Preliminary support for inplace ops. (#1921)

* Preliminary support for inplace ops.

* Add a test.

candle-core/src/custom_op.rs

@@ -242,3 +242,136 @@ impl Tensor {
         self.apply_op3_arc(t2, t3, Arc::new(Box::new(c)))
     }
 }
+
+// In place ops.
+
+/// Unary ops that can be defined in user-land.
+/// These ops work in place and as such back-prop is unsupported.
+pub trait InplaceOp1 {
+    // Box<dyn> does not support const yet, so use a function to get the name.
+    fn name(&self) -> &'static str;
+
+    /// The forward pass, as run on a cpu device. Note that the storage can use arbitrary strides,
+    /// offsets etc so the associated layout should be used to access it.
+    fn cpu_fwd(&self, storage: &mut CpuStorage, layout: &Layout) -> Result<()>;
+
+    /// The forward pass, as run on a gpu device. Note that the storage can use arbitrary strides,
+    /// offsets etc so the associated layout should be used to access it.
+    fn cuda_fwd(&self, _storage: &mut CudaStorage, _layout: &Layout) -> Result<()> {
+        Err(crate::Error::Cuda(
+            format!("no cuda implementation for {}", self.name()).into(),
+        ))
+    }
+
+    /// The forward pass, as run on a metal gpu device. Note that the storage can use arbitrary strides,
+    /// offsets etc so the associated layout should be used to access it.
+    fn metal_fwd(&self, _storage: &mut MetalStorage, _layout: &Layout) -> Result<()> {
+        Err(crate::Error::Metal(
+            format!("no metal implementation for {}", self.name()).into(),
+        ))
+    }
+}
+
+pub trait InplaceOp2 {
+    fn name(&self) -> &'static str;
+
+    /// The forward pass, as run on a cpu device. Note that the storage can use arbitrary strides,
+    /// offsets etc so the associated layout should be used to access it.
+    fn cpu_fwd(&self, s1: &mut CpuStorage, l1: &Layout, s2: &CpuStorage, l2: &Layout)
+        -> Result<()>;
+
+    /// The forward pass, as run on a gpu device. Note that the storage can use arbitrary strides,
+    /// offsets etc so the associated layout should be used to access it.
+    fn cuda_fwd(&self, _: &mut CudaStorage, _: &Layout, _: &CudaStorage, _: &Layout) -> Result<()> {
+        Err(crate::Error::Cuda(
+            format!("no cuda implementation for {}", self.name()).into(),
+        ))
+    }
+
+    /// The forward pass, as run on a metal gpu device. Note that the storage can use arbitrary strides,
+    /// offsets etc so the associated layout should be used to access it.
+    fn metal_fwd(
+        &self,
+        _: &mut MetalStorage,
+        _: &Layout,
+        _: &MetalStorage,
+        _: &Layout,
+    ) -> Result<()> {
+        Err(crate::Error::Metal(
+            format!("no metal implementation for {}", self.name()).into(),
+        ))
+    }
+}
+
+pub trait InplaceOp3 {
+    fn name(&self) -> &'static str;
+
+    /// The forward pass, as run on a cpu device. Note that the storage can use arbitrary strides,
+    /// offsets etc so the associated layout should be used to access it.
+    fn cpu_fwd(
+        &self,
+        s1: &mut CpuStorage,
+        l1: &Layout,
+        s2: &CpuStorage,
+        l2: &Layout,
+        s3: &CpuStorage,
+        l3: &Layout,
+    ) -> Result<()>;
+
+    /// The forward pass, as run on a gpu device. Note that the storage can use arbitrary strides,
+    /// offsets etc so the associated layout should be used to access it.
+    fn cuda_fwd(
+        &self,
+        _: &mut CudaStorage,
+        _: &Layout,
+        _: &CudaStorage,
+        _: &Layout,
+        _: &CudaStorage,
+        _: &Layout,
+    ) -> Result<()> {
+        Err(crate::Error::Cuda(
+            format!("no cuda implementation for {}", self.name()).into(),
+        ))
+    }
+
+    /// The forward pass, as run on a metal gpu device. Note that the storage can use arbitrary strides,
+    /// offsets etc so the associated layout should be used to access it.
+    fn metal_fwd(
+        &self,
+        _: &mut MetalStorage,
+        _: &Layout,
+        _: &MetalStorage,
+        _: &Layout,
+        _: &MetalStorage,
+        _: &Layout,
+    ) -> Result<()> {
+        Err(crate::Error::Metal(
+            format!("no metal implementation for {}", self.name()).into(),
+        ))
+    }
+}
+
+impl Tensor {
+    /// Applies a unary custom op in place.
+    pub fn inplace_op1<C: InplaceOp1>(&self, c: &C) -> Result<()> {
+        self.storage_mut().inplace_op1(self.layout(), c)
+    }
+
+    /// Applies a unary custom op in place (for the first tensor).
+    pub fn inplace_op2<C: InplaceOp2>(&self, rhs: &Self, c: &C) -> Result<()> {
+        self.storage_mut()
+            .inplace_op2(self.layout(), &rhs.storage(), rhs.layout(), c)
+    }
+
+    /// Applies a ternary custom op in place (for the first tensor).
+    pub fn inplace_op3<C: InplaceOp3>(&self, t2: &Self, t3: &Self, c: &C) -> Result<()> {
+        self.storage_mut().inplace_op3(
+            self.layout(),
+            &t2.storage(),
+            t2.layout(),
+            &t3.storage(),
+            t3.layout(),
+            c,
+        )
+    }
+}

candle-core/src/lib.rs

@@ -74,7 +74,7 @@ pub mod utils;
 mod variable;
 
 pub use cpu_backend::CpuStorage;
-pub use custom_op::{CustomOp1, CustomOp2, CustomOp3};
+pub use custom_op::{CustomOp1, CustomOp2, CustomOp3, InplaceOp1, InplaceOp2, InplaceOp3};
 pub use device::{Device, DeviceLocation, NdArray};
 pub use dtype::{DType, FloatDType, IntDType, WithDType};
 pub use error::{Error, Result};

candle-core/src/storage.rs

@@ -1,7 +1,7 @@
 use crate::backend::BackendStorage;
 use crate::op::{self, CmpOp, ReduceOp};
 use crate::{CpuStorage, CudaStorage, DType, Device, Error, Layout, MetalStorage, Result, Shape};
-use crate::{CustomOp1, CustomOp2, CustomOp3};
+use crate::{CustomOp1, CustomOp2, CustomOp3, InplaceOp1, InplaceOp2, InplaceOp3};
 
 // We do not want to implement Clone on Storage as cloning may fail because of
 // out of memory. Instead try_clone should be used.
@@ -253,6 +253,51 @@ impl Storage {
         }
     }
 
+    pub(crate) fn inplace_op1(&mut self, l: &Layout, c: &dyn InplaceOp1) -> Result<()> {
+        match self {
+            Self::Cpu(storage) => c.cpu_fwd(storage, l),
+            Self::Cuda(storage) => c.cuda_fwd(storage, l),
+            Self::Metal(storage) => c.metal_fwd(storage, l),
+        }
+    }
+
+    pub(crate) fn inplace_op2(
+        &mut self,
+        l1: &Layout,
+        t2: &Self,
+        l2: &Layout,
+        c: &dyn InplaceOp2,
+    ) -> Result<()> {
+        self.same_device(t2, c.name())?;
+        match (self, t2) {
+            (Self::Cpu(s1), Self::Cpu(s2)) => c.cpu_fwd(s1, l1, s2, l2),
+            (Self::Cuda(s1), Self::Cuda(s2)) => c.cuda_fwd(s1, l1, s2, l2),
+            (Self::Metal(s1), Self::Metal(s2)) => c.metal_fwd(s1, l1, s2, l2),
+            _ => unreachable!(),
+        }
+    }
+
+    pub(crate) fn inplace_op3(
+        &mut self,
+        l1: &Layout,
+        t2: &Self,
+        l2: &Layout,
+        t3: &Self,
+        l3: &Layout,
+        c: &dyn InplaceOp3,
+    ) -> Result<()> {
+        self.same_device(t2, c.name())?;
+        self.same_device(t3, c.name())?;
+        match (self, t2, t3) {
+            (Self::Cpu(s1), Self::Cpu(s2), Self::Cpu(s3)) => c.cpu_fwd(s1, l1, s2, l2, s3, l3),
+            (Self::Cuda(s1), Self::Cuda(s2), Self::Cuda(s3)) => c.cuda_fwd(s1, l1, s2, l2, s3, l3),
+            (Self::Metal(s1), Self::Metal(s2), Self::Metal(s3)) => {
+                c.metal_fwd(s1, l1, s2, l2, s3, l3)
+            }
+            _ => unreachable!(),
+        }
+    }
+
     pub(crate) fn unary_impl<B: op::UnaryOpT>(&self, layout: &Layout) -> Result<Self> {
         match self {
             Storage::Cpu(storage) => {

candle-core/src/tensor.rs

@@ -2254,6 +2254,10 @@ impl Tensor {
         self.storage.read().unwrap()
     }
 
+    pub(crate) fn storage_mut(&self) -> std::sync::RwLockWriteGuard<'_, Storage> {
+        self.storage.write().unwrap()
+    }
+
     // If we extend the visibility of this function to be usable outside of this crate, we should
     // make it unsafe.
     pub(crate) fn storage_mut_and_layout(

candle-core/tests/custom_op_tests.rs

@@ -112,3 +112,34 @@ fn custom_op1_with_backward() -> Result<()> {
 
     Ok(())
 }
+
+impl candle_core::InplaceOp1 for Elu {
+    fn name(&self) -> &'static str {
+        "elu"
+    }
+
+    fn cpu_fwd(&self, s: &mut CpuStorage, _l: &Layout) -> Result<()> {
+        let alpha = self.alpha;
+        match s {
+            CpuStorage::BF16(s) => s.iter_mut().for_each(|v| *v = fwd(*v, alpha)),
+            CpuStorage::F16(s) => s.iter_mut().for_each(|v| *v = fwd(*v, alpha)),
+            CpuStorage::F32(s) => s.iter_mut().for_each(|v| *v = fwd(*v, alpha)),
+            CpuStorage::F64(s) => s.iter_mut().for_each(|v| *v = fwd(*v, alpha)),
+            _ => candle_core::bail!("unsupported dtype for inplace elu"),
+        }
+        Ok(())
+    }
+}
+
+#[test]
+fn inplace_op1() -> Result<()> {
+    let cpu = &Device::Cpu;
+    let t = Tensor::arange(0u32, 12u32, cpu)?.to_dtype(DType::F32)?;
+    let t = (t - 5.)?;
+    t.inplace_op1(&Elu { alpha: 1. })?;
+    assert_eq!(
+        to_vec1_round(&t, 4)?,
+        &[-0.9933, -0.9817, -0.9502, -0.8647, -0.6321, 0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0]
+    );
+    Ok(())
+}