[llvm] [RISCV] Fix the cost of `llvm.vector.reduce.and` (PR #119160)

via llvm-commits llvm-commits at lists.llvm.org
Sun Dec 8 19:07:14 PST 2024


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-risc-v

Author: Shao-Ce SUN (sunshaoce)

<details>
<summary>Changes</summary>

I added some CodeGen test cases related to reduce. To maintain consistency, I also added cases for instructions like `vector.reduce.or`.

For cases where `v1i1` type generates `VFIRST`, please refer to: https://reviews.llvm.org/D139512.

---

Patch is 48.98 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/119160.diff


6 Files Affected:

- (modified) llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp (+16-2) 
- (modified) llvm/test/Analysis/CostModel/RISCV/reduce-and.ll (+42-8) 
- (modified) llvm/test/Analysis/CostModel/RISCV/reduce-max.ll (+2-2) 
- (modified) llvm/test/Analysis/CostModel/RISCV/reduce-min.ll (+2-2) 
- (modified) llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vreductions-mask.ll (+472) 
- (modified) llvm/test/CodeGen/RISCV/rvv/vreductions-mask.ll (+558) 


``````````diff
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index cbf8c57fde44d1..4b5f5b0c8e047d 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1538,13 +1538,27 @@ RISCVTTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *Ty,
   if (ElementTy->isIntegerTy(1)) {
     if (ISD == ISD::AND) {
       // Example sequences:
+      //   vfirst.m a0, v0
+      //   seqz a0, a0
+      if (LT.second == MVT::v1i1)
+        return getRISCVInstructionCost(RISCV::VFIRST_M, LT.second, CostKind) +
+               getCmpSelInstrCost(Instruction::ICmp, ElementTy, ElementTy,
+                                  CmpInst::ICMP_EQ, CostKind);
+      // Example sequences:
       //   vsetvli a0, zero, e8, mf8, ta, ma
       //   vmand.mm v8, v9, v8 ; needed every time type is split
       //   vmnot.m v8, v0
       //   vcpop.m a0, v8
       //   seqz a0, a0
-      return LT.first * getRISCVInstructionCost(RISCV::VMNAND_MM, LT.second,
-                                                CostKind) +
+
+      // Fixed VT:    In v512i1 and larger vector elements,
+      // Scalable VT: In v128i1 and larger vector elements,
+      // the VMAND_MM instructions have started to be added.
+      return ((LT.first >= 2)
+                  ? LT.first - (LT.second.isScalableVector() ? 1 : 2)
+                  : 0) *
+                 getRISCVInstructionCost(RISCV::VMAND_MM, LT.second, CostKind) +
+             getRISCVInstructionCost(RISCV::VMNAND_MM, LT.second, CostKind) +
              getRISCVInstructionCost(RISCV::VCPOP_M, LT.second, CostKind) +
              getCmpSelInstrCost(Instruction::ICmp, ElementTy, ElementTy,
                                 CmpInst::ICMP_EQ, CostKind);
diff --git a/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll b/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll
index e4f1cf8ff418a8..7b626c426fc226 100644
--- a/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/reduce-and.ll
@@ -6,7 +6,7 @@
 
 define i32 @reduce_i1(i32 %arg) {
 ; CHECK-LABEL: 'reduce_i1'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
@@ -14,13 +14,24 @@ define i32 @reduce_i1(i32 %arg) {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256 = call i1 @llvm.vector.reduce.and.v256i1(<256 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V512 = call i1 @llvm.vector.reduce.and.v512i1(<512 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V1024 = call i1 @llvm.vector.reduce.and.v1024i1(<1024 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V256 = call i1 @llvm.vector.reduce.and.v256i1(<256 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V512 = call i1 @llvm.vector.reduce.and.v512i1(<512 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V1024 = call i1 @llvm.vector.reduce.and.v1024i1(<1024 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV1 = call i1 @llvm.vector.reduce.and.nxv1i1(<vscale x 1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV2 = call i1 @llvm.vector.reduce.and.nxv2i1(<vscale x 2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV4 = call i1 @llvm.vector.reduce.and.nxv4i1(<vscale x 4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV8 = call i1 @llvm.vector.reduce.and.nxv8i1(<vscale x 8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV16 = call i1 @llvm.vector.reduce.and.nxv16i1(<vscale x 16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV32 = call i1 @llvm.vector.reduce.and.nxv32i1(<vscale x 32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV64 = call i1 @llvm.vector.reduce.and.nxv64i1(<vscale x 64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NXV128 = call i1 @llvm.vector.reduce.and.nxv128i1(<vscale x 128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NXV256 = call i1 @llvm.vector.reduce.and.nxv256i1(<vscale x 256 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %NXV512 = call i1 @llvm.vector.reduce.and.nxv512i1(<vscale x 512 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %NXV1024 = call i1 @llvm.vector.reduce.and.nxv1024i1(<vscale x 1024 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SIZE-LABEL: 'reduce_i1'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
@@ -28,9 +39,20 @@ define i32 @reduce_i1(i32 %arg) {
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256 = call i1 @llvm.vector.reduce.and.v256i1(<256 x i1> undef)
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V512 = call i1 @llvm.vector.reduce.and.v512i1(<512 x i1> undef)
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V1024 = call i1 @llvm.vector.reduce.and.v1024i1(<1024 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V256 = call i1 @llvm.vector.reduce.and.v256i1(<256 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V512 = call i1 @llvm.vector.reduce.and.v512i1(<512 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V1024 = call i1 @llvm.vector.reduce.and.v1024i1(<1024 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV1 = call i1 @llvm.vector.reduce.and.nxv1i1(<vscale x 1 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV2 = call i1 @llvm.vector.reduce.and.nxv2i1(<vscale x 2 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV4 = call i1 @llvm.vector.reduce.and.nxv4i1(<vscale x 4 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV8 = call i1 @llvm.vector.reduce.and.nxv8i1(<vscale x 8 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV16 = call i1 @llvm.vector.reduce.and.nxv16i1(<vscale x 16 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV32 = call i1 @llvm.vector.reduce.and.nxv32i1(<vscale x 32 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %NXV64 = call i1 @llvm.vector.reduce.and.nxv64i1(<vscale x 64 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NXV128 = call i1 @llvm.vector.reduce.and.nxv128i1(<vscale x 128 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NXV256 = call i1 @llvm.vector.reduce.and.nxv256i1(<vscale x 256 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %NXV512 = call i1 @llvm.vector.reduce.and.nxv512i1(<vscale x 512 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %NXV1024 = call i1 @llvm.vector.reduce.and.nxv1024i1(<vscale x 1024 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %V1   = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
@@ -44,6 +66,18 @@ define i32 @reduce_i1(i32 %arg) {
   %V256 = call i1 @llvm.vector.reduce.and.v256i1(<256 x i1> undef)
   %V512 = call i1 @llvm.vector.reduce.and.v512i1(<512 x i1> undef)
   %V1024 = call i1 @llvm.vector.reduce.and.v1024i1(<1024 x i1> undef)
+
+  %NXV1   = call i1 @llvm.vector.reduce.and.nxv1i1(<vscale x 1 x i1> undef)
+  %NXV2   = call i1 @llvm.vector.reduce.and.nxv2i1(<vscale x 2 x i1> undef)
+  %NXV4   = call i1 @llvm.vector.reduce.and.nxv4i1(<vscale x 4 x i1> undef)
+  %NXV8   = call i1 @llvm.vector.reduce.and.nxv8i1(<vscale x 8 x i1> undef)
+  %NXV16  = call i1 @llvm.vector.reduce.and.nxv16i1(<vscale x 16 x i1> undef)
+  %NXV32  = call i1 @llvm.vector.reduce.and.nxv32i1(<vscale x 32 x i1> undef)
+  %NXV64  = call i1 @llvm.vector.reduce.and.nxv64i1(<vscale x 64 x i1> undef)
+  %NXV128 = call i1 @llvm.vector.reduce.and.nxv128i1(<vscale x 128 x i1> undef)
+  %NXV256 = call i1 @llvm.vector.reduce.and.nxv256i1(<vscale x 256 x i1> undef)
+  %NXV512 = call i1 @llvm.vector.reduce.and.nxv512i1(<vscale x 512 x i1> undef)
+  %NXV1024 = call i1 @llvm.vector.reduce.and.nxv1024i1(<vscale x 1024 x i1> undef)
   ret i32 undef
 }
 
diff --git a/llvm/test/Analysis/CostModel/RISCV/reduce-max.ll b/llvm/test/Analysis/CostModel/RISCV/reduce-max.ll
index f11e9f2b5ae837..5c9303af31747e 100644
--- a/llvm/test/Analysis/CostModel/RISCV/reduce-max.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/reduce-max.ll
@@ -176,7 +176,7 @@ define i32 @reduce_umax_i64(i32 %arg) {
 
 define i32 @reduce_smin_i1(i32 %arg) {
 ; CHECK-LABEL: 'reduce_smin_i1'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.smax.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.smax.v1i1(<1 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.smax.v2i1(<2 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i1 @llvm.vector.reduce.smax.v4i1(<4 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8 = call i1 @llvm.vector.reduce.smax.v8i1(<8 x i1> undef)
@@ -187,7 +187,7 @@ define i32 @reduce_smin_i1(i32 %arg) {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SIZE-LABEL: 'reduce_smin_i1'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.smax.v1i1(<1 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.smax.v1i1(<1 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.smax.v2i1(<2 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i1 @llvm.vector.reduce.smax.v4i1(<4 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8 = call i1 @llvm.vector.reduce.smax.v8i1(<8 x i1> undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/reduce-min.ll b/llvm/test/Analysis/CostModel/RISCV/reduce-min.ll
index 457fdbe46f73b5..9875d3e5858115 100644
--- a/llvm/test/Analysis/CostModel/RISCV/reduce-min.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/reduce-min.ll
@@ -6,7 +6,7 @@
 
 define i32 @reduce_umin_i1(i32 %arg) {
 ; CHECK-LABEL: 'reduce_umin_i1'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.umin.v1i1(<1 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.umin.v1i1(<1 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.umin.v2i1(<2 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i1 @llvm.vector.reduce.umin.v4i1(<4 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8 = call i1 @llvm.vector.reduce.umin.v8i1(<8 x i1> undef)
@@ -17,7 +17,7 @@ define i32 @reduce_umin_i1(i32 %arg) {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SIZE-LABEL: 'reduce_umin_i1'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.umin.v1i1(<1 x i1> undef)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.umin.v1i1(<1 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.umin.v2i1(<2 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i1 @llvm.vector.reduce.umin.v4i1(<4 x i1> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8 = call i1 @llvm.vector.reduce.umin.v8i1(<8 x i1> undef)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vreductions-mask.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vreductions-mask.ll
index 44d4a8a1e04cda..0d31ec5f784352 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vreductions-mask.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vreductions-mask.ll
@@ -763,3 +763,475 @@ define zeroext i1 @vreduce_add_v64i1(<64 x i1> %v) {
   %red = call i1 @llvm.vector.reduce.add.v64i1(<64 x i1> %v)
   ret i1 %red
 }
+
+declare i1 @llvm.vector.reduce.or.v128i1(<128 x i1>)
+
+define zeroext i1 @vreduce_or_v128i1(<128 x i1> %v) {
+; CHECK-LABEL: vreduce_or_v128i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    snez a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.xor.v128i1(<128 x i1>)
+
+define zeroext i1 @vreduce_xor_v128i1(<128 x i1> %v) {
+; CHECK-LABEL: vreduce_xor_v128i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.xor.v128i1(<128 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.and.v128i1(<128 x i1>)
+
+define zeroext i1 @vreduce_and_v128i1(<128 x i1> %v) {
+; CHECK-LABEL: vreduce_and_v128i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vmnot.m v8, v0
+; CHECK-NEXT:    vcpop.m a0, v8
+; CHECK-NEXT:    seqz a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.umax.v128i1(<128 x i1>)
+
+define zeroext i1 @vreduce_umax_v128i1(<128 x i1> %v) {
+; CHECK-LABEL: vreduce_umax_v128i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    snez a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.umax.v128i1(<128 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.smax.v128i1(<128 x i1>)
+
+define zeroext i1 @vreduce_smax_v128i1(<128 x i1> %v) {
+; CHECK-LABEL: vreduce_smax_v128i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vmnot.m v8, v0
+; CHECK-NEXT:    vcpop.m a0, v8
+; CHECK-NEXT:    seqz a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.smax.v128i1(<128 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.umin.v128i1(<128 x i1>)
+
+define zeroext i1 @vreduce_umin_v128i1(<128 x i1> %v) {
+; CHECK-LABEL: vreduce_umin_v128i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vmnot.m v8, v0
+; CHECK-NEXT:    vcpop.m a0, v8
+; CHECK-NEXT:    seqz a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.umin.v128i1(<128 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.smin.v128i1(<128 x i1>)
+
+define zeroext i1 @vreduce_smin_v128i1(<128 x i1> %v) {
+; CHECK-LABEL: vreduce_smin_v128i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vcpop.m a0, v0
+; CHECK-NEXT:    snez a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.smin.v128i1(<128 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.or.v256i1(<256 x i1>)
+
+define zeroext i1 @vreduce_or_v256i1(<256 x i1> %v) {
+; CHECK-LABEL: vreduce_or_v256i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vmor.mm v8, v0, v8
+; CHECK-NEXT:    vcpop.m a0, v8
+; CHECK-NEXT:    snez a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.or.v256i1(<256 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.xor.v256i1(<256 x i1>)
+
+define zeroext i1 @vreduce_xor_v256i1(<256 x i1> %v) {
+; CHECK-LABEL: vreduce_xor_v256i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vmxor.mm v8, v0, v8
+; CHECK-NEXT:    vcpop.m a0, v8
+; CHECK-NEXT:    andi a0, a0, 1
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.xor.v256i1(<256 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.and.v256i1(<256 x i1>)
+
+define zeroext i1 @vreduce_and_v256i1(<256 x i1> %v) {
+; CHECK-LABEL: vreduce_and_v256i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vmnand.mm v8, v0, v8
+; CHECK-NEXT:    vcpop.m a0, v8
+; CHECK-NEXT:    seqz a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.and.v256i1(<256 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.umax.v256i1(<256 x i1>)
+
+define zeroext i1 @vreduce_umax_v256i1(<256 x i1> %v) {
+; CHECK-LABEL: vreduce_umax_v256i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vmor.mm v8, v0, v8
+; CHECK-NEXT:    vcpop.m a0, v8
+; CHECK-NEXT:    snez a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.umax.v256i1(<256 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.reduce.smax.v256i1(<256 x i1>)
+
+define zeroext i1 @vreduce_smax_v256i1(<256 x i1> %v) {
+; CHECK-LABEL: vreduce_smax_v256i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a0, 128
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vmnand.mm v8, v0, v8
+; CHECK-NEXT:    vcpop.m a0, v8
+; CHECK-NEXT:    seqz a0, a0
+; CHECK-NEXT:    ret
+  %red = call i1 @llvm.vector.reduce.smax.v256i1(<256 x i1> %v)
+  ret i1 %red
+}
+
+declare i1 @llvm.vector.r...
[truncated]

``````````

</details>


https://github.com/llvm/llvm-project/pull/119160


More information about the llvm-commits mailing list