arsenm created this revision.
arsenm added a reviewer: rampitec.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, 
jvesely, kzhuravl.

This wasn't setting some of the features from older generations.


https://reviews.llvm.org/D63649

Files:
  lib/Basic/Targets/AMDGPU.cpp
  test/CodeGenOpenCL/amdgpu-features.cl
  test/CodeGenOpenCL/builtins-amdgcn-ci.cl
  test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err-clamp.cl
  test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
  test/CodeGenOpenCL/builtins-amdgcn-dl-insts.cl
  test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
  test/CodeGenOpenCL/builtins-amdgcn-vi.cl

Index: test/CodeGenOpenCL/builtins-amdgcn-vi.cl
===================================================================
--- test/CodeGenOpenCL/builtins-amdgcn-vi.cl
+++ test/CodeGenOpenCL/builtins-amdgcn-vi.cl
@@ -1,5 +1,8 @@
 // REQUIRES: amdgpu-registered-target
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu tonga -S -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -S -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1012 -S -emit-llvm -o - %s | FileCheck %s
 
 #pragma OPENCL EXTENSION cl_khr_fp16 : enable
 
Index: test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
===================================================================
--- test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
+++ test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
@@ -1,5 +1,6 @@
 // REQUIRES: amdgpu-registered-target
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -S -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck %s
 
 #pragma OPENCL EXTENSION cl_khr_fp16 : enable
 
Index: test/CodeGenOpenCL/builtins-amdgcn-dl-insts.cl
===================================================================
--- test/CodeGenOpenCL/builtins-amdgcn-dl-insts.cl
+++ test/CodeGenOpenCL/builtins-amdgcn-dl-insts.cl
@@ -1,6 +1,8 @@
 // REQUIRES: amdgpu-registered-target
 
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx906 -S -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1011 -S -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1012 -S -emit-llvm -o - %s | FileCheck %s
 
 typedef unsigned int uint;
 typedef half __attribute__((ext_vector_type(2))) half2;
Index: test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
===================================================================
--- test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
+++ test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
@@ -1,6 +1,7 @@
 // REQUIRES: amdgpu-registered-target
 
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -verify -S -emit-llvm -o - %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -verify -S -emit-llvm -o - %s
 
 typedef unsigned int uint;
 typedef half __attribute__((ext_vector_type(2))) half2;
Index: test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err-clamp.cl
===================================================================
--- test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err-clamp.cl
+++ test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err-clamp.cl
@@ -1,6 +1,7 @@
 // REQUIRES: amdgpu-registered-target
 
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx906 -verify -S -emit-llvm -o - %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -verify -S -emit-llvm -o - %s
 
 typedef unsigned int uint;
 typedef half __attribute__((ext_vector_type(2))) half2;
Index: test/CodeGenOpenCL/builtins-amdgcn-ci.cl
===================================================================
--- test/CodeGenOpenCL/builtins-amdgcn-ci.cl
+++ test/CodeGenOpenCL/builtins-amdgcn-ci.cl
@@ -2,6 +2,7 @@
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu hawaii -S -emit-llvm -o - %s | FileCheck %s
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu fiji -S -emit-llvm -o - %s | FileCheck %s
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx906 -S -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck %s
 
 typedef unsigned int uint;
 
Index: test/CodeGenOpenCL/amdgpu-features.cl
===================================================================
--- test/CodeGenOpenCL/amdgpu-features.cl
+++ test/CodeGenOpenCL/amdgpu-features.cl
@@ -15,9 +15,9 @@
 
 // GFX904: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+gfx9-insts,+s-memrealtime"
 // GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+gfx9-insts,+s-memrealtime"
-// GFX1010: "target-features"="+16-bit-insts,+dl-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx9-insts,+s-memrealtime"
-// GFX1011: "target-features"="+16-bit-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx9-insts,+s-memrealtime"
-// GFX1012: "target-features"="+16-bit-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx9-insts,+s-memrealtime"
+// GFX1010: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
+// GFX1011: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
+// GFX1012: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
 // GFX801: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+s-memrealtime"
 // GFX700: "target-features"="+ci-insts,+fp64-fp16-denormals,-fp32-denormals"
 // GFX600: "target-features"="+fp64-fp16-denormals,-fp32-denormals"
Index: lib/Basic/Targets/AMDGPU.cpp
===================================================================
--- lib/Basic/Targets/AMDGPU.cpp
+++ lib/Basic/Targets/AMDGPU.cpp
@@ -144,8 +144,10 @@
       LLVM_FALLTHROUGH;
     case GK_GFX1010:
       Features["dl-insts"] = true;
+      Features["ci-insts"] = true;
       Features["16-bit-insts"] = true;
       Features["dpp"] = true;
+      Features["gfx8-insts"] = true;
       Features["gfx9-insts"] = true;
       Features["gfx10-insts"] = true;
       Features["s-memrealtime"] = true;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
  • [PATCH] D63649: AMDG... Matt Arsenault via Phabricator via cfe-commits

Reply via email to