[AMDGPU] Add perf hints to functions
This is adoption of HSAIL perfhint pass. Two types of hints are produced:
1. Function is memory bound.
2. Kernel can use wave limiter.
Currently these hints are used in the scheduler. If a function is suspected
to be memory bound we allow occupancy to decrease to 4 waves in the course
of scheduling.
Differential Revision: https://reviews.llvm.org/D46992
llvm-svn: 333289
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-kernel-code-props.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-kernel-code-props.ll
index f4a914a..379dd33 100644
--- a/llvm/test/CodeGen/AMDGPU/hsa-metadata-kernel-code-props.ll
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-kernel-code-props.ll
@@ -1,6 +1,6 @@
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX700 --check-prefix=NOTES %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX803 --check-prefix=NOTES %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX900 --check-prefix=NOTES %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -enable-misched=0 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX700 --check-prefix=NOTES %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -enable-misched=0 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX803 --check-prefix=NOTES %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-misched=0 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX900 --check-prefix=NOTES %s
@var = addrspace(1) global float 0.0
@@ -17,9 +17,7 @@
; CHECK: KernargSegmentAlign: 8
; CHECK: WavefrontSize: 64
; CHECK: NumSGPRs: 6
-; GFX700: NumVGPRs: 4
-; GFX803: NumVGPRs: 6
-; GFX900: NumVGPRs: 6
+; CHECK: NumVGPRs: 3
; CHECK: MaxFlatWorkGroupSize: 256
define amdgpu_kernel void @test(
half addrspace(1)* %r,