diff --git a/llvm/docs/RISCVUsage.rst b/llvm/docs/RISCVUsage.rst
--- a/llvm/docs/RISCVUsage.rst
+++ b/llvm/docs/RISCVUsage.rst
@@ -169,6 +169,9 @@
The current vendor extensions supported are:
+``XTHeadBa``
+ LLVM implements `the THeadBa (address-generation) vendor-defined instructions specified in <https://github.com/T-head-Semi/thead-extension-spec/releases/download/2.2.2/xthead-2023-01-30-2.2.2.pdf>`_ by T-HEAD of Alibaba. Instructions are prefixed with `th.` as described in the specification.
+
``XTHeadVdot``
LLVM implements `version 1.0.0 of the THeadV-family custom instructions specification <https://github.com/T-head-Semi/thead-extension-spec/releases/download/2.2.0/xthead-2022-12-04-2.2.0.pdf>`_ by T-HEAD of Alibaba. All instructions are prefixed with `th.` as described in the specification, and the riscv-toolchain-convention document linked above.
diff --git a/llvm/lib/Support/RISCVISAInfo.cpp b/llvm/lib/Support/RISCVISAInfo.cpp
--- a/llvm/lib/Support/RISCVISAInfo.cpp
+++ b/llvm/lib/Support/RISCVISAInfo.cpp
@@ -109,6 +109,7 @@
{"svinval", RISCVExtensionVersion{1, 0}},
// vendor-defined ('X') extensions
+ {"xtheadba", RISCVExtensionVersion{1, 0}},
{"xtheadvdot", RISCVExtensionVersion{1, 0}},
{"xventanacondops", RISCVExtensionVersion{1, 0}},
};
diff --git a/llvm/lib/Target/RISCV/RISCVFeatures.td b/llvm/lib/Target/RISCV/RISCVFeatures.td
--- a/llvm/lib/Target/RISCV/RISCVFeatures.td
+++ b/llvm/lib/Target/RISCV/RISCVFeatures.td
@@ -463,6 +463,13 @@
AssemblerPredicate<(all_of FeatureVendorXVentanaCondOps),
"'XVentanaCondOps' (Ventana Conditional Ops)">;
+def FeatureVendorXTHeadBa
+ : SubtargetFeature<"xtheadba", "HasVendorXTHeadBa", "true",
+ "'xtheadba' (T-Head address calculation instructions)">;
+def HasVendorXTHeadBa : Predicate<"Subtarget->hasVendorXTHeadBa()">,
+ AssemblerPredicate<(all_of FeatureVendorXTHeadBa),
+ "'xtheadba' (T-Head address calculation instructions)">;
+
def FeatureVendorXTHeadVdot
: SubtargetFeature<"xtheadvdot", "HasVendorXTHeadVdot", "true",
"'xtheadvdot' (T-Head Vector Extensions for Dot)",
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoXTHead.td b/llvm/lib/Target/RISCV/RISCVInstrInfoXTHead.td
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoXTHead.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoXTHead.td
@@ -13,6 +13,7 @@
//===----------------------------------------------------------------------===//
// Instruction class templates
//===----------------------------------------------------------------------===//
+
class THInstVdotVV<bits<6> funct6, RISCVVFormat opv, dag outs, dag ins,
string opcodestr, string argstr>
: RVInstVV<funct6, opv, outs, ins, opcodestr, argstr> {
@@ -43,6 +44,16 @@
opcodestr, "$vd, $rs1, $vs2$vm">;
} // hasSideEffects = 0, mayLoad = 0, mayStore = 0
+let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in
+class THShiftALU_rri<bits<3> funct3, string opcodestr>
+ : RVInstR<0, funct3, OPC_CUSTOM_0, (outs GPR:$rd),
+ (ins GPR:$rs1, GPR:$rs2, uimm2:$uimm2),
+ opcodestr, "$rd, $rs1, $rs2, $uimm2"> {
+ bits<2> uimm2;
+ let Inst{31-27} = 0;
+ let Inst{26-25} = uimm2;
+}
+
//===----------------------------------------------------------------------===//
// Combination of instruction classes.
// Use these multiclasses to define instructions more easily.
@@ -59,6 +70,11 @@
//===----------------------------------------------------------------------===//
// Instructions
//===----------------------------------------------------------------------===//
+let Predicates = [HasVendorXTHeadBa] in {
+def TH_ADDSL : THShiftALU_rri<0b001, "th.addsl">,
+ Sched<[WriteSHXADD, ReadSHXADD, ReadSHXADD]>;
+} // Predicates = [HasVendorXTHeadBa]
+
let Predicates = [HasVendorXTHeadVdot],
Constraints = "@earlyclobber $vd",
RVVConstraint = WidenV in {
@@ -134,6 +150,80 @@
//===----------------------------------------------------------------------===//
// Pseudo-instructions and codegen patterns
//===----------------------------------------------------------------------===//
+let Predicates = [HasVendorXTHeadBa] in {
+def : Pat<(add GPR:$rs1, (shl GPR:$rs2, uimm2:$uimm2)),
+ (TH_ADDSL GPR:$rs1, GPR:$rs2, uimm2:$uimm2)>;
+
+// Reuse complex patterns from StdExtZba
+def : Pat<(add sh1add_op:$rs1, non_imm12:$rs2),
+ (TH_ADDSL GPR:$rs2, sh1add_op:$rs1, 1)>;
+def : Pat<(add sh2add_op:$rs1, non_imm12:$rs2),
+ (TH_ADDSL GPR:$rs2, sh2add_op:$rs1, 2)>;
+def : Pat<(add sh3add_op:$rs1, non_imm12:$rs2),
+ (TH_ADDSL GPR:$rs2, sh3add_op:$rs1, 3)>;
+
+def : Pat<(add (mul_oneuse GPR:$rs1, (XLenVT 6)), GPR:$rs2),
+ (TH_ADDSL GPR:$rs2, (TH_ADDSL GPR:$rs1, GPR:$rs1, 1), 1)>;
+def : Pat<(add (mul_oneuse GPR:$rs1, (XLenVT 10)), GPR:$rs2),
+ (TH_ADDSL GPR:$rs2, (TH_ADDSL GPR:$rs1, GPR:$rs1, 2), 1)>;
+def : Pat<(add (mul_oneuse GPR:$rs1, (XLenVT 18)), GPR:$rs2),
+ (TH_ADDSL GPR:$rs2, (TH_ADDSL GPR:$rs1, GPR:$rs1, 3), 1)>;
+def : Pat<(add (mul_oneuse GPR:$rs1, (XLenVT 12)), GPR:$rs2),
+ (TH_ADDSL GPR:$rs2, (TH_ADDSL GPR:$rs1, GPR:$rs1, 1), 2)>;
+def : Pat<(add (mul_oneuse GPR:$rs1, (XLenVT 20)), GPR:$rs2),
+ (TH_ADDSL GPR:$rs2, (TH_ADDSL GPR:$rs1, GPR:$rs1, 2), 2)>;
+def : Pat<(add (mul_oneuse GPR:$rs1, (XLenVT 36)), GPR:$rs2),
+ (TH_ADDSL GPR:$rs2, (TH_ADDSL GPR:$rs1, GPR:$rs1, 3), 2)>;
+def : Pat<(add (mul_oneuse GPR:$rs1, (XLenVT 24)), GPR:$rs2),
+ (TH_ADDSL GPR:$rs2, (TH_ADDSL GPR:$rs1, GPR:$rs1, 1), 3)>;
+def : Pat<(add (mul_oneuse GPR:$rs1, (XLenVT 40)), GPR:$rs2),
+ (TH_ADDSL GPR:$rs2, (TH_ADDSL GPR:$rs1, GPR:$rs1, 2), 3)>;
+def : Pat<(add (mul_oneuse GPR:$rs1, (XLenVT 72)), GPR:$rs2),
+ (TH_ADDSL GPR:$rs2, (TH_ADDSL GPR:$rs1, GPR:$rs1, 3), 3)>;
+
+def : Pat<(add GPR:$r, CSImm12MulBy4:$i),
+ (TH_ADDSL GPR:$r, (ADDI X0, (SimmShiftRightBy2XForm CSImm12MulBy4:$i)), 2)>;
+def : Pat<(add GPR:$r, CSImm12MulBy8:$i),
+ (TH_ADDSL GPR:$r, (ADDI X0, (SimmShiftRightBy3XForm CSImm12MulBy8:$i)), 3)>;
+
+def : Pat<(mul GPR:$r, C3LeftShift:$i),
+ (SLLI (TH_ADDSL GPR:$r, GPR:$r, 1),
+ (TrailingZeros C3LeftShift:$i))>;
+def : Pat<(mul GPR:$r, C5LeftShift:$i),
+ (SLLI (TH_ADDSL GPR:$r, GPR:$r, 2),
+ (TrailingZeros C5LeftShift:$i))>;
+def : Pat<(mul GPR:$r, C9LeftShift:$i),
+ (SLLI (TH_ADDSL GPR:$r, GPR:$r, 3),
+ (TrailingZeros C9LeftShift:$i))>;
+
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 11)),
+ (TH_ADDSL GPR:$r, (TH_ADDSL GPR:$r, GPR:$r, 2), 1)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 19)),
+ (TH_ADDSL GPR:$r, (TH_ADDSL GPR:$r, GPR:$r, 3), 1)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 13)),
+ (TH_ADDSL GPR:$r, (TH_ADDSL GPR:$r, GPR:$r, 1), 2)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 21)),
+ (TH_ADDSL GPR:$r, (TH_ADDSL GPR:$r, GPR:$r, 2), 2)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 37)),
+ (TH_ADDSL GPR:$r, (TH_ADDSL GPR:$r, GPR:$r, 3), 2)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 25)),
+ (TH_ADDSL (TH_ADDSL GPR:$r, GPR:$r, 2), (TH_ADDSL GPR:$r, GPR:$r, 2), 2)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 41)),
+ (TH_ADDSL GPR:$r, (TH_ADDSL GPR:$r, GPR:$r, 2), 3)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 73)),
+ (TH_ADDSL GPR:$r, (TH_ADDSL GPR:$r, GPR:$r, 3), 3)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 27)),
+ (TH_ADDSL (TH_ADDSL GPR:$r, GPR:$r, 3), (TH_ADDSL GPR:$r, GPR:$r, 3), 1)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 45)),
+ (TH_ADDSL (TH_ADDSL GPR:$r, GPR:$r, 3), (TH_ADDSL GPR:$r, GPR:$r, 3), 2)>;
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 81)),
+ (TH_ADDSL (TH_ADDSL GPR:$r, GPR:$r, 3), (TH_ADDSL GPR:$r, GPR:$r, 3), 3)>;
+
+def : Pat<(mul_const_oneuse GPR:$r, (XLenVT 200)),
+ (SLLI (TH_ADDSL (TH_ADDSL GPR:$r, GPR:$r, 2),
+ (TH_ADDSL GPR:$r, GPR:$r, 2), 2), 3)>;
+} // Predicates = [HasVendorXTHeadBa]
+
defm PseudoTHVdotVMAQA : VPseudoVMAQA_VV_VX;
defm PseudoTHVdotVMAQAU : VPseudoVMAQA_VV_VX;
defm PseudoTHVdotVMAQASU : VPseudoVMAQA_VV_VX;
diff --git a/llvm/test/CodeGen/RISCV/attributes.ll b/llvm/test/CodeGen/RISCV/attributes.ll
--- a/llvm/test/CodeGen/RISCV/attributes.ll
+++ b/llvm/test/CodeGen/RISCV/attributes.ll
@@ -86,6 +86,7 @@
; RUN: llc -mtriple=riscv64 -mattr=+svpbmt %s -o - | FileCheck --check-prefix=RV64SVPBMT %s
; RUN: llc -mtriple=riscv64 -mattr=+svinval %s -o - | FileCheck --check-prefix=RV64SVINVAL %s
; RUN: llc -mtriple=riscv64 -mattr=+xventanacondops %s -o - | FileCheck --check-prefix=RV64XVENTANACONDOPS %s
+; RUN: llc -mtriple=riscv64 -mattr=+xtheadba %s -o - | FileCheck --check-prefix=RV64XTHEADBA %s
; RUN: llc -mtriple=riscv64 -mattr=+xtheadvdot %s -o - | FileCheck --check-prefix=RV64XTHEADVDOT %s
; RUN: llc -mtriple=riscv64 -mattr=+experimental-zawrs %s -o - | FileCheck --check-prefix=RV64ZAWRS %s
; RUN: llc -mtriple=riscv64 -mattr=+experimental-ztso %s -o - | FileCheck --check-prefix=RV64ZTSO %s
@@ -180,6 +181,7 @@
; RV64SVPBMT: .attribute 5, "rv64i2p0_svpbmt1p0"
; RV64SVINVAL: .attribute 5, "rv64i2p0_svinval1p0"
; RV64XVENTANACONDOPS: .attribute 5, "rv64i2p0_xventanacondops1p0"
+; RV64XTHEADBA: .attribute 5, "rv64i2p0_xtheadba1p0"
; RV64XTHEADVDOT: .attribute 5, "rv64i2p0_f2p0_d2p0_v1p0_zve32f1p0_zve32x1p0_zve64d1p0_zve64f1p0_zve64x1p0_zvl128b1p0_zvl32b1p0_zvl64b1p0_xtheadvdot1p0"
; RV64ZTSO: .attribute 5, "rv64i2p0_ztso0p1"
; RV64ZCA: .attribute 5, "rv64i2p0_zca1p0"
diff --git a/llvm/test/CodeGen/RISCV/rv64xtheadba.ll b/llvm/test/CodeGen/RISCV/rv64xtheadba.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rv64xtheadba.ll
@@ -0,0 +1,319 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --extra_scrub
+; RUN: llc -mtriple=riscv64 -mattr=+m -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefixes=CHECK,RV64I
+; RUN: llc -mtriple=riscv64 -mattr=+m,+xtheadba -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefixes=CHECK,RV64XTHEADBA
+
+define signext i16 @sh1add(i64 %0, ptr %1) {
+; RV64I-LABEL: sh1add:
+; RV64I: # %bb.0:
+; RV64I-NEXT: slli a0, a0, 1
+; RV64I-NEXT: add a0, a1, a0
+; RV64I-NEXT: lh a0, 0(a0)
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: sh1add:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 1
+; RV64XTHEADBA-NEXT: lh a0, 0(a0)
+; RV64XTHEADBA-NEXT: ret
+ %3 = getelementptr inbounds i16, ptr %1, i64 %0
+ %4 = load i16, ptr %3
+ ret i16 %4
+}
+
+define signext i32 @sh2add(i64 %0, ptr %1) {
+; RV64I-LABEL: sh2add:
+; RV64I: # %bb.0:
+; RV64I-NEXT: slli a0, a0, 2
+; RV64I-NEXT: add a0, a1, a0
+; RV64I-NEXT: lw a0, 0(a0)
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: sh2add:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 2
+; RV64XTHEADBA-NEXT: lw a0, 0(a0)
+; RV64XTHEADBA-NEXT: ret
+ %3 = getelementptr inbounds i32, ptr %1, i64 %0
+ %4 = load i32, ptr %3
+ ret i32 %4
+}
+
+define i64 @sh3add(i64 %0, ptr %1) {
+; RV64I-LABEL: sh3add:
+; RV64I: # %bb.0:
+; RV64I-NEXT: slli a0, a0, 3
+; RV64I-NEXT: add a0, a1, a0
+; RV64I-NEXT: ld a0, 0(a0)
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: sh3add:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 3
+; RV64XTHEADBA-NEXT: ld a0, 0(a0)
+; RV64XTHEADBA-NEXT: ret
+ %3 = getelementptr inbounds i64, ptr %1, i64 %0
+ %4 = load i64, ptr %3
+ ret i64 %4
+}
+
+; Type legalization inserts a sext_inreg after the first add. That add will be
+; selected as sh2add which does not sign extend. SimplifyDemandedBits is unable
+; to remove the sext_inreg because it has multiple uses. The ashr will use the
+; sext_inreg to become sraiw. This leaves the sext_inreg only used by the shl.
+; If the shl is selected as sllw, we don't need the sext_inreg.
+define i64 @sh2add_extra_sext(i32 %x, i32 %y, i32 %z) {
+; RV64I-LABEL: sh2add_extra_sext:
+; RV64I: # %bb.0:
+; RV64I-NEXT: slli a0, a0, 2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: sllw a1, a2, a0
+; RV64I-NEXT: sraiw a0, a0, 2
+; RV64I-NEXT: mul a0, a1, a0
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: sh2add_extra_sext:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 2
+; RV64XTHEADBA-NEXT: sllw a1, a2, a0
+; RV64XTHEADBA-NEXT: sraiw a0, a0, 2
+; RV64XTHEADBA-NEXT: mul a0, a1, a0
+; RV64XTHEADBA-NEXT: ret
+ %a = shl i32 %x, 2
+ %b = add i32 %a, %y
+ %c = shl i32 %z, %b
+ %d = ashr i32 %b, 2
+ %e = sext i32 %c to i64
+ %f = sext i32 %d to i64
+ %g = mul i64 %e, %f
+ ret i64 %g
+}
+
+define i64 @addmul6(i64 %a, i64 %b) {
+; RV64I-LABEL: addmul6:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a2, 6
+; RV64I-NEXT: mul a0, a0, a2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: addmul6:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 1
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 1
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 6
+ %d = add i64 %c, %b
+ ret i64 %d
+}
+
+define i64 @addmul10(i64 %a, i64 %b) {
+; RV64I-LABEL: addmul10:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a2, 10
+; RV64I-NEXT: mul a0, a0, a2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: addmul10:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 2
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 1
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 10
+ %d = add i64 %c, %b
+ ret i64 %d
+}
+
+define i64 @addmul12(i64 %a, i64 %b) {
+; RV64I-LABEL: addmul12:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a2, 12
+; RV64I-NEXT: mul a0, a0, a2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: addmul12:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 1
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 2
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 12
+ %d = add i64 %c, %b
+ ret i64 %d
+}
+
+define i64 @addmul18(i64 %a, i64 %b) {
+; RV64I-LABEL: addmul18:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a2, 18
+; RV64I-NEXT: mul a0, a0, a2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: addmul18:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 3
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 1
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 18
+ %d = add i64 %c, %b
+ ret i64 %d
+}
+
+define i64 @addmul20(i64 %a, i64 %b) {
+; RV64I-LABEL: addmul20:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a2, 20
+; RV64I-NEXT: mul a0, a0, a2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: addmul20:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 2
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 2
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 20
+ %d = add i64 %c, %b
+ ret i64 %d
+}
+
+define i64 @addmul24(i64 %a, i64 %b) {
+; RV64I-LABEL: addmul24:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a2, 24
+; RV64I-NEXT: mul a0, a0, a2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: addmul24:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 1
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 3
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 24
+ %d = add i64 %c, %b
+ ret i64 %d
+}
+
+define i64 @addmul36(i64 %a, i64 %b) {
+; RV64I-LABEL: addmul36:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a2, 36
+; RV64I-NEXT: mul a0, a0, a2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: addmul36:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 3
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 2
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 36
+ %d = add i64 %c, %b
+ ret i64 %d
+}
+
+define i64 @addmul40(i64 %a, i64 %b) {
+; RV64I-LABEL: addmul40:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a2, 40
+; RV64I-NEXT: mul a0, a0, a2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: addmul40:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 2
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 3
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 40
+ %d = add i64 %c, %b
+ ret i64 %d
+}
+
+define i64 @addmul72(i64 %a, i64 %b) {
+; RV64I-LABEL: addmul72:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a2, 72
+; RV64I-NEXT: mul a0, a0, a2
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: addmul72:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 3
+; RV64XTHEADBA-NEXT: th.addsl a0, a1, a0, 3
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 72
+ %d = add i64 %c, %b
+ ret i64 %d
+}
+
+define i64 @mul96(i64 %a) {
+; RV64I-LABEL: mul96:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a1, 96
+; RV64I-NEXT: mul a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: mul96:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 1
+; RV64XTHEADBA-NEXT: slli a0, a0, 5
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 96
+ ret i64 %c
+}
+
+define i64 @mul160(i64 %a) {
+; RV64I-LABEL: mul160:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a1, 160
+; RV64I-NEXT: mul a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: mul160:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 2
+; RV64XTHEADBA-NEXT: slli a0, a0, 5
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 160
+ ret i64 %c
+}
+
+define i64 @mul200(i64 %a) {
+; RV64I-LABEL: mul200:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a1, 200
+; RV64I-NEXT: mul a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: mul200:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 2
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 2
+; RV64XTHEADBA-NEXT: slli a0, a0, 3
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 200
+ ret i64 %c
+}
+
+define i64 @mul288(i64 %a) {
+; RV64I-LABEL: mul288:
+; RV64I: # %bb.0:
+; RV64I-NEXT: li a1, 288
+; RV64I-NEXT: mul a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV64XTHEADBA-LABEL: mul288:
+; RV64XTHEADBA: # %bb.0:
+; RV64XTHEADBA-NEXT: th.addsl a0, a0, a0, 3
+; RV64XTHEADBA-NEXT: slli a0, a0, 5
+; RV64XTHEADBA-NEXT: ret
+ %c = mul i64 %a, 288
+ ret i64 %c
+}
+
diff --git a/llvm/test/MC/RISCV/rv64xtheadba-invalid.s b/llvm/test/MC/RISCV/rv64xtheadba-invalid.s
new file mode 100644
--- /dev/null
+++ b/llvm/test/MC/RISCV/rv64xtheadba-invalid.s
@@ -0,0 +1,8 @@
+# RUN: not llvm-mc -triple riscv64 -mattr=+xtheadba < %s 2>&1 | FileCheck %s
+
+# Too few operands
+th.addsl t0, t1 # CHECK: :[[@LINE]]:1: error: too few operands for instruction
+# Too few operands
+th.addsl t0, t1, t2 # CHECK: :[[@LINE]]:1: error: too few operands for instruction
+# Immediate operand out of range
+th.addsl t0, t1, t2, 4 # CHECK: :[[@LINE]]:22: error: immediate must be an integer in the range [0, 3]
diff --git a/llvm/test/MC/RISCV/rv64xtheadba-valid.s b/llvm/test/MC/RISCV/rv64xtheadba-valid.s
new file mode 100644
--- /dev/null
+++ b/llvm/test/MC/RISCV/rv64xtheadba-valid.s
@@ -0,0 +1,16 @@
+# With Bitmanip base extension:
+# RUN: llvm-mc %s -triple=riscv64 -mattr=+xtheadba -show-encoding \
+# RUN: | FileCheck -check-prefixes=CHECK-ASM,CHECK-ASM-AND-OBJ %s
+# RUN: llvm-mc -filetype=obj -triple=riscv64 -mattr=+xtheadba < %s \
+# RUN: | llvm-objdump --mattr=+xtheadba -d -r - \
+# RUN: | FileCheck --check-prefix=CHECK-ASM-AND-OBJ %s
+
+# CHECK-ASM-AND-OBJ: th.addsl t0, t1, t2, 1
+# CHECK-ASM: encoding: [0x8b,0x12,0x73,0x02]
+th.addsl t0, t1, t2, 1
+# CHECK-ASM-AND-OBJ: th.addsl t0, t1, t2, 2
+# CHECK-ASM: encoding: [0x8b,0x12,0x73,0x04]
+th.addsl t0, t1, t2, 2
+# CHECK-ASM-AND-OBJ: th.addsl t0, t1, t2, 3
+# CHECK-ASM: encoding: [0x8b,0x12,0x73,0x06]
+th.addsl t0, t1, t2, 3