[clang] [AArch64][SME2] Add __arm_streaming_compatible attribute to CLAMP bui… (PR #76712)
Dinar Temirbulatov via cfe-commits
cfe-commits at lists.llvm.org
Tue Jan 2 04:04:44 PST 2024
https://github.com/dtemirbulatov created https://github.com/llvm/llvm-project/pull/76712
…ltins.
Patch-by: Caroline Concatto <caroline.concatto at arm.com>
>From d21c30bb3d655ab66e1ecb2f9b26dc441ca8928a Mon Sep 17 00:00:00 2001
From: Dinar Temirbulatov <Dinar.Temirbulatov at arm.com>
Date: Tue, 2 Jan 2024 12:01:17 +0000
Subject: [PATCH] [AArch64][SME2] Add __arm_streaming_compatible attribute to
CLAMP builtins.
Patch-by: Caroline Concatto <caroline.concatto at arm.com>
---
clang/include/clang/Basic/arm_sve.td | 4 ++--
.../acle_sve2p1_fclamp.c | 14 ++++++++++----
.../acle_sve2p1_sclamp.c | 17 ++++++++++++-----
.../acle_sve2p1_uclamp.c | 17 ++++++++++++-----
4 files changed, 36 insertions(+), 16 deletions(-)
diff --git a/clang/include/clang/Basic/arm_sve.td b/clang/include/clang/Basic/arm_sve.td
index 91f62c4c76339d..9b88be633aa55c 100644
--- a/clang/include/clang/Basic/arm_sve.td
+++ b/clang/include/clang/Basic/arm_sve.td
@@ -2052,8 +2052,8 @@ def SVDOT_LANE_X2_F : SInst<"svdot_lane[_{d}_{2}_{3}]", "ddhhi", "f", MergeNone
}
let TargetGuard = "sve2p1|sme" in {
-def SVSCLAMP : SInst<"svclamp[_{d}]", "dddd", "csil", MergeNone, "aarch64_sve_sclamp", [], []>;
-def SVUCLAMP : SInst<"svclamp[_{d}]", "dddd", "UcUsUiUl", MergeNone, "aarch64_sve_uclamp", [], []>;
+def SVSCLAMP : SInst<"svclamp[_{d}]", "dddd", "csil", MergeNone, "aarch64_sve_sclamp", [IsStreamingCompatible], []>;
+def SVUCLAMP : SInst<"svclamp[_{d}]", "dddd", "UcUsUiUl", MergeNone, "aarch64_sve_uclamp", [IsStreamingCompatible], []>;
defm SVREVD : SInstZPZ<"svrevd", "csilUcUsUiUlbhfd", "aarch64_sve_revd">;
}
diff --git a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_fclamp.c b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_fclamp.c
index 5d8c5b7b8a18c6..fd397292d1f2b6 100644
--- a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_fclamp.c
+++ b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_fclamp.c
@@ -10,7 +10,7 @@
// RUN: -S -Werror -emit-llvm -disable-O0-optnone -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sve2p1 \
// RUN: -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
-// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sme2 -target-feature +sve \
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sme2 -target-feature +sve -DTEST_SME2 \
// RUN: -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
#include <arm_sve.h>
@@ -22,6 +22,12 @@
#define SVE_ACLE_FUNC(A1, A2, A3, A4) A1##A2##A3##A4
#endif
+#ifndef TEST_SME2
+#define ATTR
+#else
+#define ATTR __arm_streaming_compatible
+#endif
+
// CHECK-LABEL: @test_svclamp_f16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fclamp.nxv8f16(<vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[OP3:%.*]])
@@ -32,7 +38,7 @@
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.fclamp.nxv8f16(<vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
//
-svfloat16_t test_svclamp_f16(svfloat16_t op1, svfloat16_t op2, svfloat16_t op3) {
+svfloat16_t test_svclamp_f16(svfloat16_t op1, svfloat16_t op2, svfloat16_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _f16, , )(op1, op2, op3);
}
@@ -46,7 +52,7 @@ svfloat16_t test_svclamp_f16(svfloat16_t op1, svfloat16_t op2, svfloat16_t op3)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.fclamp.nxv4f32(<vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 4 x float> [[TMP0]]
//
-svfloat32_t test_svclamp_f32(svfloat32_t op1, svfloat32_t op2, svfloat32_t op3) {
+svfloat32_t test_svclamp_f32(svfloat32_t op1, svfloat32_t op2, svfloat32_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _f32, , )(op1, op2, op3);
}
@@ -60,7 +66,7 @@ svfloat32_t test_svclamp_f32(svfloat32_t op1, svfloat32_t op2, svfloat32_t op3)
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.fclamp.nxv2f64(<vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 2 x double> [[TMP0]]
//
-svfloat64_t test_svclamp_f64(svfloat64_t op1, svfloat64_t op2, svfloat64_t op3) {
+svfloat64_t test_svclamp_f64(svfloat64_t op1, svfloat64_t op2, svfloat64_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _f64, , )(op1, op2, op3);
}
diff --git a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_sclamp.c b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_sclamp.c
index 8c63a7455c79f4..54c4c1c1679d7a 100644
--- a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_sclamp.c
+++ b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_sclamp.c
@@ -10,6 +10,8 @@
// RUN: -S -Werror -emit-llvm -disable-O0-optnone -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sve2p1 \
// RUN: -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sme2 -DTEST_SME2 \
+// RUN: -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
#include <arm_sve.h>
@@ -20,6 +22,12 @@
#define SVE_ACLE_FUNC(A1, A2, A3, A4) A1##A2##A3##A4
#endif
+#ifndef TEST_SME2
+#define ATTR
+#else
+#define ATTR __arm_streaming_compatible
+#endif
+
// CHECK-LABEL: @test_svclamp_s8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sclamp.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[OP3:%.*]])
@@ -30,7 +38,7 @@
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.sclamp.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
-svint8_t test_svclamp_s8(svint8_t op1, svint8_t op2, svint8_t op3) {
+svint8_t test_svclamp_s8(svint8_t op1, svint8_t op2, svint8_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _s8, , )(op1, op2, op3);
}
@@ -44,7 +52,7 @@ svint8_t test_svclamp_s8(svint8_t op1, svint8_t op2, svint8_t op3) {
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sclamp.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
-svint16_t test_svclamp_s16(svint16_t op1, svint16_t op2, svint16_t op3) {
+svint16_t test_svclamp_s16(svint16_t op1, svint16_t op2, svint16_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _s16, , )(op1, op2, op3);
}
@@ -58,7 +66,7 @@ svint16_t test_svclamp_s16(svint16_t op1, svint16_t op2, svint16_t op3) {
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.sclamp.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
-svint32_t test_svclamp_s32(svint32_t op1, svint32_t op2, svint32_t op3) {
+svint32_t test_svclamp_s32(svint32_t op1, svint32_t op2, svint32_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _s32, , )(op1, op2, op3);
}
@@ -72,7 +80,6 @@ svint32_t test_svclamp_s32(svint32_t op1, svint32_t op2, svint32_t op3) {
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.sclamp.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
-svint64_t test_svclamp_s64(svint64_t op1, svint64_t op2, svint64_t op3) {
+svint64_t test_svclamp_s64(svint64_t op1, svint64_t op2, svint64_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _s64, , )(op1, op2, op3);
}
-
diff --git a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_uclamp.c b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_uclamp.c
index b8789862488777..ecbb08679f2c53 100644
--- a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_uclamp.c
+++ b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_uclamp.c
@@ -10,6 +10,8 @@
// RUN: -S -Werror -emit-llvm -disable-O0-optnone -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sve2p1 \
// RUN: -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sme2 -target-feature +sve -DTEST_SME2 \
+// RUN: -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
#include <arm_sve.h>
@@ -20,6 +22,12 @@
#define SVE_ACLE_FUNC(A1, A2, A3, A4) A1##A2##A3##A4
#endif
+#ifndef TEST_SME2
+#define ATTR
+#else
+#define ATTR __arm_streaming_compatible
+#endif
+
// CHECK-LABEL: @test_svclamp_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uclamp.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[OP3:%.*]])
@@ -30,7 +38,7 @@
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.uclamp.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
-svuint8_t test_svclamp_u8(svuint8_t op1, svuint8_t op2, svuint8_t op3) {
+svuint8_t test_svclamp_u8(svuint8_t op1, svuint8_t op2, svuint8_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _u8, , )(op1, op2, op3);
}
@@ -44,7 +52,7 @@ svuint8_t test_svclamp_u8(svuint8_t op1, svuint8_t op2, svuint8_t op3) {
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.uclamp.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
-svuint16_t test_svclamp_u16(svuint16_t op1, svuint16_t op2, svuint16_t op3) {
+svuint16_t test_svclamp_u16(svuint16_t op1, svuint16_t op2, svuint16_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _u16, , )(op1, op2, op3);
}
@@ -58,7 +66,7 @@ svuint16_t test_svclamp_u16(svuint16_t op1, svuint16_t op2, svuint16_t op3) {
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.uclamp.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
-svuint32_t test_svclamp_u32(svuint32_t op1, svuint32_t op2, svuint32_t op3) {
+svuint32_t test_svclamp_u32(svuint32_t op1, svuint32_t op2, svuint32_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _u32, , )(op1, op2, op3);
}
@@ -72,7 +80,6 @@ svuint32_t test_svclamp_u32(svuint32_t op1, svuint32_t op2, svuint32_t op3) {
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.uclamp.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[OP3:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
-svuint64_t test_svclamp_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3) {
+svuint64_t test_svclamp_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3) ATTR {
return SVE_ACLE_FUNC(svclamp, _u64, , )(op1, op2, op3);
}
-
More information about the cfe-commits
mailing list