From 62d6beba976142a58c7c95afd84a5d632ab4cd84 Mon Sep 17 00:00:00 2001
From: Helena Kotas <hekotas@microsoft.com>
Date: Thu, 28 Mar 2024 14:41:33 -0700
Subject: [PATCH] [DXIL] Add lowering for `reversebits` and `trunc` (#86909)

Add lowering of `llvm.bitreverse` and `llvm.trunc` intrinsics to DXIL
ops.

Fixes #86582
Fixes #86581
---
 llvm/lib/Target/DirectX/DXIL.td          |  6 +++++
 llvm/test/CodeGen/DirectX/reversebits.ll | 31 ++++++++++++++++++++++++
 llvm/test/CodeGen/DirectX/trunc.ll       | 20 +++++++++++++++
 llvm/test/CodeGen/DirectX/trunc_error.ll | 10 ++++++++
 4 files changed, 67 insertions(+)
 create mode 100644 llvm/test/CodeGen/DirectX/reversebits.ll
 create mode 100644 llvm/test/CodeGen/DirectX/trunc.ll
 create mode 100644 llvm/test/CodeGen/DirectX/trunc_error.ll

diff --git a/llvm/lib/Target/DirectX/DXIL.td b/llvm/lib/Target/DirectX/DXIL.td
index 1fd6f3ed044ecd..c5d7ee76275f86 100644
--- a/llvm/lib/Target/DirectX/DXIL.td
+++ b/llvm/lib/Target/DirectX/DXIL.td
@@ -292,6 +292,12 @@ def Round : DXILOpMapping<26, unary, int_round,
 def Floor : DXILOpMapping<27, unary, int_floor,
                          "Returns the largest integer that is less than or equal to the input.",
                          [llvm_halforfloat_ty, LLVMMatchType<0>]>;
+def Trunc : DXILOpMapping<29, unary, int_trunc,
+                         "Returns the specified value truncated to the integer component.",
+                         [llvm_halforfloat_ty, LLVMMatchType<0>]>;
+def Rbits : DXILOpMapping<30, unary, int_bitreverse,
+                         "Returns the specified value with its bits reversed.",
+                         [llvm_anyint_ty, LLVMMatchType<0>]>;
 def FMax : DXILOpMapping<35, binary, int_maxnum,
                          "Float maximum. FMax(a,b) = a > b ? a : b">;
 def FMin : DXILOpMapping<36, binary, int_minnum,
diff --git a/llvm/test/CodeGen/DirectX/reversebits.ll b/llvm/test/CodeGen/DirectX/reversebits.ll
new file mode 100644
index 00000000000000..b6a7a1bc6152e3
--- /dev/null
+++ b/llvm/test/CodeGen/DirectX/reversebits.ll
@@ -0,0 +1,31 @@
+; RUN: opt -S -dxil-op-lower < %s | FileCheck %s
+
+; Make sure dxil operation function calls for reversebits are generated for all integer types.
+
+; Function Attrs: nounwind
+define noundef i16 @test_bitreverse_short(i16 noundef %a) {
+entry:
+; CHECK:call i16 @dx.op.unary.i16(i32 30, i16 %{{.*}})
+  %elt.bitreverse = call i16 @llvm.bitreverse.i16(i16 %a)
+  ret i16 %elt.bitreverse
+}
+
+; Function Attrs: nounwind
+define noundef i32 @test_bitreverse_int(i32 noundef %a) {
+entry:
+; CHECK:call i32 @dx.op.unary.i32(i32 30, i32 %{{.*}})
+  %elt.bitreverse = call i32 @llvm.bitreverse.i32(i32 %a)
+  ret i32 %elt.bitreverse
+}
+
+; Function Attrs: nounwind
+define noundef i64 @test_bitreverse_long(i64 noundef %a) {
+entry:
+; CHECK:call i64 @dx.op.unary.i64(i32 30, i64 %{{.*}})
+  %elt.bitreverse = call i64 @llvm.bitreverse.i64(i64 %a)
+  ret i64 %elt.bitreverse
+}
+
+declare i16 @llvm.bitreverse.i16(i16)
+declare i32 @llvm.bitreverse.i32(i32)
+declare i64 @llvm.bitreverse.i64(i64)
diff --git a/llvm/test/CodeGen/DirectX/trunc.ll b/llvm/test/CodeGen/DirectX/trunc.ll
new file mode 100644
index 00000000000000..2072f28cef50a0
--- /dev/null
+++ b/llvm/test/CodeGen/DirectX/trunc.ll
@@ -0,0 +1,20 @@
+; RUN: opt -S -dxil-op-lower < %s | FileCheck %s
+
+; Make sure dxil operation function calls for trunc are generated for float and half.
+
+define noundef float @trunc_float(float noundef %a) {
+entry:
+; CHECK:call float @dx.op.unary.f32(i32 29, float %{{.*}})
+  %elt.trunc = call float @llvm.trunc.f32(float %a)
+  ret float %elt.trunc
+}
+
+define noundef half @trunc_half(half noundef %a) {
+entry:
+; CHECK:call half @dx.op.unary.f16(i32 29, half %{{.*}})
+  %elt.trunc = call half @llvm.trunc.f16(half %a)
+  ret half %elt.trunc
+}
+
+declare half @llvm.trunc.f16(half)
+declare float @llvm.trunc.f32(float)
diff --git a/llvm/test/CodeGen/DirectX/trunc_error.ll b/llvm/test/CodeGen/DirectX/trunc_error.ll
new file mode 100644
index 00000000000000..751b0b94c280df
--- /dev/null
+++ b/llvm/test/CodeGen/DirectX/trunc_error.ll
@@ -0,0 +1,10 @@
+; RUN: not opt -S -dxil-op-lower %s 2>&1 | FileCheck %s
+
+; DXIL operation trunc does not support double overload type
+; CHECK: LLVM ERROR: Invalid Overload Type
+
+define noundef double @trunc_double(double noundef %a) {
+entry:
+  %elt.trunc = call double @llvm.trunc.f64(double %a)
+  ret double %elt.trunc
+}