[clang] [llvm] [AARCH64][SVE] Add intrinsics for SVE LUTI instructions (PR #97058)
via cfe-commits
cfe-commits at lists.llvm.org
Fri Jun 28 06:53:11 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-ir
Author: None (Lukacma)
<details>
<summary>Changes</summary>
This patch adds intrinsics for LUTI2 and LUTI4 instructions, which use SVE registers, as specified in the https://github.com/ARM-software/acle/pull/324
---
Patch is 39.37 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/97058.diff
6 Files Affected:
- (modified) clang/include/clang/Basic/arm_sve.td (+20-1)
- (added) clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_luti.c (+336)
- (modified) clang/test/Sema/aarch64-sve2-intrinsics/acle_sve2_imm_lane.cpp (+32)
- (modified) llvm/include/llvm/IR/IntrinsicsAArch64.td (+20)
- (modified) llvm/lib/Target/AArch64/SVEInstrFormats.td (+36-1)
- (added) llvm/test/CodeGen/AArch64/sve2-intrinsics-luti.ll (+107)
``````````diff
diff --git a/clang/include/clang/Basic/arm_sve.td b/clang/include/clang/Basic/arm_sve.td
index 94c093d891156..dc999a5bbb3d8 100644
--- a/clang/include/clang/Basic/arm_sve.td
+++ b/clang/include/clang/Basic/arm_sve.td
@@ -1939,6 +1939,25 @@ def SVTBL2_BF16 : SInst<"svtbl2[_{d}]", "d2u", "b", MergeNone, "", [VerifyRunti
def SVTBX_BF16 : SInst<"svtbx[_{d}]", "dddu", "b", MergeNone, "aarch64_sve_tbx", [VerifyRuntimeMode]>;
}
+
+////////////////////////////////////////////////////////////////////////////////
+// SVE2 - Lookup table
+let SVETargetGuard = "sve2,lut", SMETargetGuard = "sme2,lut" in {
+ def SVLUTI2_B : SInst<"svluti2_lane[_{d}]", "dd[i", "cUc", MergeNone, "aarch64_sve_luti2_lane", [VerifyRuntimeMode], [ImmCheck<2, ImmCheck0_3>]>;
+ def SVLUTI2_H : SInst<"svluti2_lane[_{d}]", "dd[i", "sUsh", MergeNone, "aarch64_sve_luti2_lane", [VerifyRuntimeMode], [ImmCheck<2, ImmCheck0_7>]>;
+
+ def SVLUTI4_B : SInst<"svluti4_lane[_{d}]", "dd[i", "cUc", MergeNone, "aarch64_sve_luti4_lane", [VerifyRuntimeMode], [ImmCheck<2, ImmCheck0_1>]>;
+ def SVLUTI4_H : SInst<"svluti4_lane[_{d}]", "dd[i", "sUsh", MergeNone, "aarch64_sve_luti4_lane", [VerifyRuntimeMode], [ImmCheck<2, ImmCheck0_3>]>;
+
+ def SVLUTI4_x2 : SInst<"svluti4_lane[_{d}]_x2", "d2.d[i", "sUsh", MergeNone, "aarch64_sve_luti4_lane_x2", [VerifyRuntimeMode], [ImmCheck<2, ImmCheck0_3>]>;
+}
+
+let SVETargetGuard = "sve2,lut,bf16", SMETargetGuard = "sme2,lut,bf16" in {
+ def SVLUTI2_BF16 : SInst<"svluti2_lane[_{d}]", "dd[i", "b", MergeNone, "aarch64_sve_luti2_lane", [ VerifyRuntimeMode], [ImmCheck<2, ImmCheck0_7>]>;
+ def SVLUTI4_BF16 : SInst<"svluti4_lane[_{d}]", "dd[i", "b", MergeNone, "aarch64_sve_luti4_lane", [ VerifyRuntimeMode], [ImmCheck<2, ImmCheck0_3>]>;
+ def SVLUTI4_BF16_x2 : SInst<"svluti4_lane[_{d}]_x2", "d2.d[i", "b", MergeNone, "aarch64_sve_luti4_lane_x2", [ VerifyRuntimeMode], [ImmCheck<2, ImmCheck0_3>]>;
+}
+
////////////////////////////////////////////////////////////////////////////////
// SVE2 - Optional
@@ -2384,4 +2403,4 @@ let SVETargetGuard = "sve2p1", SMETargetGuard = "sme2" in {
def SVBFMLSLB_LANE : SInst<"svbfmlslb_lane[_{d}]", "dd$$i", "f", MergeNone, "aarch64_sve_bfmlslb_lane", [IsOverloadNone, VerifyRuntimeMode], [ImmCheck<3, ImmCheck0_7>]>;
def SVBFMLSLT_LANE : SInst<"svbfmlslt_lane[_{d}]", "dd$$i", "f", MergeNone, "aarch64_sve_bfmlslt_lane", [IsOverloadNone, VerifyRuntimeMode], [ImmCheck<3, ImmCheck0_7>]>;
-}
+}
\ No newline at end of file
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_luti.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_luti.c
new file mode 100644
index 0000000000000..d19246cba2d37
--- /dev/null
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_luti.c
@@ -0,0 +1,336 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// REQUIRES: aarch64-registered-target
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu \
+// RUN: -target-feature +sme -target-feature +sme2 -target-feature +lut -target-feature +bf16 -O1 -Werror -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu \
+// RUN: -target-feature +sve -target-feature +sve2 -target-feature +lut -target-feature +bf16 -O1 -Werror -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu \
+// RUN: -target-feature +sve -target-feature +sve2 -target-feature +lut -target-feature +bf16 -O1 -Werror -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu \
+// RUN: -target-feature +sve -target-feature +sve2 -target-feature +lut -target-feature +bf16 -O1 -Werror -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+#include <arm_sve.h>
+
+#if defined __ARM_FEATURE_SME
+#define MODE_ATTR __arm_streaming
+#else
+#define MODE_ATTR
+#endif
+
+#ifdef SVE_OVERLOADED_FORMS
+// A simple used,unused... macro, long enough to represent any SVE builtin.
+#define SVE_ACLE_FUNC(A1,A2_UNUSED,A3) A1##A3
+#else
+#define SVE_ACLE_FUNC(A1,A2,A3) A1##A2##A3
+#endif
+
+// SME-CHECK-LABEL: @test_svluti2_lane_s8(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// SME-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+// CHECK-LABEL: @test_svluti2_lane_s8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svluti2_lane_s8u10__SVInt8_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+svint8_t test_svluti2_lane_s8(svint8_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti2_lane,_s8,)(table, indices, 0);
+}
+
+// SME-CHECK-LABEL: @test_svluti2_lane_u8(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
+// SME-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+// CHECK-LABEL: @test_svluti2_lane_u8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
+// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svluti2_lane_u8u11__SVUint8_tS_(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
+// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+svuint8_t test_svluti2_lane_u8(svuint8_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti2_lane,_u8,)(table, indices, 3);
+}
+
+// SME-CHECK-LABEL: @test_svluti2_lane_s16(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// SME-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+// CHECK-LABEL: @test_svluti2_lane_s16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z21test_svluti2_lane_s16u11__SVInt16_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+svint16_t test_svluti2_lane_s16(svint16_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti2_lane,_s16,)(table, indices, 0);
+}
+
+// SME-CHECK-LABEL: @test_svluti2_lane_u16(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
+// SME-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+// CHECK-LABEL: @test_svluti2_lane_u16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
+// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z21test_svluti2_lane_u16u12__SVUint16_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
+// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+svuint16_t test_svluti2_lane_u16(svuint16_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti2_lane,_u16,)(table, indices, 7);
+}
+
+// SME-CHECK-LABEL: @test_svluti2_lane_f16(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti2.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 5)
+// SME-CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
+// CHECK-LABEL: @test_svluti2_lane_f16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti2.lane.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 5)
+// CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z21test_svluti2_lane_f16u13__SVFloat16_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti2.lane.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 5)
+// CPP-CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
+//
+svfloat16_t test_svluti2_lane_f16(svfloat16_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti2_lane,_f16,)(table, indices, 5);
+}
+
+// SME-CHECK-LABEL: @test_svluti2_lane_bf16(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti2.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
+// SME-CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP0]]
+// CHECK-LABEL: @test_svluti2_lane_bf16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti2.lane.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
+// CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z22test_svluti2_lane_bf16u14__SVBfloat16_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti2.lane.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
+// CPP-CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP0]]
+//
+svbfloat16_t test_svluti2_lane_bf16(svbfloat16_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti2_lane,_bf16,)(table, indices, 2);
+}
+
+// SME-CHECK-LABEL: @test_svluti4_lane_s8(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// SME-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+// CHECK-LABEL: @test_svluti4_lane_s8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svluti4_lane_s8u10__SVInt8_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+svint8_t test_svluti4_lane_s8(svint8_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti4_lane,_s8,)(table, indices, 0);
+}
+
+// SME-CHECK-LABEL: @test_svluti4_lane_u8(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
+// SME-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+// CHECK-LABEL: @test_svluti4_lane_u8(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
+// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z20test_svluti4_lane_u8u11__SVUint8_tS_(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
+// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
+//
+svuint8_t test_svluti4_lane_u8(svuint8_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti4_lane,_u8,)(table, indices, 1);
+}
+
+// SME-CHECK-LABEL: @test_svluti4_lane_s16(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// SME-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+// CHECK-LABEL: @test_svluti4_lane_s16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z21test_svluti4_lane_s16u11__SVInt16_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+svint16_t test_svluti4_lane_s16(svint16_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti4_lane,_s16,)(table, indices, 0);
+}
+
+// SME-CHECK-LABEL: @test_svluti4_lane_u16(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
+// SME-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+// CHECK-LABEL: @test_svluti4_lane_u16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
+// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z21test_svluti4_lane_u16u12__SVUint16_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
+// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
+//
+svuint16_t test_svluti4_lane_u16(svuint16_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti4_lane,_u16,)(table, indices, 3);
+}
+
+// SME-CHECK-LABEL: @test_svluti4_lane_f16(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 5)
+// SME-CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
+// CHECK-LABEL: @test_svluti4_lane_f16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.lane.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
+// CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z21test_svluti4_lane_f16u13__SVFloat16_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.lane.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
+// CPP-CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
+//
+svfloat16_t test_svluti4_lane_f16(svfloat16_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti4_lane,_f16,)(table, indices, 2);
+}
+
+// SME-CHECK-LABEL: @test_svluti4_lane_bf16(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
+// SME-CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP0]]
+// CHECK-LABEL: @test_svluti4_lane_bf16(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.lane.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
+// CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP0]]
+//
+// CPP-CHECK-LABEL: @_Z22test_svluti4_lane_bf16u14__SVBfloat16_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.lane.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
+// CPP-CHECK-NEXT: ret <vscale x 8 x bfloat> [[TMP0]]
+//
+svbfloat16_t test_svluti4_lane_bf16(svbfloat16_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti4_lane,_bf16,)(table, indices, 1);
+}
+
+// SME-CHECK-LABEL: @test_svluti4_lane_s16_x2(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE:%.*]], i64 0)
+// SME-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE]], i64 8)
+// SME-CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.x2.nxv8i16(<vscale x 8 x i16> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// SME-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]]
+// CHECK-LABEL: @test_svluti4_lane_s16_x2(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE]], i64 8)
+// CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.x2.nxv8i16(<vscale x 8 x i16> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]]
+//
+// CPP-CHECK-LABEL: @_Z24test_svluti4_lane_s16_x211svint16x2_tu11__SVUint8_t(
+// CPP-CHECK-NEXT: entry:
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE:%.*]], i64 0)
+// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE]], i64 8)
+// CPP-CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.x2.nxv8i16(<vscale x 8 x i16> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
+// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]]
+//
+svint16_t test_svluti4_lane_s16_x2(svint16x2_t table, svuint8_t indices) MODE_ATTR{
+ return SVE_ACLE_FUNC(svluti4_lane,_s16,_x2)(table, indices, 0);
+}
+
+// SME-CHECK-LABEL: @test_svluti4_lane_u16_x2(
+// SME-CHECK-NEXT: entry:
+// SME-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE:%.*]], i64 0)
+// SME-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE]], i64 8)
+// SME-CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.x2.nxv8i16(<vscale x 8 x i16> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
+// SME-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP2]]
+// CHECK-LABEL: @test_svluti4_lane_u16_x2(
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE:%.*]], i64 0)
+// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16>...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/97058
More information about the cfe-commits
mailing list