[llvm] 145e28d - [RISCV][llvm] Support logical comparison codegen for P extension (#174626)
via llvm-commits
llvm-commits at lists.llvm.org
Sun Jan 11 22:45:50 PST 2026
Author: Brandon Wu
Date: 2026-01-12T06:45:45Z
New Revision: 145e28d061ae560f5b61c3fc2b9d487632d2ab43
URL: https://github.com/llvm/llvm-project/commit/145e28d061ae560f5b61c3fc2b9d487632d2ab43
DIFF: https://github.com/llvm/llvm-project/commit/145e28d061ae560f5b61c3fc2b9d487632d2ab43.diff
LOG: [RISCV][llvm] Support logical comparison codegen for P extension (#174626)
Result type of P extension's comparison instructions is same as operands
and the result bits are all 1s or 0s so we need to set
ZeroOrNegativeOneBooleanContent to make sext(setcc) auto combined.
Added:
Modified:
llvm/lib/Target/RISCV/RISCVISelLowering.cpp
llvm/lib/Target/RISCV/RISCVInstrInfoP.td
llvm/test/CodeGen/RISCV/rvp-ext-rv32.ll
llvm/test/CodeGen/RISCV/rvp-ext-rv64.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index b23bffba4a0e0..db1973fc27326 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -554,6 +554,12 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
setOperationAction({ISD::SDIV, ISD::UDIV, ISD::SREM, ISD::UREM,
ISD::SDIVREM, ISD::UDIVREM},
VTs, Expand);
+ setOperationAction(ISD::SETCC, VTs, Legal);
+ setCondCodeAction({ISD::SETNE, ISD::SETGT, ISD::SETGE, ISD::SETUGT,
+ ISD::SETUGE, ISD::SETULE, ISD::SETLE},
+ VTs, Expand);
+ // P extension vector comparisons produce all 1s for true, all 0s for false
+ setBooleanVectorContents(ZeroOrNegativeOneBooleanContent);
}
if (Subtarget.hasStdExtZfbfmin()) {
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoP.td b/llvm/lib/Target/RISCV/RISCVInstrInfoP.td
index 6603ece86c7b6..d2b122df62264 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoP.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoP.td
@@ -1596,6 +1596,22 @@ let Predicates = [HasStdExtP] in {
// // splat pattern
def: Pat<(XLenVecI8VT (splat_vector (XLenVT GPR:$rs2))), (PADD_BS (XLenVT X0), GPR:$rs2)>;
def: Pat<(XLenVecI16VT (splat_vector (XLenVT GPR:$rs2))), (PADD_HS (XLenVT X0), GPR:$rs2)>;
+
+ // 8/16-bit comparison patterns (result is all 1s or all 0s per element)
+ // a == b
+ def: Pat<(XLenVecI8VT (setcc (XLenVecI8VT GPR:$rs1), (XLenVecI8VT GPR:$rs2), SETEQ)),
+ (PMSEQ_B GPR:$rs1, GPR:$rs2)>;
+ def: Pat<(XLenVecI16VT (setcc (XLenVecI16VT GPR:$rs1), (XLenVecI16VT GPR:$rs2), SETEQ)),
+ (PMSEQ_H GPR:$rs1, GPR:$rs2)>;
+ // a < b
+ def: Pat<(XLenVecI8VT (setcc (XLenVecI8VT GPR:$rs1), (XLenVecI8VT GPR:$rs2), SETLT)),
+ (PMSLT_B GPR:$rs1, GPR:$rs2)>;
+ def: Pat<(XLenVecI8VT (setcc (XLenVecI8VT GPR:$rs1), (XLenVecI8VT GPR:$rs2), SETULT)),
+ (PMSLTU_B GPR:$rs1, GPR:$rs2)>;
+ def: Pat<(XLenVecI16VT (setcc (XLenVecI16VT GPR:$rs1), (XLenVecI16VT GPR:$rs2), SETLT)),
+ (PMSLT_H GPR:$rs1, GPR:$rs2)>;
+ def: Pat<(XLenVecI16VT (setcc (XLenVecI16VT GPR:$rs1), (XLenVecI16VT GPR:$rs2), SETULT)),
+ (PMSLTU_H GPR:$rs1, GPR:$rs2)>;
} // Predicates = [HasStdExtP]
let Predicates = [HasStdExtP, IsRV32] in {
@@ -1679,6 +1695,21 @@ let Predicates = [HasStdExtP, IsRV64] in {
// splat pattern
def: Pat<(v2i32 (splat_vector (XLenVT GPR:$rs2))), (PADD_WS (XLenVT X0), GPR:$rs2)>;
+ // 32-bit comparison patterns (result is all 1s or all 0s per element)
+ // a == b
+ def: Pat<(v2i32 (setcc (v2i32 GPR:$rs1), (v2i32 GPR:$rs2), SETEQ)),
+ (PMSEQ_W GPR:$rs1, GPR:$rs2)>;
+ // a < b
+ def: Pat<(v2i32 (setcc (v2i32 GPR:$rs1), (v2i32 GPR:$rs2), SETLT)),
+ (PMSLT_W GPR:$rs1, GPR:$rs2)>;
+ def: Pat<(v2i32 (setcc (v2i32 GPR:$rs1), (v2i32 GPR:$rs2), SETULT)),
+ (PMSLTU_W GPR:$rs1, GPR:$rs2)>;
+ // a > b => b < a
+ def: Pat<(v2i32 (setcc (v2i32 GPR:$rs2), (v2i32 GPR:$rs1), SETGT)),
+ (PMSLT_W GPR:$rs1, GPR:$rs2)>;
+ def: Pat<(v2i32 (setcc (v2i32 GPR:$rs2), (v2i32 GPR:$rs1), SETUGT)),
+ (PMSLTU_W GPR:$rs1, GPR:$rs2)>;
+
// 32-bit logical shift left/right patterns
def: Pat<(v2i32 (shl GPR:$rs1, (v2i32 (splat_vector uimm5:$shamt)))),
(PSLLI_W GPR:$rs1, uimm5:$shamt)>;
diff --git a/llvm/test/CodeGen/RISCV/rvp-ext-rv32.ll b/llvm/test/CodeGen/RISCV/rvp-ext-rv32.ll
index 6497203c70c73..10964a64b576a 100644
--- a/llvm/test/CodeGen/RISCV/rvp-ext-rv32.ll
+++ b/llvm/test/CodeGen/RISCV/rvp-ext-rv32.ll
@@ -1687,3 +1687,335 @@ define void @test_purem_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
store <4 x i8> %res, ptr %ret_ptr
ret void
}
+
+; Comparison operations for v2i16
+define void @test_eq_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_eq_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmseq.h a1, a1, a2
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp eq <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ne_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ne_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmseq.h a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp ne <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_slt_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_slt_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmslt.h a1, a1, a2
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp slt <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sle_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sle_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmslt.h a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp sle <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sgt_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sgt_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmslt.h a1, a2, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp sgt <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sge_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sge_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmslt.h a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp sge <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ult_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ult_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmsltu.h a1, a1, a2
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp ult <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ule_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ule_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmsltu.h a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp ule <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ugt_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ugt_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmsltu.h a1, a2, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp ugt <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_uge_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_uge_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmsltu.h a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i16>, ptr %a_ptr
+ %b = load <2 x i16>, ptr %b_ptr
+ %cmp = icmp uge <2 x i16> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i16>
+ store <2 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+; Comparison operations for v4i8
+define void @test_eq_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_eq_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmseq.b a1, a1, a2
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp eq <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ne_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ne_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmseq.b a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp ne <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_slt_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_slt_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmslt.b a1, a1, a2
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp slt <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sle_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sle_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmslt.b a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp sle <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sgt_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sgt_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmslt.b a1, a2, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp sgt <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sge_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sge_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmslt.b a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp sge <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ult_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ult_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmsltu.b a1, a1, a2
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp ult <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ule_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ule_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmsltu.b a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp ule <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ugt_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ugt_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmsltu.b a1, a2, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp ugt <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_uge_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_uge_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: lw a1, 0(a1)
+; CHECK-NEXT: lw a2, 0(a2)
+; CHECK-NEXT: pmsltu.b a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sw a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i8>, ptr %a_ptr
+ %b = load <4 x i8>, ptr %b_ptr
+ %cmp = icmp uge <4 x i8> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i8>
+ store <4 x i8> %res, ptr %ret_ptr
+ ret void
+}
diff --git a/llvm/test/CodeGen/RISCV/rvp-ext-rv64.ll b/llvm/test/CodeGen/RISCV/rvp-ext-rv64.ll
index db5a510ae422b..48eda85f375cb 100644
--- a/llvm/test/CodeGen/RISCV/rvp-ext-rv64.ll
+++ b/llvm/test/CodeGen/RISCV/rvp-ext-rv64.ll
@@ -1812,3 +1812,501 @@ define void @test_purem_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
store <2 x i32> %res, ptr %ret_ptr
ret void
}
+
+; Comparison operations for v4i16
+define void @test_eq_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_eq_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmseq.h a1, a1, a2
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp eq <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ne_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ne_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmseq.h a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp ne <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_slt_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_slt_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.h a1, a1, a2
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp slt <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sle_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sle_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.h a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp sle <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sgt_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sgt_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.h a1, a2, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp sgt <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sge_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sge_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.h a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp sge <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ult_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ult_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.h a1, a1, a2
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp ult <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ule_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ule_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.h a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp ule <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ugt_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ugt_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.h a1, a2, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp ugt <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_uge_h(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_uge_h:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.h a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <4 x i16>, ptr %a_ptr
+ %b = load <4 x i16>, ptr %b_ptr
+ %cmp = icmp uge <4 x i16> %a, %b
+ %res = sext <4 x i1> %cmp to <4 x i16>
+ store <4 x i16> %res, ptr %ret_ptr
+ ret void
+}
+
+; Comparison operations for v8i8
+define void @test_eq_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_eq_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmseq.b a1, a1, a2
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp eq <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ne_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ne_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmseq.b a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp ne <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_slt_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_slt_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.b a1, a1, a2
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp slt <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sle_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sle_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.b a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp sle <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sgt_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sgt_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.b a1, a2, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp sgt <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sge_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sge_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.b a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp sge <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ult_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ult_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.b a1, a1, a2
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp ult <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ule_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ule_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.b a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp ule <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ugt_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ugt_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.b a1, a2, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp ugt <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_uge_b(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_uge_b:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.b a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <8 x i8>, ptr %a_ptr
+ %b = load <8 x i8>, ptr %b_ptr
+ %cmp = icmp uge <8 x i8> %a, %b
+ %res = sext <8 x i1> %cmp to <8 x i8>
+ store <8 x i8> %res, ptr %ret_ptr
+ ret void
+}
+
+; Comparison operations for v2i32
+define void @test_eq_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_eq_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmseq.w a1, a1, a2
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp eq <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ne_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ne_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmseq.w a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp ne <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_slt_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_slt_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.w a1, a1, a2
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp slt <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sle_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sle_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.w a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp sle <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sgt_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sgt_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.w a1, a2, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp sgt <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_sge_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_sge_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmslt.w a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp sge <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ult_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ult_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.w a1, a1, a2
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp ult <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ule_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ule_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.w a1, a2, a1
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp ule <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_ugt_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_ugt_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.w a1, a2, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp ugt <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
+
+define void @test_uge_w(ptr %ret_ptr, ptr %a_ptr, ptr %b_ptr) {
+; CHECK-LABEL: test_uge_w:
+; CHECK: # %bb.0:
+; CHECK-NEXT: ld a1, 0(a1)
+; CHECK-NEXT: ld a2, 0(a2)
+; CHECK-NEXT: pmsltu.w a1, a1, a2
+; CHECK-NEXT: not a1, a1
+; CHECK-NEXT: sd a1, 0(a0)
+; CHECK-NEXT: ret
+ %a = load <2 x i32>, ptr %a_ptr
+ %b = load <2 x i32>, ptr %b_ptr
+ %cmp = icmp uge <2 x i32> %a, %b
+ %res = sext <2 x i1> %cmp to <2 x i32>
+ store <2 x i32> %res, ptr %ret_ptr
+ ret void
+}
More information about the llvm-commits
mailing list