[clang] [llvm] [Clang][LLVM][AArch64]SVE2.1 update the intrinsics according to acle[1] (PR #76842)
via cfe-commits
cfe-commits at lists.llvm.org
Wed Jan 3 10:55:21 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
Author: None (CarolineConcatto)
<details>
<summary>Changes</summary>
```svst1uwq[_{d}] replaced by svst1wq[_{d}]
svst1uwq_vnum[_{d}] replaced by svst1wq_vnum[_{d}]
svst1udq[_{d}] replaced by svst1dq[_{d}]
svst1udq_vnum[_{d}] replaced by svst1dq_vnum[_{d}]
```
Drops 'u' from the quadword stores because it is simply truncating the
quadwords to 32 bits
```
svextq_lane[_{d}] replaced by svextq[_{d}]
```
EXTQ follows the previous defined EXT intrinsics
```
svdot[_{d}_{2}_{3}] replaced by svdot[_{d}_{2}]
```
Introduced with the latest SME2 ACLE change
[1]https://github.com/ARM-software/acle/pull/257
---
Patch is 256.59 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/76842.diff
34 Files Affected:
- (modified) clang/include/clang/Basic/arm_sve.td (+11-11)
- (modified) clang/lib/CodeGen/CGBuiltin.cpp (+2-2)
- (modified) clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_dot.c (+6-6)
- (modified) clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_extq.c (+72-72)
- (modified) clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_st1_single.c (+72-72)
- (modified) clang/test/Sema/aarch64-sve2p1-intrinsics/acle_sve2p1_imm.cpp (+5-5)
- (modified) llvm/include/llvm/IR/IntrinsicsAArch64.td (+3-3)
- (modified) llvm/lib/Target/AArch64/AArch64ISelDAGToDAG.cpp (+2-2)
- (modified) llvm/lib/Target/AArch64/AArch64SMEInstrInfo.td (+1-1)
- (modified) llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td (+7-7)
- (modified) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-extq.ll (+16-16)
- (modified) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-st1-single.ll (+38-38)
- (modified) llvm/test/MC/AArch64/SME2p1/bfadd-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfadd.s (+55-55)
- (modified) llvm/test/MC/AArch64/SME2p1/bfclamp-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfclamp.s (+15-15)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmax-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmax.s (+23-23)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmaxnm-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmaxnm.s (+23-23)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmin-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmin.s (+23-23)
- (modified) llvm/test/MC/AArch64/SME2p1/bfminnm-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfminnm.s (+23-23)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmla-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmla.s (+151-151)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmls-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmls.s (+151-151)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmopa-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmopa.s (+19-19)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmops-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfmops.s (+19-19)
- (modified) llvm/test/MC/AArch64/SME2p1/bfsub-diagnostics.s (+1-1)
- (modified) llvm/test/MC/AArch64/SME2p1/bfsub.s (+55-55)
``````````diff
diff --git a/clang/include/clang/Basic/arm_sve.td b/clang/include/clang/Basic/arm_sve.td
index 04bf7acdeba799..f43ea996f4e927 100644
--- a/clang/include/clang/Basic/arm_sve.td
+++ b/clang/include/clang/Basic/arm_sve.td
@@ -454,11 +454,11 @@ let TargetGuard = "sve,bf16" in {
let TargetGuard = "sve2p1" in {
// Contiguous truncating store from quadword (single vector).
- def SVST1UWQ : MInst<"svst1uwq[_{d}]", "vPcd", "iUif", [IsStore], MemEltTyInt32, "aarch64_sve_st1uwq">;
- def SVST1UWQ_VNUM : MInst<"svst1uwq_vnum[_{d}]", "vPcld", "iUif", [IsStore], MemEltTyInt32, "aarch64_sve_st1uwq">;
+ def SVST1UWQ : MInst<"svst1wq[_{d}]", "vPcd", "iUif", [IsStore], MemEltTyInt32, "aarch64_sve_st1wq">;
+ def SVST1UWQ_VNUM : MInst<"svst1wq_vnum[_{d}]", "vPcld", "iUif", [IsStore], MemEltTyInt32, "aarch64_sve_st1wq">;
- def SVST1UDQ : MInst<"svst1udq[_{d}]", "vPcd", "lUld", [IsStore], MemEltTyInt64, "aarch64_sve_st1udq">;
- def SVST1UDQ_VNUM : MInst<"svst1udq_vnum[_{d}]", "vPcld", "lUld", [IsStore], MemEltTyInt64, "aarch64_sve_st1udq">;
+ def SVST1UDQ : MInst<"svst1dq[_{d}]", "vPcd", "lUld", [IsStore], MemEltTyInt64, "aarch64_sve_st1dq">;
+ def SVST1UDQ_VNUM : MInst<"svst1dq_vnum[_{d}]", "vPcld", "lUld", [IsStore], MemEltTyInt64, "aarch64_sve_st1dq">;
// Store one vector (vector base + scalar offset)
def SVST1Q_SCATTER_U64BASE_OFFSET : MInst<"svst1q_scatter[_{2}base]_offset[_{d}]", "vPgld", "cUcsUsiUilUlfhdb", [IsScatterStore, IsByteIndexed], MemEltTyDefault, "aarch64_sve_st1q_scatter_scalar_offset">;
@@ -2061,12 +2061,12 @@ def SVSTNT1H_VNUM_X4 : MInst<"svstnt1_vnum[_{2}_x4]", "v}pl4", "sUshb", [IsStruc
def SVSTNT1W_VNUM_X4 : MInst<"svstnt1_vnum[_{2}_x4]", "v}pl4", "iUif", [IsStructStore], MemEltTyDefault, "aarch64_sve_stnt1_pn_x4">;
def SVSTNT1D_VNUM_X4 : MInst<"svstnt1_vnum[_{2}_x4]", "v}pl4", "lUld", [IsStructStore], MemEltTyDefault, "aarch64_sve_stnt1_pn_x4">;
-def SVDOT_X2_S : SInst<"svdot[_{d}_{2}_{3}]", "ddhh", "i", MergeNone, "aarch64_sve_sdot_x2", [], []>;
-def SVDOT_X2_U : SInst<"svdot[_{d}_{2}_{3}]", "ddhh", "Ui", MergeNone, "aarch64_sve_udot_x2", [], []>;
-def SVDOT_X2_F : SInst<"svdot[_{d}_{2}_{3}]", "ddhh", "f", MergeNone, "aarch64_sve_fdot_x2", [], []>;
-def SVDOT_LANE_X2_S : SInst<"svdot_lane[_{d}_{2}_{3}]", "ddhhi", "i", MergeNone, "aarch64_sve_sdot_lane_x2", [], [ImmCheck<3, ImmCheck0_3>]>;
-def SVDOT_LANE_X2_U : SInst<"svdot_lane[_{d}_{2}_{3}]", "ddhhi", "Ui", MergeNone, "aarch64_sve_udot_lane_x2", [], [ImmCheck<3, ImmCheck0_3>]>;
-def SVDOT_LANE_X2_F : SInst<"svdot_lane[_{d}_{2}_{3}]", "ddhhi", "f", MergeNone, "aarch64_sve_fdot_lane_x2", [], [ImmCheck<3, ImmCheck0_3>]>;
+def SVDOT_X2_S : SInst<"svdot[_{d}_{2}]", "ddhh", "i", MergeNone, "aarch64_sve_sdot_x2", [], []>;
+def SVDOT_X2_U : SInst<"svdot[_{d}_{2}]", "ddhh", "Ui", MergeNone, "aarch64_sve_udot_x2", [], []>;
+def SVDOT_X2_F : SInst<"svdot[_{d}_{2}]", "ddhh", "f", MergeNone, "aarch64_sve_fdot_x2", [], []>;
+def SVDOT_LANE_X2_S : SInst<"svdot_lane[_{d}_{2}]", "ddhhi", "i", MergeNone, "aarch64_sve_sdot_lane_x2", [], [ImmCheck<3, ImmCheck0_3>]>;
+def SVDOT_LANE_X2_U : SInst<"svdot_lane[_{d}_{2}]", "ddhhi", "Ui", MergeNone, "aarch64_sve_udot_lane_x2", [], [ImmCheck<3, ImmCheck0_3>]>;
+def SVDOT_LANE_X2_F : SInst<"svdot_lane[_{d}_{2}]", "ddhhi", "f", MergeNone, "aarch64_sve_fdot_lane_x2", [], [ImmCheck<3, ImmCheck0_3>]>;
}
let TargetGuard = "sve2p1|sme" in {
@@ -2215,7 +2215,7 @@ let TargetGuard = "sve2p1" in {
def SVTBLQ : SInst<"svtblq[_{d}]", "ddu", "cUcsUsiUilUlbhfd", MergeNone, "aarch64_sve_tblq">;
def SVTBXQ : SInst<"svtbxq[_{d}]", "dddu", "cUcsUsiUilUlbhfd", MergeNone, "aarch64_sve_tbxq">;
// EXTQ
- def EXTQ : SInst<"svextq_lane[_{d}]", "dddk", "cUcsUsiUilUlbhfd", MergeNone, "aarch64_sve_extq_lane", [], [ImmCheck<2, ImmCheck0_15>]>;
+ def EXTQ : SInst<"svextq[_{d}]", "dddk", "cUcsUsiUilUlbhfd", MergeNone, "aarch64_sve_extq", [], [ImmCheck<2, ImmCheck0_15>]>;
// PMOV
// Move to Pred
multiclass PMOV_TO_PRED<string name, string types, string intrinsic, list<FlagType> flags=[], ImmCheckType immCh > {
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index a29304c81928cc..1bc4e2b4afd143 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -9681,8 +9681,8 @@ Value *CodeGenFunction::EmitSVEMaskedStore(const CallExpr *E,
bool IsQuadStore = false;
switch (IntrinsicID) {
- case Intrinsic::aarch64_sve_st1uwq:
- case Intrinsic::aarch64_sve_st1udq:
+ case Intrinsic::aarch64_sve_st1wq:
+ case Intrinsic::aarch64_sve_st1dq:
AddrMemoryTy = llvm::ScalableVectorType::get(MemEltTy, 1);
PredTy =
llvm::ScalableVectorType::get(IntegerType::get(getLLVMContext(), 1), 1);
diff --git a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_dot.c b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_dot.c
index d01b59114d5429..035ba244f9441e 100644
--- a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_dot.c
+++ b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_dot.c
@@ -26,7 +26,7 @@
//
svint32_t test_svdot_s32_x2(svint32_t op1, svint16_t op2, svint16_t op3)
{
- return SVE_ACLE_FUNC(svdot,_s32_s16_s16,)(op1, op2, op3);
+ return SVE_ACLE_FUNC(svdot,_s32_s16,)(op1, op2, op3);
}
// CHECK-LABEL: @test_svdot_u32_x2(
@@ -41,7 +41,7 @@ svint32_t test_svdot_s32_x2(svint32_t op1, svint16_t op2, svint16_t op3)
//
svuint32_t test_svdot_u32_x2(svuint32_t op1, svuint16_t op2, svuint16_t op3)
{
- return SVE_ACLE_FUNC(svdot,_u32_u16_u16,)(op1, op2, op3);
+ return SVE_ACLE_FUNC(svdot,_u32_u16,)(op1, op2, op3);
}
// CHECK-LABEL: @test_svdot_f32_x2(
@@ -56,7 +56,7 @@ svuint32_t test_svdot_u32_x2(svuint32_t op1, svuint16_t op2, svuint16_t op3)
//
svfloat32_t test_svdot_f32_x2(svfloat32_t op1, svfloat16_t op2, svfloat16_t op3)
{
- return SVE_ACLE_FUNC(svdot,_f32_f16_f16,)(op1, op2, op3);
+ return SVE_ACLE_FUNC(svdot,_f32_f16,)(op1, op2, op3);
}
@@ -73,7 +73,7 @@ svfloat32_t test_svdot_f32_x2(svfloat32_t op1, svfloat16_t op2, svfloat16_t op3)
//
svint32_t test_svdot_lane_s32_x2(svint32_t op1, svint16_t op2, svint16_t op3)
{
- return SVE_ACLE_FUNC(svdot_lane,_s32_s16_s16,)(op1, op2, op3, 3);
+ return SVE_ACLE_FUNC(svdot_lane,_s32_s16,)(op1, op2, op3, 3);
}
// CHECK-LABEL: @test_svdot_lane_u32_x2(
@@ -88,7 +88,7 @@ svint32_t test_svdot_lane_s32_x2(svint32_t op1, svint16_t op2, svint16_t op3)
//
svuint32_t test_svdot_lane_u32_x2(svuint32_t op1, svuint16_t op2, svuint16_t op3)
{
- return SVE_ACLE_FUNC(svdot_lane,_u32_u16_u16,)(op1, op2, op3, 3);
+ return SVE_ACLE_FUNC(svdot_lane,_u32_u16,)(op1, op2, op3, 3);
}
// CHECK-LABEL: @test_svdot_lane_f32_x2(
@@ -103,5 +103,5 @@ svuint32_t test_svdot_lane_u32_x2(svuint32_t op1, svuint16_t op2, svuint16_t op3
//
svfloat32_t test_svdot_lane_f32_x2(svfloat32_t op1, svfloat16_t op2, svfloat16_t op3)
{
- return SVE_ACLE_FUNC(svdot_lane,_f32_f16_f16,)(op1, op2, op3, 3);
+ return SVE_ACLE_FUNC(svdot_lane,_f32_f16,)(op1, op2, op3, 3);
}
diff --git a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_extq.c b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_extq.c
index 7704db5667a2a7..738b290b76cf59 100644
--- a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_extq.c
+++ b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_extq.c
@@ -20,194 +20,194 @@
#define SVE_ACLE_FUNC(A1, A2, A3, A4) A1##A2##A3##A4
#endif
-// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svextq_lane_u8
+// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svextq_u8
// CHECK-SAME: (<vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.extq.lane.nxv16i8(<vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 0)
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.extq.nxv16i8(<vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 0)
// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
-// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z19test_svextq_lane_u8u11__SVUint8_tS_
+// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z14test_svextq_u8u11__SVUint8_tS_
// CPP-CHECK-SAME: (<vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) #[[ATTR0:[0-9]+]] {
// CPP-CHECK-NEXT: entry:
-// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.extq.lane.nxv16i8(<vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 0)
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.extq.nxv16i8(<vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 0)
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
-svuint8_t test_svextq_lane_u8(svuint8_t zn, svuint8_t zm) {
- return SVE_ACLE_FUNC(svextq_lane, _u8,,)(zn, zm, 0);
+svuint8_t test_svextq_u8(svuint8_t zn, svuint8_t zm) {
+ return SVE_ACLE_FUNC(svextq, _u8,,)(zn, zm, 0);
}
-// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svextq_lane_s8
+// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svextq_s8
// CHECK-SAME: (<vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.extq.lane.nxv16i8(<vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 4)
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.extq.nxv16i8(<vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 4)
// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
-// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z19test_svextq_lane_s8u10__SVInt8_tS_
+// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z14test_svextq_s8u10__SVInt8_tS_
// CPP-CHECK-SAME: (<vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT: entry:
-// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.extq.lane.nxv16i8(<vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 4)
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.extq.nxv16i8(<vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 4)
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
-svint8_t test_svextq_lane_s8(svint8_t zn, svint8_t zm) {
- return SVE_ACLE_FUNC(svextq_lane, _s8,,)(zn, zm, 4);
+svint8_t test_svextq_s8(svint8_t zn, svint8_t zm) {
+ return SVE_ACLE_FUNC(svextq, _s8,,)(zn, zm, 4);
}
-// CHECK-LABEL: define dso_local <vscale x 8 x i16> @test_svextq_lane_u16
+// CHECK-LABEL: define dso_local <vscale x 8 x i16> @test_svextq_u16
// CHECK-SAME: (<vscale x 8 x i16> [[ZN:%.*]], <vscale x 8 x i16> [[ZM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.extq.lane.nxv8i16(<vscale x 8 x i16> [[ZN]], <vscale x 8 x i16> [[ZM]], i32 1)
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.extq.nxv8i16(<vscale x 8 x i16> [[ZN]], <vscale x 8 x i16> [[ZM]], i32 1)
// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
-// CPP-CHECK-LABEL: define dso_local <vscale x 8 x i16> @_Z20test_svextq_lane_u16u12__SVUint16_tS_
+// CPP-CHECK-LABEL: define dso_local <vscale x 8 x i16> @_Z15test_svextq_u16u12__SVUint16_tS_
// CPP-CHECK-SAME: (<vscale x 8 x i16> [[ZN:%.*]], <vscale x 8 x i16> [[ZM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT: entry:
-// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.extq.lane.nxv8i16(<vscale x 8 x i16> [[ZN]], <vscale x 8 x i16> [[ZM]], i32 1)
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.extq.nxv8i16(<vscale x 8 x i16> [[ZN]], <vscale x 8 x i16> [[ZM]], i32 1)
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
-svuint16_t test_svextq_lane_u16(svuint16_t zn, svuint16_t zm) {
- return SVE_ACLE_FUNC(svextq_lane, _u16,,)(zn, zm, 1);
+svuint16_t test_svextq_u16(svuint16_t zn, svuint16_t zm) {
+ return SVE_ACLE_FUNC(svextq, _u16,,)(zn, zm, 1);
}
-// CHECK-LABEL: define dso_local <vscale x 8 x i16> @test_svextq_lane_s16
+// CHECK-LABEL: define dso_local <vscale x 8 x i16> @test_svextq_s16
// CHECK-SAME: (<vscale x 8 x i16> [[ZN:%.*]], <vscale x 8 x i16> [[ZM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.extq.lane.nxv8i16(<vscale x 8 x i16> [[ZN]], <vscale x 8 x i16> [[ZM]], i32 5)
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.extq.nxv8i16(<vscale x 8 x i16> [[ZN]], <vscale x 8 x i16> [[ZM]], i32 5)
// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
-// CPP-CHECK-LABEL: define dso_local <vscale x 8 x i16> @_Z20test_svextq_lane_s16u11__SVInt16_tS_
+// CPP-CHECK-LABEL: define dso_local <vscale x 8 x i16> @_Z15test_svextq_s16u11__SVInt16_tS_
// CPP-CHECK-SAME: (<vscale x 8 x i16> [[ZN:%.*]], <vscale x 8 x i16> [[ZM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT: entry:
-// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.extq.lane.nxv8i16(<vscale x 8 x i16> [[ZN]], <vscale x 8 x i16> [[ZM]], i32 5)
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.extq.nxv8i16(<vscale x 8 x i16> [[ZN]], <vscale x 8 x i16> [[ZM]], i32 5)
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
-svint16_t test_svextq_lane_s16(svint16_t zn, svint16_t zm) {
- return SVE_ACLE_FUNC(svextq_lane, _s16,,)(zn, zm, 5);
+svint16_t test_svextq_s16(svint16_t zn, svint16_t zm) {
+ return SVE_ACLE_FUNC(svextq, _s16,,)(zn, zm, 5);
}
-// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svextq_lane_u32
+// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svextq_u32
// CHECK-SAME: (<vscale x 4 x i32> [[ZN:%.*]], <vscale x 4 x i32> [[ZM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.extq.lane.nxv4i32(<vscale x 4 x i32> [[ZN]], <vscale x 4 x i32> [[ZM]], i32 2)
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.extq.nxv4i32(<vscale x 4 x i32> [[ZN]], <vscale x 4 x i32> [[ZM]], i32 2)
// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
-// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z20test_svextq_lane_u32u12__SVUint32_tS_
+// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z15test_svextq_u32u12__SVUint32_tS_
// CPP-CHECK-SAME: (<vscale x 4 x i32> [[ZN:%.*]], <vscale x 4 x i32> [[ZM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT: entry:
-// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.extq.lane.nxv4i32(<vscale x 4 x i32> [[ZN]], <vscale x 4 x i32> [[ZM]], i32 2)
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.extq.nxv4i32(<vscale x 4 x i32> [[ZN]], <vscale x 4 x i32> [[ZM]], i32 2)
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
-svuint32_t test_svextq_lane_u32(svuint32_t zn, svuint32_t zm) {
- return SVE_ACLE_FUNC(svextq_lane, _u32,,)(zn, zm, 2);
+svuint32_t test_svextq_u32(svuint32_t zn, svuint32_t zm) {
+ return SVE_ACLE_FUNC(svextq, _u32,,)(zn, zm, 2);
}
-// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svextq_lane_s32
+// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svextq_s32
// CHECK-SAME: (<vscale x 4 x i32> [[ZN:%.*]], <vscale x 4 x i32> [[ZM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.extq.lane.nxv4i32(<vscale x 4 x i32> [[ZN]], <vscale x 4 x i32> [[ZM]], i32 6)
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.extq.nxv4i32(<vscale x 4 x i32> [[ZN]], <vscale x 4 x i32> [[ZM]], i32 6)
// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
-// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z20test_svextq_lane_s32u11__SVInt32_tS_
+// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z15test_svextq_s32u11__SVInt32_tS_
// CPP-CHECK-SAME: (<vscale x 4 x i32> [[ZN:%.*]], <vscale x 4 x i32> [[ZM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT: entry:
-// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.extq.lane.nxv4i32(<vscale x 4 x i32> [[ZN]], <vscale x 4 x i32> [[ZM]], i32 6)
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.extq.nxv4i32(<vscale x 4 x i32> [[ZN]], <vscale x 4 x i32> [[ZM]], i32 6)
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
-svint32_t test_svextq_lane_s32(svint32_t zn, svint32_t zm) {
- return SVE_ACLE_FUNC(svextq_lane, _s32,,)(zn, zm, 6);
+svint32_t test_svextq_s32(svint32_t zn, svint32_t zm) {
+ return SVE_ACLE_FUNC(svextq, _s32,,)(zn, zm, 6);
}
-// CHECK-LABEL: define dso_local <vscale x 2 x i64> @test_svextq_lane_u64
+// CHECK-LABEL: define dso_local <vscale x 2 x i64> @test_svextq_u64
// CHECK-SAME: (<vscale x 2 x i64> [[ZN:%.*]], <vscale x 2 x i64> [[ZM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.extq.lane.nxv2i64(<vscale x 2 x i64> [[ZN]], <vscale x 2 x i64> [[ZM]], i32 3)
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.extq.nxv2i64(<vscale x 2 x i64> [[ZN]], <vscale x 2 x i64> [[ZM]], i32 3)
// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
-// CPP-CHECK-LABEL: define dso_local <vscale x 2 x i64> @_Z20test_svextq_lane_u64u12__SVUint64_tS_
+// CPP-CHECK-LABEL: define dso_local <vscale x 2 x i64> @_Z15test_svextq_u64u12__SVUint64_tS_
// CPP-CHECK-SAME: (<vscale x 2 x i64> [[ZN:%.*]], <vscale x 2 x i64> [[ZM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT: entry:
-// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.extq.lane.nxv2i64(<vscale x 2 x i64> [[ZN]], <vscale x 2 x i64> [[ZM]], i32 3)
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.extq.nxv2i64(<vscale x 2 x i64> [[ZN]], <vscale x 2 x i64> [[ZM]], i32 3)
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
-svuint64_t test_svextq_lane_u64(svuint64_t zn, svuint64_t zm) {
- return SVE_ACLE_FUNC(svextq_lane, _u64,,)(zn, zm, 3);
+svuint64_t test_svextq_u64(svuint64_t zn, svuint64_t zm) {
+ return SVE_ACLE_FUNC(svextq, _u64,,)(zn, zm, 3);
}
-// CHECK-LABEL: define dso_local <vscale x 2 x i64> @test_svextq_lane_s64
+// CHECK-LABEL: define dso_local <vscale x 2 x i64> @test_svextq_s64
// CHECK-SAME: (<vscale x 2 x i64> [[ZN:%.*]], <vscale x 2 x i64> [[ZM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.extq.lane.nxv2i64(<vscale x 2 x i64> [[ZN]], <vscale x 2 x i64> [[ZM]], i32 7)
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.extq.nxv2i64(<vscale x 2 x i64> [[ZN]], <vscale x 2 x i64> [[ZM]], i32 7)
// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
-// CPP-CHECK-LABEL: define dso_local <vscale x 2 x i64> @_Z20test_svextq_lane_s64u11__SVInt64_tS_
+// CPP-CHECK-LABEL: define dso_local <vscale x 2 x i64> @_Z15test_svextq_s64u11__SVInt64_tS_
// CPP-CHECK-SAME: (<vscale x 2 x i64> [[ZN:%.*]], <vscale x 2 x i64> [[ZM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT: entry:
-// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.extq.lane.nxv2i64(<vscale x 2 x i64> [[ZN]], <vscale x 2 x i64> [[ZM]], i32 7)
+// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.extq.nxv2i64(<vscale x 2 x i64> [[ZN]], <vscale x 2 x i64> [[ZM]], i32 7)
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
-svint64_t test_svextq_lane_s64(svint64_t zn, svint64_t zm) {
- return SVE_ACLE_FUNC(svextq_lane, _s64,,)(zn, zm, 7);
+svint64_t test_svextq_s64(svint64_t zn, svint64_t zm) {
+ return SVE_ACLE_FUNC(svextq, _s64,,)(zn, zm, 7);
}
-// CHECK-LABEL: define dso_local <vscale x 8 x half> @test_svextq_lane_f16
+// CHECK-LABEL: define dso_local <vscale x 8 x half> @test_svextq_f16
// CHECK-SAME: (<vscale x 8 x half> [[ZN:%.*]], <vscale x 8 x half> [[ZM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.extq.lane.nxv8f16(<vscale x 8 x half> [[ZN]], <vscale x 8 x half> [[ZM]], i32 8)
+// CHECK-NEXT: [[TMP0:%.*]] = tail call...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/76842
More information about the cfe-commits
mailing list