[AMDGPU] Support bfloat comparison for ballot intrinsic (#165495)

We do not have native instructions for direct bfloat comparisons.
However, we can expand bfloat to float, and do float comparison instead.

TODO: handle bfloat comparison for ballot intrinsic on global isel path.

Fixes: SWDEV-563403

3 files changed, 41 insertions, 2 deletions

diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index b34ab2a..8bb2808 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -7035,9 +7035,15 @@ static SDValue lowerBALLOTIntrinsic(const SITargetLowering &TLI, SDNode *N,
   SDLoc SL(N);
 
   if (Src.getOpcode() == ISD::SETCC) {
+    SDValue Op0 = Src.getOperand(0);
+    SDValue Op1 = Src.getOperand(1);
+    // Need to expand bfloat to float for comparison (setcc).
+    if (Op0.getValueType() == MVT::bf16) {
+      Op0 = DAG.getNode(ISD::FP_EXTEND, SL, MVT::f32, Op0);
+      Op1 = DAG.getNode(ISD::FP_EXTEND, SL, MVT::f32, Op1);
+    }
     // (ballot (ISD::SETCC ...)) -> (AMDGPUISD::SETCC ...)
-    return DAG.getNode(AMDGPUISD::SETCC, SL, VT, Src.getOperand(0),
-                       Src.getOperand(1), Src.getOperand(2));
+    return DAG.getNode(AMDGPUISD::SETCC, SL, VT, Op0, Op1, Src.getOperand(2));
   }
   if (const ConstantSDNode *Arg = dyn_cast<ConstantSDNode>(Src)) {
     // (ballot 0) -> 0
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i32.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i32.ll
index aa591d2..c1f3a12 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i32.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i32.ll
@@ -591,3 +591,24 @@ exit:
   store i32 %ballot, ptr addrspace(1) %out
   ret void
 }
+
+define amdgpu_cs i32 @compare_bfloats(bfloat %x, bfloat %y) {
+; GFX10-LABEL: compare_bfloats:
+; GFX10:       ; %bb.0:
+; GFX10-NEXT:    v_lshlrev_b32_e32 v1, 16, v1
+; GFX10-NEXT:    v_lshlrev_b32_e32 v0, 16, v0
+; GFX10-NEXT:    v_cmp_gt_f32_e64 s0, v0, v1
+; GFX10-NEXT:    ; return to shader part epilog
+;
+; GFX11-LABEL: compare_bfloats:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    v_mov_b16_e32 v2.l, 0
+; GFX11-NEXT:    v_mov_b16_e32 v2.h, v1.l
+; GFX11-NEXT:    v_mov_b16_e32 v1.h, v0.l
+; GFX11-NEXT:    v_mov_b16_e32 v1.l, v2.l
+; GFX11-NEXT:    v_cmp_gt_f32_e64 s0, v1, v2
+; GFX11-NEXT:    ; return to shader part epilog
+  %cmp = fcmp ogt bfloat %x, %y
+  %ballot = call i32 @llvm.amdgcn.ballot.i32(i1 %cmp)
+  ret i32 %ballot
+}
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i64.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i64.ll
index 30c2c26..827a01f 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i64.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i64.ll
@@ -557,3 +557,15 @@ exit:
   store i64 %ballot, ptr addrspace(1) %out
   ret void
 }
+
+define amdgpu_cs i64 @compare_bfloats(bfloat %x, bfloat %y) {
+; CHECK-LABEL: compare_bfloats:
+; CHECK:       ; %bb.0:
+; CHECK-NEXT:    v_lshlrev_b32_e32 v1, 16, v1
+; CHECK-NEXT:    v_lshlrev_b32_e32 v0, 16, v0
+; CHECK-NEXT:    v_cmp_gt_f32_e64 s[0:1], v0, v1
+; CHECK-NEXT:    ; return to shader part epilog
+  %cmp = fcmp ogt bfloat %x, %y
+  %ballot = call i64 @llvm.amdgcn.ballot.i64(i1 %cmp)
+  ret i64 %ballot
+}