Fix Vulkan Build, add tanh to llvm instrinsic, fix halideIR (#868)

* Fix Vulkan Build, add tanh to llvm instrinsic, fix halideIR

* fix llvm tanh

HalideIR @ e20e5e9a

-Subproject commit 87b089a0ba20f2e8257038ee9211d6816088ce95
+Subproject commit e20e5e9abb3aa43147a90a4ffb3e190f62862970

Jenkinsfile

@@ -107,6 +107,7 @@ stage('Build') {
         sh """
            echo USE_ROCM=1 >> config.mk
            echo ROCM_PATH=/opt/rocm >> config.mk
+           echo USE_VULKAN=1 >> config.mk
            """
         make('gpu', '-j2')
       }

src/codegen/llvm/intrin_rule_llvm.cc

@@ -25,6 +25,27 @@ TVM_REGISTER_GLOBAL("tvm.intrin.rule.llvm.log")
 TVM_REGISTER_GLOBAL("tvm.intrin.rule.llvm.sqrt")
 .set_body(DispatchLLVMPureIntrin<::llvm::Intrinsic::sqrt, 1>);
 
+TVM_REGISTER_GLOBAL("tvm.intrin.rule.llvm.tanh")
+.set_body([](const TVMArgs& targs, TVMRetValue* rv) {
+  Expr e = targs[0];
+  const ir::Call* call = e.as<ir::Call>();
+  CHECK(call != nullptr);
+  const Expr& x = call->args[0];
+  Expr one = make_const(x.type(), 1);
+  Expr two = make_const(x.type(), 2);
+  Expr neg_two = make_const(x.type(), -2);
+
+  Expr exp_neg2x = ir::Call::make(
+      x.type(), "exp", {neg_two * x}, ir::Call::PureIntrinsic);
+  Expr exp_pos2x = ir::Call::make(
+      x.type(), "exp", {two * x}, ir::Call::PureIntrinsic);
+
+  Expr tanh_pos = (one - exp_neg2x) / (one + exp_neg2x);
+  Expr tanh_neg = (exp_pos2x - one) / (exp_pos2x + one);
+  *rv = ir::Select::make(
+      x >= make_zero(x.type()), tanh_pos, tanh_neg);
+});
+
 TVM_REGISTER_GLOBAL("tvm.intrin.rule.llvm.pow")
 .set_body(DispatchLLVMPureIntrin<::llvm::Intrinsic::pow, 1>);
 

src/codegen/spirv/ir_builder.cc

@@ -311,8 +311,8 @@ Value IRBuilder::GetConst_(const SType& dtype, const uint64_t* pvalue) {
   }
   CHECK_LE(dtype.type.bits(), 64);
   Value ret = NewValue(dtype, kConstant);
-  if (1 == dtype.type.bits() && dtype.is_uint()) {
-    // Boolean types.
+  if (dtype.type == UInt(1)) {
+    // bool types.
     if (*pvalue) {
       ib_.Begin(spv::OpConstantTrue).AddSeq(ret);
     } else {

tests/ci_build/Dockerfile.gpu

@@ -43,6 +43,11 @@ RUN bash /install/ubuntu_install_opengl.sh
 # Enable doxygen for c++ doc build
 RUN apt-get install -y doxygen graphviz
 
+# Install vulkan
+COPY install/ubuntu_install_vulkan.sh /install/ubuntu_install_vulkan.sh
+RUN bash /install/ubuntu_install_vulkan.sh
+
+
 # Environment variables
 ENV PATH=/node_modules/.bin:${PATH}
 ENV PATH=/usr/local/nvidia/bin:${PATH}
@@ -53,3 +58,10 @@ ENV C_INCLUDE_PATH=/usr/local/cuda/include:${C_INCLUDE_PATH}
 ENV LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib64:${LIBRARY_PATH}
 ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib64:${LD_LIBRARY_PATH}
 ENV LD_LIBRARY_PATH=/opt/rocm/lib:${LD_LIBRARY_PATH}
+
+ENV PATH=/node_modules/.bin:${PATH}
+
+ENV VULKAN_SDK=/usr/local/VulkanSDK/1.0.65.0/x86_64
+ENV PATH=${PATH}:${VULKAN_SDK}/bin
+ENV LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:${VULKAN_SDK}/lib
+ENV VK_LAYER_PATH=${VULKAN_SDK}/etc/explicit_layer.d

tests/ci_build/install/ubuntu_install_vulkan.sh

+#/bin/bash
+
+wget https://sdk.lunarg.com/sdk/download/1.0.65.0/linux/vulkansdk-linux-x86_64-1.0.65.0.run
+
+bash vulkansdk-linux-x86_64-1.0.65.0.run
+mv VulkanSDK /usr/local/VulkanSDK
+cd /usr/local/VulkanSDK/1.0.65.0
+./build_tools.sh
+./build_samples.sh

topi/tests/python/test_topi_math.py

@@ -15,16 +15,38 @@ def test_ewise():
     l = tvm.var('l')
     A = tvm.placeholder((m, l), name='A')
 
-    def test_apply(func, name):
+    shape = (20, 3)
+
+    def test_apply(func, name, f_numpy):
         B = func(A)
         assert tuple(B.shape) == tuple(A.shape)
         assert B.op.body[0].name == name
+        a_np = np.random.uniform(size=shape).astype(A.dtype)
+        a_np = np.abs(a_np)
+        b_np = f_numpy(a_np)
+
+        def check_device(device):
+            ctx = tvm.context(device, 0)
+            if not ctx.exist:
+                print("Skip because %s is not enabled" % device)
+                return
+            print("Running on target: %s" % device)
+            with tvm.target.create(device):
+                s = topi.generic.schedule_injective(B)
+            a = tvm.nd.array(a_np, ctx)
+            b = tvm.nd.array(np.zeros_like(b_np), ctx)
+            foo = tvm.build(s, [A, B], device, name=name)
+            foo(a, b)
+            np.testing.assert_allclose(b.asnumpy(), b_np, rtol=1e-5)
+
+        for device in ['cuda', 'opencl', 'metal', 'rocm', 'vulkan', 'llvm']:
+            check_device(device)
 
-    test_apply(topi.exp, "exp")
-    test_apply(topi.tanh, "tanh")
-    test_apply(topi.sigmoid, "sigmoid")
-    test_apply(topi.log, "log")
-    test_apply(topi.sqrt, "sqrt")
+    test_apply(topi.exp, "exp", np.exp)
+    test_apply(topi.tanh, "tanh", np.tanh)
+    test_apply(topi.sigmoid, "sigmoid", lambda x:1/(1+np.exp(-x)))
+    test_apply(topi.log, "log", np.log)
+    test_apply(topi.sqrt, "sqrt", np.sqrt)
 
 if __name__ == "__main__":
     test_util()