
+ ret double %1
+}
+
+define double @atomic_load_f64_monotonic(ptr %a) nounwind {
+; RV32I-LABEL: atomic_load_f64_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
+; RV32I-NEXT: sw a0, 0(sp)
+; RV32I-NEXT: sw a1, 4(sp)
+; RV32I-NEXT: fld fa0, 0(sp)
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV32IA-LABEL: atomic_load_f64_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
+; RV32IA-NEXT: sw a0, 0(sp)
+; RV32IA-NEXT: sw a1, 4(sp)
+; RV32IA-NEXT: fld fa0, 0(sp)
+; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32IA-NEXT: addi sp, sp, 16
+; RV32IA-NEXT: ret
+;
+; RV64I-LABEL: atomic_load_f64_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
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV64IA-LABEL: atomic_load_f64_monotonic:
+; RV64IA: # %bb.0:
+; RV64IA-NEXT: ld a0, 0(a0)
+; RV64IA-NEXT: fmv.d.x fa0, a0
+; RV64IA-NEXT: ret
+ %1 = load atomic double, ptr %a monotonic, align 8
+ ret double %1
+}
+
+define double @atomic_load_f64_acquire(ptr %a) nounwind {
+; RV32I-LABEL: atomic_load_f64_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
+; RV32I-NEXT: sw a0, 0(sp)
+; RV32I-NEXT: sw a1, 4(sp)
+; RV32I-NEXT: fld fa0, 0(sp)
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV32IA-LABEL: atomic_load_f64_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
+; RV32IA-NEXT: sw a0, 0(sp)
+; RV32IA-NEXT: sw a1, 4(sp)
+; RV32IA-NEXT: fld fa0, 0(sp)
+; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32IA-NEXT: addi sp, sp, 16
+; RV32IA-NEXT: ret
+;
+; RV64I-LABEL: atomic_load_f64_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
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV64IA-WMO-LABEL: atomic_load_f64_acquire:
+; RV64IA-WMO: # %bb.0:
+; RV64IA-WMO-NEXT: ld a0, 0(a0)
+; RV64IA-WMO-NEXT: fence r, rw
+; RV64IA-WMO-NEXT: fmv.d.x fa0, a0
+; RV64IA-WMO-NEXT: ret
+;
+; RV64IA-TSO-LABEL: atomic_load_f64_acquire:
+; RV64IA-TSO: # %bb.0:
+; RV64IA-TSO-NEXT: ld a0, 0(a0)
+; RV64IA-TSO-NEXT: fmv.d.x fa0, a0
+; RV64IA-TSO-NEXT: ret
+;
+; RV64IA-WMO-TRAILING-FENCE-LABEL: atomic_load_f64_acquire:
+; RV64IA-WMO-TRAILING-FENCE: # %bb.0:
+; RV64IA-WMO-TRAILING-FENCE-NEXT: ld a0, 0(a0)
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fence r, rw
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fmv.d.x fa0, a0
+; RV64IA-WMO-TRAILING-FENCE-NEXT: ret
+;
+; RV64IA-TSO-TRAILING-FENCE-LABEL: atomic_load_f64_acquire:
+; RV64IA-TSO-TRAILING-FENCE: # %bb.0:
+; RV64IA-TSO-TRAILING-FENCE-NEXT: ld a0, 0(a0)
+; RV64IA-TSO-TRAILING-FENCE-NEXT: fmv.d.x fa0, a0
+; RV64IA-TSO-TRAILING-FENCE-NEXT: ret
+ %1 = load atomic double, ptr %a acquire, align 8
+ ret double %1
+}
+
+define double @atomic_load_f64_seq_cst(ptr %a) nounwind {
+; RV32I-LABEL: atomic_load_f64_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
+; RV32I-NEXT: sw a0, 0(sp)
+; RV32I-NEXT: sw a1, 4(sp)
+; RV32I-NEXT: fld fa0, 0(sp)
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV32IA-LABEL: atomic_load_f64_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
+; RV32IA-NEXT: sw a0, 0(sp)
+; RV32IA-NEXT: sw a1, 4(sp)
+; RV32IA-NEXT: fld fa0, 0(sp)
+; RV32IA-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32IA-NEXT: addi sp, sp, 16
+; RV32IA-NEXT: ret
+;
+; RV64I-LABEL: atomic_load_f64_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
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV64IA-WMO-LABEL: atomic_load_f64_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: fmv.d.x fa0, a0
+; RV64IA-WMO-NEXT: ret
+;
+; RV64IA-TSO-LABEL: atomic_load_f64_seq_cst:
+; RV64IA-TSO: # %bb.0:
+; RV64IA-TSO-NEXT: fence rw, rw
+; RV64IA-TSO-NEXT: ld a0, 0(a0)
+; RV64IA-TSO-NEXT: fmv.d.x fa0, a0
+; RV64IA-TSO-NEXT: ret
+;
+; RV64IA-WMO-TRAILING-FENCE-LABEL: atomic_load_f64_seq_cst:
+; RV64IA-WMO-TRAILING-FENCE: # %bb.0:
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fence rw, rw
+; RV64IA-WMO-TRAILING-FENCE-NEXT: ld a0, 0(a0)
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fence r, rw
+; RV64IA-WMO-TRAILING-FENCE-NEXT: fmv.d.x fa0, a0
+; RV64IA-WMO-TRAILING-FENCE-NEXT: ret
+;
+; RV64IA-TSO-TRAILING-FENCE-LABEL: atomic_load_f64_seq_cst:
+; RV64IA-TSO-TRAILING-FENCE: # %bb.0:
+; RV64IA-TSO-TRAILING-FENCE-NEXT: fence rw, rw
+; RV64IA-TSO-TRAILING-FENCE-NEXT: ld a0, 0(a0)
+; RV64IA-TSO-TRAILING-FENCE-NEXT: fmv.d.x fa0, a0
+; RV64IA-TSO-TRAILING-FENCE-NEXT: ret
+ %1 = load atomic double, ptr %a seq_cst, align 8
+ ret double %1
+}
+
+define void @atomic_store_f32_unordered(ptr %a, float %b) nounwind {
+; RV32I-LABEL: atomic_store_f32_unordered:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -16
+; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT: fmv.x.w a1, fa0
+; RV32I-NEXT: li a2, 0
+; RV32I-NEXT: call __atomic_store_4
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV32IA-LABEL: atomic_store_f32_unordered:
+; RV32IA: # %bb.0:
+; RV32IA-NEXT: fmv.x.w a1, fa0
+; RV32IA-NEXT: sw a1, 0(a0)
+; RV32IA-NEXT: ret
+;
+; RV64I-LABEL: atomic_store_f32_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
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV64IA-LABEL: atomic_store_f32_unordered:
+; RV64IA: # %bb.0:
+; RV64IA-NEXT: fmv.x.w a1, fa0
+; RV64IA-NEXT: sw a1, 0(a0)
+; RV64IA-NEXT: ret
+ store atomic float %b, ptr %a unordered, align 4
+ ret void
+}
+
+define void @atomic_store_f32_monotonic(ptr %a, float %b) nounwind {
+; RV32I-LABEL: atomic_store_f32_monotonic:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -16
+; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT: fmv.x.w a1, fa0
+; RV32I-NEXT: li a2...
[truncated]
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
We don't have FPR isel patterns for G_LOAD/STORE so force to the GPR register bank.