[AArch64][SVE] Add SVE2 mla indexed intrinsics.

Summary:
Add SVE2 mla indexed intrinsics:
- smlalb, smalalt, umlalb, umlalt, smlslb, smlslt, umlslb, umlslt.

Reviewers: efriedma, sdesmalen, dancgr, cameron.mcinally, c-rhodes, rengolin

Subscribers: tschuett, kristof.beyls, hiraditya, rkruppe, arphaman, psnobl, llvm-commits, amehsan

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D73576

4 files changed, 492 insertions, 13 deletions

diff --git a/llvm/include/llvm/IR/IntrinsicsAArch64.td b/llvm/include/llvm/IR/IntrinsicsAArch64.td
index a2aa8a6..222a177 100644
--- a/llvm/include/llvm/IR/IntrinsicsAArch64.td
+++ b/llvm/include/llvm/IR/IntrinsicsAArch64.td
@@ -1080,6 +1080,14 @@ let TargetPrefix = "aarch64" in {  // All intrinsics start with "llvm.aarch64.".
                    llvm_i32_ty],
                   [IntrNoMem, ImmArg<2>]>;
 
+  class SVE2_3VectorArg_Indexed_Intrinsic
+    : Intrinsic<[llvm_anyvector_ty],
+                [LLVMMatchType<0>,
+                 LLVMSubdivide2VectorType<0>,
+                 LLVMSubdivide2VectorType<0>,
+                 llvm_i64_ty],
+                [IntrNoMem, ImmArg<3>]>;
+
   // NOTE: There is no relationship between these intrinsics beyond an attempt
   // to reuse currently identical class definitions.
   class AdvSIMD_SVE_LOGB_Intrinsic  : AdvSIMD_SVE_CNT_Intrinsic;
@@ -1732,4 +1740,14 @@ def int_aarch64_sve_sqshrunt  : SVE2_2VectorArg_Imm_Narrowing_Intrinsic;
 
 def int_aarch64_sve_sqrshrunb : SVE2_1VectorArg_Imm_Narrowing_Intrinsic;
 def int_aarch64_sve_sqrshrunt : SVE2_2VectorArg_Imm_Narrowing_Intrinsic;
+
+def int_aarch64_sve_smlalb    : SVE2_3VectorArg_Indexed_Intrinsic;
+def int_aarch64_sve_smlalt    : SVE2_3VectorArg_Indexed_Intrinsic;
+def int_aarch64_sve_umlalb    : SVE2_3VectorArg_Indexed_Intrinsic;
+def int_aarch64_sve_umlalt    : SVE2_3VectorArg_Indexed_Intrinsic;
+def int_aarch64_sve_smlslb    : SVE2_3VectorArg_Indexed_Intrinsic;
+def int_aarch64_sve_smlslt    : SVE2_3VectorArg_Indexed_Intrinsic;
+def int_aarch64_sve_umlslb    : SVE2_3VectorArg_Indexed_Intrinsic;
+def int_aarch64_sve_umlslt    : SVE2_3VectorArg_Indexed_Intrinsic;
+
 }
diff --git a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
index 7fdbee3..7a2000e 100644
--- a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
@@ -1467,14 +1467,14 @@ let Predicates = [HasSVE2] in {
   defm SQDMULLT_ZZZI : sve2_int_mul_long_by_indexed_elem<0b101, "sqdmullt">;
 
   // SVE2 integer multiply-add long (indexed)
-  defm SMLALB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1000, "smlalb">;
-  defm SMLALT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1001, "smlalt">;
-  defm UMLALB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1010, "umlalb">;
-  defm UMLALT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1011, "umlalt">;
-  defm SMLSLB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1100, "smlslb">;
-  defm SMLSLT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1101, "smlslt">;
-  defm UMLSLB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1110, "umlslb">;
-  defm UMLSLT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1111, "umlslt">;
+  defm SMLALB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1000, "smlalb", int_aarch64_sve_smlalb>;
+  defm SMLALT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1001, "smlalt", int_aarch64_sve_smlalt>;
+  defm UMLALB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1010, "umlalb", int_aarch64_sve_umlalb>;
+  defm UMLALT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1011, "umlalt", int_aarch64_sve_umlalt>;
+  defm SMLSLB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1100, "smlslb", int_aarch64_sve_smlslb>;
+  defm SMLSLT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1101, "smlslt", int_aarch64_sve_smlslt>;
+  defm UMLSLB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1110, "umlslb", int_aarch64_sve_umlslb>;
+  defm UMLSLT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b1111, "umlslt", int_aarch64_sve_umlslt>;
 
   // SVE2 integer multiply-add long (vectors, unpredicated)
   defm SMLALB_ZZZ : sve2_int_mla_long<0b10000, "smlalb">;
@@ -1487,10 +1487,10 @@ let Predicates = [HasSVE2] in {
   defm UMLSLT_ZZZ : sve2_int_mla_long<0b10111, "umlslt">;
 
   // SVE2 saturating multiply-add long (indexed)
-  defm SQDMLALB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b0100, "sqdmlalb">;
-  defm SQDMLALT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b0101, "sqdmlalt">;
-  defm SQDMLSLB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b0110, "sqdmlslb">;
-  defm SQDMLSLT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b0111, "sqdmlslt">;
+  defm SQDMLALB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b0100, "sqdmlalb", null_frag>;
+  defm SQDMLALT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b0101, "sqdmlalt", null_frag>;
+  defm SQDMLSLB_ZZZI : sve2_int_mla_long_by_indexed_elem<0b0110, "sqdmlslb", null_frag>;
+  defm SQDMLSLT_ZZZI : sve2_int_mla_long_by_indexed_elem<0b0111, "sqdmlslt", null_frag>;
 
   // SVE2 saturating multiply-add long (vectors, unpredicated)
   defm SQDMLALB_ZZZ : sve2_int_mla_long<0b11000, "sqdmlalb">;
diff --git a/llvm/lib/Target/AArch64/SVEInstrFormats.td b/llvm/lib/Target/AArch64/SVEInstrFormats.td
index 038657d..e9f9381 100644
--- a/llvm/lib/Target/AArch64/SVEInstrFormats.td
+++ b/llvm/lib/Target/AArch64/SVEInstrFormats.td
@@ -2402,7 +2402,7 @@ multiclass sve2_int_mla_by_indexed_elem<bits<2> opc, bit S, string asm> {
 // SVE2 Integer Multiply-Add Long - Indexed Group
 //===----------------------------------------------------------------------===//
 
-multiclass sve2_int_mla_long_by_indexed_elem<bits<4> opc, string asm> {
+multiclass sve2_int_mla_long_by_indexed_elem<bits<4> opc, string asm, SDPatternOperator op> {
   def _S : sve2_int_mla_by_indexed_elem<0b10, { opc{3}, 0b0, opc{2-1}, ?, opc{0} },
                                         asm, ZPR32, ZPR16, ZPR3b16, VectorIndexH> {
     bits<3> Zm;
@@ -2419,6 +2419,9 @@ multiclass sve2_int_mla_long_by_indexed_elem<bits<4> opc, string asm> {
     let Inst{19-16} = Zm;
     let Inst{11} = iop{0};
   }
+
+  def : SVE_4_Op_Imm_Pat<nxv4i32, op, nxv4i32, nxv8i16, nxv8i16, i64, VectorIndexH_timm, !cast<Instruction>(NAME # _S)>;
+  def : SVE_4_Op_Imm_Pat<nxv2i64, op, nxv2i64, nxv4i32, nxv4i32, i64, VectorIndexS_timm, !cast<Instruction>(NAME # _D)>;
 }
 
 //===----------------------------------------------------------------------===//
diff --git a/llvm/test/CodeGen/AArch64/sve2-mla-indexed.ll b/llvm/test/CodeGen/AArch64/sve2-mla-indexed.ll
new file mode 100644
index 0000000..ded4155
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve2-mla-indexed.ll
@@ -0,0 +1,458 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s
+
+;
+; SMLALB
+;
+define <vscale x 4 x i32> @smlalb_i32(<vscale x 4 x i32> %a,
+                                      <vscale x 8 x i16> %b,
+                                      <vscale x 8 x i16> %c) {
+; CHECK-LABEL: smlalb_i32
+; CHECK: smlalb z0.s, z1.h, z2.h[1]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.smlalb.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 1)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 4 x i32> @smlalb_i32_2(<vscale x 4 x i32> %a,
+                                        <vscale x 8 x i16> %b,
+                                        <vscale x 8 x i16> %c) {
+; CHECK-LABEL: smlalb_i32_2
+; CHECK: smlalb z0.s, z1.h, z2.h[7]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.smlalb.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 7)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @smlalb_i64(<vscale x 2 x i64> %a,
+                                      <vscale x 4 x i32> %b,
+                                      <vscale x 4 x i32> %c) {
+; CHECK-LABEL: smlalb_i64
+; CHECK: smlalb z0.d, z1.s, z2.s[0]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.smlalb.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 0)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 2 x i64> @smlalb_i64_2(<vscale x 2 x i64> %a,
+                                        <vscale x 4 x i32> %b,
+                                        <vscale x 4 x i32> %c) {
+; CHECK-LABEL: smlalb_i64_2
+; CHECK: smlalb z0.d, z1.s, z2.s[3]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.smlalb.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 3)
+  ret <vscale x 2 x i64> %res
+}
+
+;
+; SMLALT
+;
+define <vscale x 4 x i32> @smlalt_i32(<vscale x 4 x i32> %a,
+                                      <vscale x 8 x i16> %b,
+                                      <vscale x 8 x i16> %c) {
+; CHECK-LABEL: smlalt_i32
+; CHECK: smlalt z0.s, z1.h, z2.h[1]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.smlalt.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 1)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 4 x i32> @smlalt_i32_2(<vscale x 4 x i32> %a,
+                                        <vscale x 8 x i16> %b,
+                                        <vscale x 8 x i16> %c) {
+; CHECK-LABEL: smlalt_i32_2
+; CHECK: smlalt z0.s, z1.h, z2.h[7]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.smlalt.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 7)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @smlalt_i64(<vscale x 2 x i64> %a,
+                                      <vscale x 4 x i32> %b,
+                                      <vscale x 4 x i32> %c) {
+; CHECK-LABEL: smlalt_i64
+; CHECK: smlalt z0.d, z1.s, z2.s[0]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.smlalt.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 0)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 2 x i64> @smlalt_i64_2(<vscale x 2 x i64> %a,
+                                        <vscale x 4 x i32> %b,
+                                        <vscale x 4 x i32> %c) {
+; CHECK-LABEL: smlalt_i64_2
+; CHECK: smlalt z0.d, z1.s, z2.s[3]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.smlalt.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 3)
+  ret <vscale x 2 x i64> %res
+}
+
+;
+; UMLALB
+;
+define <vscale x 4 x i32> @umlalb_i32(<vscale x 4 x i32> %a,
+                                      <vscale x 8 x i16> %b,
+                                      <vscale x 8 x i16> %c) {
+; CHECK-LABEL: umlalb_i32
+; CHECK: umlalb z0.s, z1.h, z2.h[1]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.umlalb.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 1)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 4 x i32> @umlalb_i32_2(<vscale x 4 x i32> %a,
+                                        <vscale x 8 x i16> %b,
+                                        <vscale x 8 x i16> %c) {
+; CHECK-LABEL: umlalb_i32_2
+; CHECK: umlalb z0.s, z1.h, z2.h[7]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.umlalb.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 7)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @umlalb_i64(<vscale x 2 x i64> %a,
+                                      <vscale x 4 x i32> %b,
+                                      <vscale x 4 x i32> %c) {
+; CHECK-LABEL: umlalb_i64
+; CHECK: umlalb z0.d, z1.s, z2.s[0]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.umlalb.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 0)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 2 x i64> @umlalb_i64_2(<vscale x 2 x i64> %a,
+                                        <vscale x 4 x i32> %b,
+                                        <vscale x 4 x i32> %c) {
+; CHECK-LABEL: umlalb_i64_2
+; CHECK: umlalb z0.d, z1.s, z2.s[3]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.umlalb.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 3)
+  ret <vscale x 2 x i64> %res
+}
+
+;
+; UMLALT
+;
+define <vscale x 4 x i32> @umlalt_i32(<vscale x 4 x i32> %a,
+                                      <vscale x 8 x i16> %b,
+                                      <vscale x 8 x i16> %c) {
+; CHECK-LABEL: umlalt_i32
+; CHECK: umlalt z0.s, z1.h, z2.h[1]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.umlalt.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 1)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 4 x i32> @umlalt_i32_2(<vscale x 4 x i32> %a,
+                                        <vscale x 8 x i16> %b,
+                                        <vscale x 8 x i16> %c) {
+; CHECK-LABEL: umlalt_i32_2
+; CHECK: umlalt z0.s, z1.h, z2.h[7]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.umlalt.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 7)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @umlalt_i64(<vscale x 2 x i64> %a,
+                                      <vscale x 4 x i32> %b,
+                                      <vscale x 4 x i32> %c) {
+; CHECK-LABEL: umlalt_i64
+; CHECK: umlalt z0.d, z1.s, z2.s[0]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.umlalt.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 0)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 2 x i64> @umlalt_i64_2(<vscale x 2 x i64> %a,
+                                        <vscale x 4 x i32> %b,
+                                        <vscale x 4 x i32> %c) {
+; CHECK-LABEL: umlalt_i64_2
+; CHECK: umlalt z0.d, z1.s, z2.s[3]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.umlalt.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 3)
+  ret <vscale x 2 x i64> %res
+}
+
+;
+; SMLSLB
+;
+define <vscale x 4 x i32> @smlslb_i32(<vscale x 4 x i32> %a,
+                                      <vscale x 8 x i16> %b,
+                                      <vscale x 8 x i16> %c) {
+; CHECK-LABEL: smlslb_i32
+; CHECK: smlslb z0.s, z1.h, z2.h[1]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.smlslb.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 1)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 4 x i32> @smlslb_i32_2(<vscale x 4 x i32> %a,
+                                        <vscale x 8 x i16> %b,
+                                        <vscale x 8 x i16> %c) {
+; CHECK-LABEL: smlslb_i32_2
+; CHECK: smlslb z0.s, z1.h, z2.h[7]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.smlslb.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 7)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @smlslb_i64(<vscale x 2 x i64> %a,
+                                      <vscale x 4 x i32> %b,
+                                      <vscale x 4 x i32> %c) {
+; CHECK-LABEL: smlslb_i64
+; CHECK: smlslb z0.d, z1.s, z2.s[0]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.smlslb.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 0)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 2 x i64> @smlslb_i64_2(<vscale x 2 x i64> %a,
+                                        <vscale x 4 x i32> %b,
+                                        <vscale x 4 x i32> %c) {
+; CHECK-LABEL: smlslb_i64_2
+; CHECK: smlslb z0.d, z1.s, z2.s[3]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.smlslb.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 3)
+  ret <vscale x 2 x i64> %res
+}
+
+;
+; SMLSLT
+;
+define <vscale x 4 x i32> @smlslt_i32(<vscale x 4 x i32> %a,
+                                      <vscale x 8 x i16> %b,
+                                      <vscale x 8 x i16> %c) {
+; CHECK-LABEL: smlslt_i32
+; CHECK: smlslt z0.s, z1.h, z2.h[1]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.smlslt.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 1)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 4 x i32> @smlslt_i32_2(<vscale x 4 x i32> %a,
+                                        <vscale x 8 x i16> %b,
+                                        <vscale x 8 x i16> %c) {
+; CHECK-LABEL: smlslt_i32_2
+; CHECK: smlslt z0.s, z1.h, z2.h[7]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.smlslt.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 7)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @smlslt_i64(<vscale x 2 x i64> %a,
+                                      <vscale x 4 x i32> %b,
+                                      <vscale x 4 x i32> %c) {
+; CHECK-LABEL: smlslt_i64
+; CHECK: smlslt z0.d, z1.s, z2.s[0]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.smlslt.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 0)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 2 x i64> @smlslt_i64_2(<vscale x 2 x i64> %a,
+                                        <vscale x 4 x i32> %b,
+                                        <vscale x 4 x i32> %c) {
+; CHECK-LABEL: smlslt_i64_2
+; CHECK: smlslt z0.d, z1.s, z2.s[3]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.smlslt.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 3)
+  ret <vscale x 2 x i64> %res
+}
+
+;
+; UMLSLB
+;
+define <vscale x 4 x i32> @umlslb_i32(<vscale x 4 x i32> %a,
+                                      <vscale x 8 x i16> %b,
+                                      <vscale x 8 x i16> %c) {
+; CHECK-LABEL: umlslb_i32
+; CHECK: umlslb z0.s, z1.h, z2.h[1]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.umlslb.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 1)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 4 x i32> @umlslb_i32_2(<vscale x 4 x i32> %a,
+                                        <vscale x 8 x i16> %b,
+                                        <vscale x 8 x i16> %c) {
+; CHECK-LABEL: umlslb_i32_2
+; CHECK: umlslb z0.s, z1.h, z2.h[7]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.umlslb.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 7)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @umlslb_i64(<vscale x 2 x i64> %a,
+                                      <vscale x 4 x i32> %b,
+                                      <vscale x 4 x i32> %c) {
+; CHECK-LABEL: umlslb_i64
+; CHECK: umlslb z0.d, z1.s, z2.s[0]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.umlslb.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 0)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 2 x i64> @umlslb_i64_2(<vscale x 2 x i64> %a,
+                                        <vscale x 4 x i32> %b,
+                                        <vscale x 4 x i32> %c) {
+; CHECK-LABEL: umlslb_i64_2
+; CHECK: umlslb z0.d, z1.s, z2.s[3]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.umlslb.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 3)
+  ret <vscale x 2 x i64> %res
+}
+
+;
+; UMLSLT
+;
+define <vscale x 4 x i32> @umlslt_i32(<vscale x 4 x i32> %a,
+                                      <vscale x 8 x i16> %b,
+                                      <vscale x 8 x i16> %c) {
+; CHECK-LABEL: umlslt_i32
+; CHECK: umlslt z0.s, z1.h, z2.h[1]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.umlslt.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 1)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 4 x i32> @umlslt_i32_2(<vscale x 4 x i32> %a,
+                                        <vscale x 8 x i16> %b,
+                                        <vscale x 8 x i16> %c) {
+; CHECK-LABEL: umlslt_i32_2
+; CHECK: umlslt z0.s, z1.h, z2.h[7]
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.umlslt.nxv4i32(<vscale x 4 x i32> %a,
+                                                                  <vscale x 8 x i16> %b,
+                                                                  <vscale x 8 x i16> %c,
+                                                                  i64 7)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @umlslt_i64(<vscale x 2 x i64> %a,
+                                      <vscale x 4 x i32> %b,
+                                      <vscale x 4 x i32> %c) {
+; CHECK-LABEL: umlslt_i64
+; CHECK: umlslt z0.d, z1.s, z2.s[0]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.umlslt.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 0)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 2 x i64> @umlslt_i64_2(<vscale x 2 x i64> %a,
+                                        <vscale x 4 x i32> %b,
+                                        <vscale x 4 x i32> %c) {
+; CHECK-LABEL: umlslt_i64_2
+; CHECK: umlslt z0.d, z1.s, z2.s[3]
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.umlslt.nxv2i64(<vscale x 2 x i64> %a,
+                                                                  <vscale x 4 x i32> %b,
+                                                                  <vscale x 4 x i32> %c,
+                                                                  i64 3)
+  ret <vscale x 2 x i64> %res
+}
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.smlalb.nxv4i32(<vscale x 4 x i32>, <vscale x 8 x i16>, <vscale x 8 x i16>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.smlalb.nxv2i64(<vscale x 2 x i64>, <vscale x 4 x i32>, <vscale x 4 x i32>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.smlalt.nxv4i32(<vscale x 4 x i32>, <vscale x 8 x i16>, <vscale x 8 x i16>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.smlalt.nxv2i64(<vscale x 2 x i64>, <vscale x 4 x i32>, <vscale x 4 x i32>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.umlalb.nxv4i32(<vscale x 4 x i32>, <vscale x 8 x i16>, <vscale x 8 x i16>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.umlalb.nxv2i64(<vscale x 2 x i64>, <vscale x 4 x i32>, <vscale x 4 x i32>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.umlalt.nxv4i32(<vscale x 4 x i32>, <vscale x 8 x i16>, <vscale x 8 x i16>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.umlalt.nxv2i64(<vscale x 2 x i64>, <vscale x 4 x i32>, <vscale x 4 x i32>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.smlslb.nxv4i32(<vscale x 4 x i32>, <vscale x 8 x i16>, <vscale x 8 x i16>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.smlslb.nxv2i64(<vscale x 2 x i64>, <vscale x 4 x i32>, <vscale x 4 x i32>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.smlslt.nxv4i32(<vscale x 4 x i32>, <vscale x 8 x i16>, <vscale x 8 x i16>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.smlslt.nxv2i64(<vscale x 2 x i64>, <vscale x 4 x i32>, <vscale x 4 x i32>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.umlslb.nxv4i32(<vscale x 4 x i32>, <vscale x 8 x i16>, <vscale x 8 x i16>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.umlslb.nxv2i64(<vscale x 2 x i64>, <vscale x 4 x i32>, <vscale x 4 x i32>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.umlslt.nxv4i32(<vscale x 4 x i32>, <vscale x 8 x i16>, <vscale x 8 x i16>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.umlslt.nxv2i64(<vscale x 2 x i64>, <vscale x 4 x i32>, <vscale x 4 x i32>, i64)