[AMDGPU] add support for hostcall buffer pointer as hidden kernel argument

Hostcall is a service that allows a kernel to submit requests to the
host using shared buffers, and block until a response is
received. This will eventually replace the shared buffer currently
used for printf, and repurposes the same hidden kernel argument. This
change introduces a new ValueKind in the HSA metadata to represent the
hostcall buffer.

Differential Revision: https://reviews.llvm.org/D70038

7 files changed, 244 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full-v3.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full-v3.ll
index 72e96a19606..9d34d417e77 100644
--- a/llvm/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full-v3.ll
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full-v3.ll
@@ -42,6 +42,7 @@
 ; CHECK-NEXT:         .size:           8
 ; CHECK-NOT:          .value_kind:     hidden_default_queue
 ; CHECK-NOT:          .value_kind:     hidden_completion_action
+; CHECK-NOT:          .value_kind:     hidden_hostcall_buffer
 ; CHECK-NEXT:         .value_kind:     hidden_printf_buffer
 ; CHECK-NEXT:         .value_type:     i8
 ; CHECK:              .value_kind:     hidden_multigrid_sync_arg
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll
index db1d5c5ec85..f5a47a862d6 100644
--- a/llvm/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll
@@ -49,6 +49,7 @@
 ; CHECK-NEXT:       ValueType:     I64
 ; CHECK-NEXT:     - Size:          8
 ; CHECK-NEXT:       Align:         8
+; CHECK-NOT:        ValueKind:     HiddenHostcallBuffer
 ; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
 ; CHECK-NEXT:       ValueType:     I8
 ; CHECK-NEXT:       AddrSpaceQual: Global
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent-v3.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent-v3.ll
new file mode 100644
index 00000000000..8741bfbc1bb
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent-v3.ll
@@ -0,0 +1,55 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mattr=+code-object-v3 -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mattr=+code-object-v3 -mcpu=gfx900 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s
+
+; CHECK:              ---
+; CHECK:      amdhsa.kernels:
+; CHECK:        - .args:
+; CHECK-NEXT:       - .name:           a
+; CHECK-NEXT:         .offset:         0
+; CHECK-NEXT:         .size:           1
+; CHECK-NEXT:         .type_name:      char
+; CHECK-NEXT:         .value_kind:     by_value
+; CHECK-NEXT:         .value_type:     i8
+; CHECK-NEXT:       - .offset:         8
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_x
+; CHECK-NEXT:         .value_type:     i64
+; CHECK-NEXT:       - .offset:         16
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_y
+; CHECK-NEXT:         .value_type:     i64
+; CHECK-NEXT:       - .offset:         24
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_z
+; CHECK-NEXT:         .value_type:     i64
+
+; CHECK-NOT:          .value_kind:     hidden_hostcall_buffer
+
+; CHECK:          .language:       OpenCL C
+; CHECK-NEXT:     .language_version:
+; CHECK-NEXT:       - 2
+; CHECK-NEXT:       - 0
+; CHECK:          .name:           test_kernel
+; CHECK:          .symbol:         test_kernel.kd
+
+define amdgpu_kernel void @test_kernel(i8 %a) #0
+    !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
+    !kernel_arg_base_type !3 !kernel_arg_type_qual !4 {
+  ret void
+}
+
+; CHECK:  amdhsa.version:
+; CHECK-NEXT: - 1
+; CHECK-NEXT: - 0
+
+attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" }
+
+!1 = !{i32 0}
+!2 = !{!"none"}
+!3 = !{!"char"}
+!4 = !{!""}
+
+!opencl.ocl.version = !{!90}
+!90 = !{i32 2, i32 0}
+
+; PARSER: AMDGPU HSA Metadata Parser Test: PASS
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent.ll
new file mode 100644
index 00000000000..5f1cda0fd21
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent.ll
@@ -0,0 +1,52 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mattr=-code-object-v3 -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mattr=-code-object-v3 -mcpu=gfx900 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s
+
+; CHECK: ---
+; CHECK:  Version: [ 1, 0 ]
+; CHECK:  Kernels:
+
+; CHECK:      - Name:            test_kernel
+; CHECK-NEXT:   SymbolName:      'test_kernel@kd'
+; CHECK-NEXT:   Language:        OpenCL C
+; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
+; CHECK-NEXT:   Args:
+; CHECK-NEXT:     - Name:          a
+; CHECK-NEXT:       TypeName:      char
+; CHECK-NEXT:       Size:          1
+; CHECK-NEXT:       Align:         1
+; CHECK-NEXT:       ValueKind:     ByValue
+; CHECK-NEXT:       ValueType:     I8
+; CHECK-NEXT:       AccQual:       Default
+; CHECK-NEXT:     - Size:          8
+; CHECK-NEXT:       Align:         8
+; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
+; CHECK-NEXT:       ValueType:     I64
+; CHECK-NEXT:     - Size:          8
+; CHECK-NEXT:       Align:         8
+; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
+; CHECK-NEXT:       ValueType:     I64
+; CHECK-NEXT:     - Size:          8
+; CHECK-NEXT:       Align:         8
+; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
+; CHECK-NEXT:       ValueType:     I64
+; CHECK-NOT:        ValueKind:     HiddenHostcallBuffer
+; CHECK-NOT:        ValueKind:     HiddenDefaultQueue
+; CHECK-NOT:        ValueKind:     HiddenCompletionAction
+
+define amdgpu_kernel void @test_kernel(i8 %a) #0
+    !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
+    !kernel_arg_base_type !3 !kernel_arg_type_qual !4 {
+  ret void
+}
+
+attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" }
+
+!1 = !{i32 0}
+!2 = !{!"none"}
+!3 = !{!"char"}
+!4 = !{!""}
+
+!opencl.ocl.version = !{!90}
+!90 = !{i32 2, i32 0}
+
+; PARSER: AMDGPU HSA Metadata Parser Test: PASS
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll
new file mode 100644
index 00000000000..1a75f3661bd
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll
@@ -0,0 +1,59 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mattr=+code-object-v3 -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mattr=+code-object-v3 -mcpu=gfx900 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s
+
+; CHECK:              ---
+; CHECK:      amdhsa.kernels:
+; CHECK:        - .args:
+; CHECK-NEXT:       - .name:           a
+; CHECK-NEXT:         .offset:         0
+; CHECK-NEXT:         .size:           1
+; CHECK-NEXT:         .type_name:      char
+; CHECK-NEXT:         .value_kind:     by_value
+; CHECK-NEXT:         .value_type:     i8
+; CHECK-NEXT:       - .offset:         8
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_x
+; CHECK-NEXT:         .value_type:     i64
+; CHECK-NEXT:       - .offset:         16
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_y
+; CHECK-NEXT:         .value_type:     i64
+; CHECK-NEXT:       - .offset:         24
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_z
+; CHECK-NEXT:         .value_type:     i64
+; CHECK-NEXT:       - .address_space:  global
+; CHECK-NEXT:         .offset:         32
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_hostcall_buffer
+; CHECK-NEXT:         .value_type:     i8
+; CHECK:          .language:       OpenCL C
+; CHECK-NEXT:     .language_version:
+; CHECK-NEXT:       - 2
+; CHECK-NEXT:       - 0
+; CHECK:          .name:           test_kernel
+; CHECK:          .symbol:         test_kernel.kd
+
+declare <2 x i64> @__ockl_hostcall_internal(i8*, i32, i64, i64, i64, i64, i64, i64, i64, i64)
+
+define amdgpu_kernel void @test_kernel(i8 %a) #0
+    !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
+    !kernel_arg_base_type !3 !kernel_arg_type_qual !4 {
+  ret void
+}
+
+; CHECK:  amdhsa.version:
+; CHECK-NEXT: - 1
+; CHECK-NEXT: - 0
+
+attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" }
+
+!1 = !{i32 0}
+!2 = !{!"none"}
+!3 = !{!"char"}
+!4 = !{!""}
+
+!opencl.ocl.version = !{!90}
+!90 = !{i32 2, i32 0}
+
+; PARSER: AMDGPU HSA Metadata Parser Test: PASS
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present.ll
new file mode 100644
index 00000000000..b0428638e25
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present.ll
@@ -0,0 +1,58 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mattr=-code-object-v3 -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mattr=-code-object-v3 -mcpu=gfx900 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s
+
+; CHECK: ---
+; CHECK:  Version: [ 1, 0 ]
+; CHECK:  Kernels:
+
+; CHECK:      - Name:            test_kernel
+; CHECK-NEXT:   SymbolName:      'test_kernel@kd'
+; CHECK-NEXT:   Language:        OpenCL C
+; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
+; CHECK-NEXT:   Args:
+; CHECK-NEXT:     - Name:          a
+; CHECK-NEXT:       TypeName:      char
+; CHECK-NEXT:       Size:          1
+; CHECK-NEXT:       Align:         1
+; CHECK-NEXT:       ValueKind:     ByValue
+; CHECK-NEXT:       ValueType:     I8
+; CHECK-NEXT:       AccQual:       Default
+; CHECK-NEXT:     - Size:          8
+; CHECK-NEXT:       Align:         8
+; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
+; CHECK-NEXT:       ValueType:     I64
+; CHECK-NEXT:     - Size:          8
+; CHECK-NEXT:       Align:         8
+; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
+; CHECK-NEXT:       ValueType:     I64
+; CHECK-NEXT:     - Size:          8
+; CHECK-NEXT:       Align:         8
+; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
+; CHECK-NEXT:       ValueType:     I64
+; CHECK-NEXT:     - Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       HiddenHostcallBuffer
+; CHECK-NEXT:       ValueType:       I8
+; CHECK-NEXT:       AddrSpaceQual:   Global
+; CHECK-NOT:        ValueKind:     HiddenDefaultQueue
+; CHECK-NOT:        ValueKind:     HiddenCompletionAction
+
+declare <2 x i64> @__ockl_hostcall_internal(i8*, i32, i64, i64, i64, i64, i64, i64, i64, i64)
+
+define amdgpu_kernel void @test_kernel(i8 %a) #0
+    !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
+    !kernel_arg_base_type !3 !kernel_arg_type_qual !4 {
+  ret void
+}
+
+attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" }
+
+!1 = !{i32 0}
+!2 = !{!"none"}
+!3 = !{!"char"}
+!4 = !{!""}
+
+!opencl.ocl.version = !{!90}
+!90 = !{i32 2, i32 0}
+
+; PARSER: AMDGPU HSA Metadata Parser Test: PASS
diff --git a/llvm/test/CodeGen/AMDGPU/opencl-printf-no-hostcall.ll b/llvm/test/CodeGen/AMDGPU/opencl-printf-no-hostcall.ll
new file mode 100644
index 00000000000..14c29760e3f
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/opencl-printf-no-hostcall.ll
@@ -0,0 +1,18 @@
+; RUN: not opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-printf-runtime-binding < %s 2>&1 | FileCheck %s
+
+@.str = private unnamed_addr addrspace(2) constant [6 x i8] c"%s:%d\00", align 1
+
+define amdgpu_kernel void @test_kernel(i32 %n) {
+entry:
+  %str = alloca [9 x i8], align 1
+  %arraydecay = getelementptr inbounds [9 x i8], [9 x i8]* %str, i32 0, i32 0
+  %call1 = call i32 (i8 addrspace(2)*, ...) @printf(i8 addrspace(2)* getelementptr inbounds ([6 x i8], [6 x i8] addrspace(2)* @.str, i32 0, i32 0), i8* %arraydecay, i32 %n)
+  %call2 = call <2 x i64> (i8*, i32, i64, i64, i64, i64, i64, i64, i64, i64) @__ockl_hostcall_internal(i8* undef, i32 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9)
+  ret void
+}
+
+declare i32 @printf(i8 addrspace(2)*, ...)
+
+declare <2 x i64> @__ockl_hostcall_internal(i8*, i32, i64, i64, i64, i64, i64, i64, i64, i64)
+
+; CHECK: error: Cannot use both printf and hostcall in the same module