Index: llvm/lib/Target/AArch64/AArch64InstrInfo.cpp =================================================================== --- llvm/lib/Target/AArch64/AArch64InstrInfo.cpp +++ llvm/lib/Target/AArch64/AArch64InstrInfo.cpp @@ -1409,6 +1409,20 @@ if (isLdStPairSuppressed(MI)) return false; + // Do not pair quad ld/st for Exynos. + if (Subtarget.isExynosM1()) { + switch (MI->getOpcode()) { + default: + break; + + case AArch64::LDURQi: + case AArch64::STURQi: + case AArch64::LDRQui: + case AArch64::STRQui: + return false; + } + } + return true; } Index: llvm/test/CodeGen/AArch64/arm64-ldp-cluster.ll =================================================================== --- llvm/test/CodeGen/AArch64/arm64-ldp-cluster.ll +++ llvm/test/CodeGen/AArch64/arm64-ldp-cluster.ll @@ -1,5 +1,6 @@ ; REQUIRES: asserts ; RUN: llc < %s -mtriple=arm64-linux-gnu -mcpu=cortex-a57 -verify-misched -debug-only=misched -o - 2>&1 > /dev/null | FileCheck %s +; RUN: llc < %s -mtriple=arm64-linux-gnu -mcpu=exynos-m1 -verify-misched -debug-only=misched -o - 2>&1 > /dev/null | FileCheck --check-prefix=EXYNOS %s ; Test ldr clustering. ; CHECK: ********** MI Scheduling ********** @@ -97,3 +98,18 @@ %tmp3 = add i32 %tmp1, %tmp2 ret i32 %tmp3 } + +; Test no ldq clustering for Exynos. +; EXYNOS: ********** MI Scheduling ********** +; EXYNOS-LABEL: exynos_ldq_no_cluster:BB#0 +; EXYNOS-NOT: Cluster loads +define <2 x i64> @exynos_ldq_no_cluster(i64* %p) { + %a1 = bitcast i64* %p to <2 x i64>* + %tmp1 = load <2 x i64>, < 2 x i64>* %a1, align 8 + %add.ptr2 = getelementptr inbounds i64, i64* %p, i64 2 + %a2 = bitcast i64* %add.ptr2 to <2 x i64>* + %tmp2 = mul nsw <2 x i64> %tmp1, %tmp1 + %tmp3 = load <2 x i64>, <2 x i64>* %a2, align 8 + %res = add nsw <2 x i64> %tmp2, %tmp3 + ret <2 x i64> %res +} Index: llvm/test/CodeGen/AArch64/exynos-quad-ldp-stp.ll =================================================================== --- /dev/null +++ llvm/test/CodeGen/AArch64/exynos-quad-ldp-stp.ll @@ -0,0 +1,28 @@ +; RUN: llc < %s -march=aarch64 -mcpu=exynos-m1 -verify-machineinstrs -asm-verbose=false | FileCheck %s + +; CHECK-LABEL: test_exynos_nopair_st +; CHECK: str +; CHECK: stur +; CHECK-NOT: stp +define void @test_exynos_nopair_st(double* %ptr, <2 x double> %v1, <2 x double> %v2) { + %tmp1 = bitcast double* %ptr to <2 x double>* + store <2 x double> %v2, <2 x double>* %tmp1, align 16 + %add.ptr = getelementptr inbounds double, double* %ptr, i64 -2 + %tmp = bitcast double* %add.ptr to <2 x double>* + store <2 x double> %v1, <2 x double>* %tmp, align 16 + ret void +} + +; CHECK-LABEL: test_exynos_nopair_ld +; CHECK: ldr +; CHECK: ldr +; CHECK-NOT: ldp +define <2 x i64> @test_exynos_nopair_ld(i64* %p) { + %a1 = bitcast i64* %p to <2 x i64>* + %tmp1 = load <2 x i64>, < 2 x i64>* %a1, align 8 + %add.ptr2 = getelementptr inbounds i64, i64* %p, i64 2 + %a2 = bitcast i64* %add.ptr2 to <2 x i64>* + %tmp2 = load <2 x i64>, <2 x i64>* %a2, align 8 + %add = add nsw <2 x i64> %tmp1, %tmp2 + ret <2 x i64> %add +}