diff options
Diffstat (limited to 'llvm/test/CodeGen/AArch64')
4 files changed, 97 insertions, 12 deletions
diff --git a/llvm/test/CodeGen/AArch64/arm64-copy-phys-zero-reg.mir b/llvm/test/CodeGen/AArch64/arm64-copy-phys-zero-reg.mir index f34d3ed..6b2a31b 100644 --- a/llvm/test/CodeGen/AArch64/arm64-copy-phys-zero-reg.mir +++ b/llvm/test/CodeGen/AArch64/arm64-copy-phys-zero-reg.mir @@ -35,7 +35,7 @@ body: | ; CHECK-NOZCZ-GPR32-ZCZ-GPR64-LABEL: name: f0 ; CHECK-NOZCZ-GPR32-ZCZ-GPR64: liveins: $x0, $lr ; CHECK-NOZCZ-GPR32-ZCZ-GPR64-NEXT: {{ $}} - ; CHECK-NOZCZ-GPR32-ZCZ-GPR64-NEXT: $w0 = ORRWrr $wzr, $wzr + ; CHECK-NOZCZ-GPR32-ZCZ-GPR64-NEXT: $x0 = MOVZXi 0, 0 ; CHECK-NOZCZ-GPR32-ZCZ-GPR64-NEXT: BL @f2, csr_darwin_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $w0, implicit-def $sp, implicit-def $w0 ; ; CHECK-ZCZ-GPR32-ZCZ-GPR64-LABEL: name: f0 diff --git a/llvm/test/CodeGen/AArch64/arm64-vhadd.ll b/llvm/test/CodeGen/AArch64/arm64-vhadd.ll index 076cbf7..a505b42 100644 --- a/llvm/test/CodeGen/AArch64/arm64-vhadd.ll +++ b/llvm/test/CodeGen/AArch64/arm64-vhadd.ll @@ -1408,6 +1408,88 @@ define <4 x i16> @ext_via_i19(<4 x i16> %a) { ret <4 x i16> %t6 } +define <8 x i8> @srhadd_v8i8_trunc(<8 x i8> %s0, <8 x i8> %s1) { +; CHECK-LABEL: srhadd_v8i8_trunc: +; CHECK: // %bb.0: +; CHECK-NEXT: srhadd.8b v0, v0, v1 +; CHECK-NEXT: ret + %s0s = sext <8 x i8> %s0 to <8 x i16> + %s1s = sext <8 x i8> %s1 to <8 x i16> + %s = call <8 x i16> @llvm.aarch64.neon.urhadd.v8i16(<8 x i16> %s0s, <8 x i16> %s1s) + %s2 = trunc <8 x i16> %s to <8 x i8> + ret <8 x i8> %s2 +} + +define <4 x i16> @srhadd_v4i16_trunc(<4 x i16> %s0, <4 x i16> %s1) { +; CHECK-LABEL: srhadd_v4i16_trunc: +; CHECK: // %bb.0: +; CHECK-NEXT: srhadd.4h v0, v0, v1 +; CHECK-NEXT: ret + %s0s = sext <4 x i16> %s0 to <4 x i32> + %s1s = sext <4 x i16> %s1 to <4 x i32> + %s = call <4 x i32> @llvm.aarch64.neon.urhadd.v4i32(<4 x i32> %s0s, <4 x i32> %s1s) + %s2 = trunc <4 x i32> %s to <4 x i16> + ret <4 x i16> %s2 +} + +define <2 x i32> @srhadd_v2i32_trunc(<2 x i32> %s0, <2 x i32> %s1) { +; CHECK-LABEL: srhadd_v2i32_trunc: +; CHECK: // %bb.0: +; CHECK-NEXT: sshll.2d v0, v0, #0 +; CHECK-NEXT: sshll.2d v1, v1, #0 +; CHECK-NEXT: eor.16b v2, v0, v1 +; CHECK-NEXT: orr.16b v0, v0, v1 +; CHECK-NEXT: ushr.2d v1, v2, #1 +; CHECK-NEXT: sub.2d v0, v0, v1 +; CHECK-NEXT: xtn.2s v0, v0 +; CHECK-NEXT: ret + %s0s = sext <2 x i32> %s0 to <2 x i64> + %s1s = sext <2 x i32> %s1 to <2 x i64> + %s = call <2 x i64> @llvm.aarch64.neon.urhadd.v2i64(<2 x i64> %s0s, <2 x i64> %s1s) + %s2 = trunc <2 x i64> %s to <2 x i32> + ret <2 x i32> %s2 +} + +define <8 x i8> @urhadd_v8i8_trunc(<8 x i8> %s0, <8 x i8> %s1) { +; CHECK-LABEL: urhadd_v8i8_trunc: +; CHECK: // %bb.0: +; CHECK-NEXT: urhadd.8b v0, v0, v1 +; CHECK-NEXT: ret + %s0s = zext <8 x i8> %s0 to <8 x i16> + %s1s = zext <8 x i8> %s1 to <8 x i16> + %s = call <8 x i16> @llvm.aarch64.neon.srhadd.v8i16(<8 x i16> %s0s, <8 x i16> %s1s) + %s2 = trunc <8 x i16> %s to <8 x i8> + ret <8 x i8> %s2 +} + +define <4 x i16> @urhadd_v4i16_trunc(<4 x i16> %s0, <4 x i16> %s1) { +; CHECK-LABEL: urhadd_v4i16_trunc: +; CHECK: // %bb.0: +; CHECK-NEXT: urhadd.4h v0, v0, v1 +; CHECK-NEXT: ret + %s0s = zext <4 x i16> %s0 to <4 x i32> + %s1s = zext <4 x i16> %s1 to <4 x i32> + %s = call <4 x i32> @llvm.aarch64.neon.srhadd.v4i32(<4 x i32> %s0s, <4 x i32> %s1s) + %s2 = trunc <4 x i32> %s to <4 x i16> + ret <4 x i16> %s2 +} + +define <2 x i32> @urhadd_v2i32_trunc(<2 x i32> %s0, <2 x i32> %s1) { +; CHECK-LABEL: urhadd_v2i32_trunc: +; CHECK: // %bb.0: +; CHECK-NEXT: mov w8, #1 // =0x1 +; CHECK-NEXT: uaddl.2d v0, v0, v1 +; CHECK-NEXT: dup.2d v1, x8 +; CHECK-NEXT: add.2d v0, v0, v1 +; CHECK-NEXT: shrn.2s v0, v0, #1 +; CHECK-NEXT: ret + %s0s = zext <2 x i32> %s0 to <2 x i64> + %s1s = zext <2 x i32> %s1 to <2 x i64> + %s = call <2 x i64> @llvm.aarch64.neon.srhadd.v2i64(<2 x i64> %s0s, <2 x i64> %s1s) + %s2 = trunc <2 x i64> %s to <2 x i32> + ret <2 x i32> %s2 +} + declare <8 x i8> @llvm.aarch64.neon.srhadd.v8i8(<8 x i8>, <8 x i8>) declare <4 x i16> @llvm.aarch64.neon.srhadd.v4i16(<4 x i16>, <4 x i16>) declare <2 x i32> @llvm.aarch64.neon.srhadd.v2i32(<2 x i32>, <2 x i32>) diff --git a/llvm/test/CodeGen/AArch64/arm64-zero-cycle-zeroing-gpr.ll b/llvm/test/CodeGen/AArch64/arm64-zero-cycle-zeroing-gpr.ll index dc64306..0f284aa 100644 --- a/llvm/test/CodeGen/AArch64/arm64-zero-cycle-zeroing-gpr.ll +++ b/llvm/test/CodeGen/AArch64/arm64-zero-cycle-zeroing-gpr.ll @@ -1,41 +1,44 @@ -; RUN: llc < %s -mtriple=aarch64-linux-gnu | FileCheck %s -check-prefixes=ALL,NOZCZ-GPR +; RUN: llc < %s -mtriple=aarch64-linux-gnu | FileCheck %s -check-prefixes=ALL,NOZCZ-GPR32-NOZCZ-GPR64 ; RUN: llc < %s -mtriple=aarch64-linux-gnu -mattr=+zcz-gpr32 | FileCheck %s -check-prefixes=ALL,ZCZ-GPR32 -; RUN: llc < %s -mtriple=aarch64-linux-gnu -mattr=+zcz-gpr64 | FileCheck %s -check-prefixes=ALL,ZCZ-GPR64 -; RUN: llc < %s -mtriple=arm64-apple-macosx -mcpu=generic | FileCheck %s -check-prefixes=ALL,NOZCZ-GPR +; RUN: llc < %s -mtriple=aarch64-linux-gnu -mattr=+zcz-gpr64 | FileCheck %s -check-prefixes=ALL,NOZCZ-GPR32-ZCZ-GPR64 +; RUN: llc < %s -mtriple=arm64-apple-macosx -mcpu=generic | FileCheck %s -check-prefixes=ALL,NOZCZ-GPR32-NOZCZ-GPR64 ; RUN: llc < %s -mtriple=arm64-apple-ios -mcpu=cyclone | FileCheck %s -check-prefixes=ALL,ZCZ-GPR32,ZCZ-GPR64 ; RUN: llc < %s -mtriple=arm64-apple-macosx -mcpu=apple-m1 | FileCheck %s -check-prefixes=ALL,ZCZ-GPR32,ZCZ-GPR64 -; RUN: llc < %s -mtriple=aarch64-linux-gnu -mcpu=exynos-m3 | FileCheck %s -check-prefixes=ALL,NOZCZ-GPR +; RUN: llc < %s -mtriple=aarch64-linux-gnu -mcpu=exynos-m3 | FileCheck %s -check-prefixes=ALL,NOZCZ-GPR32-NOZCZ-GPR64 ; RUN: llc < %s -mtriple=aarch64-linux-gnu -mcpu=kryo | FileCheck %s -check-prefixes=ALL,ZCZ-GPR32,ZCZ-GPR64 ; RUN: llc < %s -mtriple=aarch64-linux-gnu -mcpu=falkor | FileCheck %s -check-prefixes=ALL,ZCZ-GPR32,ZCZ-GPR64 define i8 @ti8() { entry: ; ALL-LABEL: ti8: -; NOZCZ-GPR: mov w0, wzr +; NOZCZ-GPR32-NOZCZ-GPR64: mov w0, wzr ; ZCZ-GPR32: mov w0, #0 +; NOZCZ-GPR32-ZCZ-GPR64: mov x0, #0 ret i8 0 } define i16 @ti16() { entry: ; ALL-LABEL: ti16: -; NOZCZ-GPR: mov w0, wzr +; NOZCZ-GPR32-NOZCZ-GPR64: mov w0, wzr ; ZCZ-GPR32: mov w0, #0 +; NOZCZ-GPR32-ZCZ-GPR64: mov x0, #0 ret i16 0 } define i32 @ti32() { entry: ; ALL-LABEL: ti32: -; NOZCZ-GPR: mov w0, wzr +; NOZCZ-GPR32-NOZCZ-GPR64: mov w0, wzr ; ZCZ-GPR32: mov w0, #0 +; NOZCZ-GPR32-ZCZ-GPR64: mov x0, #0 ret i32 0 } define i64 @ti64() { entry: ; ALL-LABEL: ti64: -; NOZCZ-GPR: mov x0, xzr +; NOZCZ-GPR32-NOZCZ-GPR64 mov x0, xzr ; ZCZ-GPR64: mov x0, #0 ret i64 0 } diff --git a/llvm/test/CodeGen/AArch64/sme-support-routines-calling-convention.ll b/llvm/test/CodeGen/AArch64/sme-support-routines-calling-convention.ll index 63c6533..a5b7612 100644 --- a/llvm/test/CodeGen/AArch64/sme-support-routines-calling-convention.ll +++ b/llvm/test/CodeGen/AArch64/sme-support-routines-calling-convention.ll @@ -64,6 +64,6 @@ define i64 @test_sme_calling_convention_x2() nounwind { ret i64 %pstate.sm } -declare void @__arm_tpidr2_save() -declare i64 @__arm_get_current_vg() -declare {i64, i64} @__arm_sme_state() +declare aarch64_sme_preservemost_from_x0 void @__arm_tpidr2_save() +declare aarch64_sme_preservemost_from_x1 i64 @__arm_get_current_vg() +declare aarch64_sme_preservemost_from_x2 {i64, i64} @__arm_sme_state() |