diff --git a/clang/include/clang/Basic/BuiltinsAMDGPU.def b/clang/include/clang/Basic/BuiltinsAMDGPU.def index bb3953ea1253d..fced35aa6bc4b 100644 --- a/clang/include/clang/Basic/BuiltinsAMDGPU.def +++ b/clang/include/clang/Basic/BuiltinsAMDGPU.def @@ -163,6 +163,13 @@ BUILTIN(__builtin_amdgcn_raw_buffer_load_b64, "V2UiQbiiIi", "n") BUILTIN(__builtin_amdgcn_raw_buffer_load_b96, "V3UiQbiiIi", "n") BUILTIN(__builtin_amdgcn_raw_buffer_load_b128, "V4UiQbiiIi", "n") +BUILTIN(__builtin_amdgcn_raw_ptr_buffer_atomic_add_i32, "iiQbiiIi", "t") +TARGET_BUILTIN(__builtin_amdgcn_raw_ptr_buffer_atomic_fadd_f32, "ffQbiiIi", "t", "atomic-fadd-rtn-insts") +TARGET_BUILTIN(__builtin_amdgcn_raw_ptr_buffer_atomic_fadd_v2f16, "V2hV2hQbiiIi", "t", "atomic-buffer-global-pk-add-f16-insts") + +TARGET_BUILTIN(__builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f32, "ffQbiiIi", "t", "atomic-fmin-fmax-global-f32") +TARGET_BUILTIN(__builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f64, "ddQbiiIi", "t", "atomic-fmin-fmax-global-f64") + TARGET_BUILTIN(__builtin_amdgcn_raw_ptr_buffer_load_lds, "vQbv*3IUiiiIiIi", "t", "vmem-to-lds-load-insts") TARGET_BUILTIN(__builtin_amdgcn_struct_ptr_buffer_load_lds, "vQbv*3IUiiiiIiIi", "t", "vmem-to-lds-load-insts") diff --git a/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp b/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp index 70f510ae52ed6..281162f4b2ecf 100644 --- a/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp +++ b/clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp @@ -1487,6 +1487,17 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID, F, {EmitScalarExpr(E->getArg(0)), EmitScalarExpr(E->getArg(1)), EmitScalarExpr(E->getArg(2)), EmitScalarExpr(E->getArg(3))}); } + case AMDGPU::BI__builtin_amdgcn_raw_ptr_buffer_atomic_add_i32: + return emitBuiltinWithOneOverloadedType<5>( + *this, E, Intrinsic::amdgcn_raw_ptr_buffer_atomic_add); + case AMDGPU::BI__builtin_amdgcn_raw_ptr_buffer_atomic_fadd_f32: + case AMDGPU::BI__builtin_amdgcn_raw_ptr_buffer_atomic_fadd_v2f16: + return emitBuiltinWithOneOverloadedType<5>( + *this, E, Intrinsic::amdgcn_raw_ptr_buffer_atomic_fadd); + case AMDGPU::BI__builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f32: + case AMDGPU::BI__builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f64: + return emitBuiltinWithOneOverloadedType<5>( + *this, E, Intrinsic::amdgcn_raw_ptr_buffer_atomic_fmax); case AMDGPU::BI__builtin_amdgcn_s_prefetch_data: return emitBuiltinWithOneOverloadedType<2>( *this, E, Intrinsic::amdgcn_s_prefetch_data); diff --git a/clang/test/CodeGen/link-builtin-bitcode.c b/clang/test/CodeGen/link-builtin-bitcode.c index 963a3956ff808..9a5b6de3c3b38 100644 --- a/clang/test/CodeGen/link-builtin-bitcode.c +++ b/clang/test/CodeGen/link-builtin-bitcode.c @@ -43,7 +43,7 @@ int bar() { return no_attr() + attr_in_target() + attr_not_in_target() + attr_in // CHECK-LABEL: @attr_incompatible // CHECK-SAME: () #[[ATTR_INCOMPATIBLE:[0-9]+]] { -// CHECK: attributes #[[ATTR_BAR]] = { {{.*}} "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" } -// CHECK: attributes #[[ATTR_COMPATIBLE]] = { {{.*}} "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gws,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+vmem-to-lds-load-insts,+wavefrontsize64" } -// CHECK: attributes #[[ATTR_EXTEND]] = { {{.*}} "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+extended-image-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gws,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+vmem-to-lds-load-insts,+wavefrontsize64" } -// CHECK: attributes #[[ATTR_INCOMPATIBLE]] = { {{.*}} "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx90a-insts,+gws,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+vmem-to-lds-load-insts,+wavefrontsize64,-gfx9-insts" } +// CHECK: attributes #[[ATTR_BAR]] = { {{.*}} "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" } +// CHECK: attributes #[[ATTR_COMPATIBLE]] = { {{.*}} "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gws,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+vmem-to-lds-load-insts,+wavefrontsize64" } +// CHECK: attributes #[[ATTR_EXTEND]] = { {{.*}} "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+extended-image-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gws,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+vmem-to-lds-load-insts,+wavefrontsize64" } +// CHECK: attributes #[[ATTR_INCOMPATIBLE]] = { {{.*}} "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx90a-insts,+gws,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+vmem-to-lds-load-insts,+wavefrontsize64,-gfx9-insts" } diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl index df71ead39f48c..db8bc976a52ba 100644 --- a/clang/test/CodeGenOpenCL/amdgpu-features.cl +++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl @@ -82,34 +82,34 @@ // GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" // GFX908: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" // GFX909: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX90A: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX90A: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" // GFX90C: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX942: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+fp8-conversion-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,+xf32-insts" -// GFX9_4_Generic: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX950: "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+bf8-cvt-scale-insts,+bitop3-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot12-insts,+dot13-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+f16bf16-to-fp6bf6-cvt-scale-insts,+f32-to-f16bf16-cvt-sr-insts,+fp4-cvt-scale-insts,+fp6bf6-cvt-scale-insts,+fp8-conversion-insts,+fp8-cvt-scale-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+gfx950-insts,+mai-insts,+permlane16-swap,+permlane32-swap,+prng-inst,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX1010: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1011: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1012: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1013: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1030: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1031: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1032: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1033: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1034: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1035: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1036: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1100: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1101: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1102: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1103: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1150: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1151: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1152: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1153: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1201: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1250: "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+bf16-cvt-insts,+bf16-trans-insts,+bitop3-insts,+ci-insts,+dl-insts,+dot7-insts,+dot8-insts,+dpp,+fp8-conversion-insts,+fp8e5m3-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx1250-insts,+gfx8-insts,+gfx9-insts,+permlane16-swap,+prng-inst,+setprio-inc-wg-inst,+tanh-insts,+transpose-load-f4f6-insts,+vmem-pref-insts,+wavefrontsize32" +// GFX942: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+fp8-conversion-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,+xf32-insts" +// GFX9_4_Generic: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX950: "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+bf8-cvt-scale-insts,+bitop3-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot12-insts,+dot13-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+f16bf16-to-fp6bf6-cvt-scale-insts,+f32-to-f16bf16-cvt-sr-insts,+fp4-cvt-scale-insts,+fp6bf6-cvt-scale-insts,+fp8-conversion-insts,+fp8-cvt-scale-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+gfx950-insts,+mai-insts,+permlane16-swap,+permlane32-swap,+prng-inst,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX1010: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1011: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1012: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1013: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1030: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1031: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1032: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1033: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1034: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1035: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1036: "target-features"="+16-bit-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1100: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1101: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1102: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1103: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1150: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1151: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1152: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1153: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1201: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1250: "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+bf16-cvt-insts,+bf16-trans-insts,+bitop3-insts,+ci-insts,+dl-insts,+dot7-insts,+dot8-insts,+dpp,+fp8-conversion-insts,+fp8e5m3-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx1250-insts,+gfx8-insts,+gfx9-insts,+permlane16-swap,+prng-inst,+setprio-inc-wg-inst,+tanh-insts,+transpose-load-f4f6-insts,+vmem-pref-insts,+wavefrontsize32" -// GFX1103-W64: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize64" +// GFX1103-W64: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize64" kernel void test() {} diff --git a/clang/test/CodeGenOpenCL/amdgpu-readonly-features-written-with-no-target.cl b/clang/test/CodeGenOpenCL/amdgpu-readonly-features-written-with-no-target.cl index 1542efa14efb9..1a0a30ca0b51e 100644 --- a/clang/test/CodeGenOpenCL/amdgpu-readonly-features-written-with-no-target.cl +++ b/clang/test/CodeGenOpenCL/amdgpu-readonly-features-written-with-no-target.cl @@ -11,6 +11,6 @@ __attribute__((target("gws,image-insts,vmem-to-lds-load-insts"))) void test() {} // NOCPU: "target-features"="+gws,+image-insts,+vmem-to-lds-load-insts" -// GFX942: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+fp8-conversion-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,+xf32-insts" -// GFX1100: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" -// GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX942: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+fp8-conversion-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,+xf32-insts" +// GFX1100: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32" +// GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32 diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-raw-buffer-atomic-add.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn-raw-buffer-atomic-add.cl new file mode 100644 index 0000000000000..689046ace4479 --- /dev/null +++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-raw-buffer-atomic-add.cl @@ -0,0 +1,38 @@ +// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5 +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx90a -emit-llvm -o - %s | FileCheck %s +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx942 -emit-llvm -o - %s | FileCheck %s +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx950 -emit-llvm -o - %s | FileCheck %s + +// REQUIRES: amdgpu-registered-target + +typedef half __attribute__((ext_vector_type(2))) float16x2_t; + +// CHECK-LABEL: define dso_local i32 @test_atomic_add_i32( +// CHECK-SAME: ptr addrspace(8) captures(none) [[RSRC:%.*]], i32 noundef [[X:%.*]], i32 noundef [[OFFSET:%.*]], i32 noundef [[SOFFSET:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[TMP0:%.*]] = tail call i32 @llvm.amdgcn.raw.ptr.buffer.atomic.add.i32(i32 [[X]], ptr addrspace(8) [[RSRC]], i32 [[OFFSET]], i32 [[SOFFSET]], i32 0) +// CHECK-NEXT: ret i32 [[TMP0]] +// +int test_atomic_add_i32(__amdgpu_buffer_rsrc_t rsrc, int x, int offset, int soffset) { + return __builtin_amdgcn_raw_ptr_buffer_atomic_add_i32(x, rsrc, offset, soffset, 0); +} + +// CHECK-LABEL: define dso_local float @test_atomic_fadd_f32( +// CHECK-SAME: ptr addrspace(8) captures(none) [[RSRC:%.*]], float noundef [[X:%.*]], i32 noundef [[OFFSET:%.*]], i32 noundef [[SOFFSET:%.*]]) local_unnamed_addr #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[TMP0:%.*]] = tail call float @llvm.amdgcn.raw.ptr.buffer.atomic.fadd.f32(float [[X]], ptr addrspace(8) [[RSRC]], i32 [[OFFSET]], i32 [[SOFFSET]], i32 0) +// CHECK-NEXT: ret float [[TMP0]] +// +float test_atomic_fadd_f32(__amdgpu_buffer_rsrc_t rsrc, float x, int offset, int soffset) { + return __builtin_amdgcn_raw_ptr_buffer_atomic_fadd_f32(x, rsrc, offset, soffset, 0); +} + +// CHECK-LABEL: define dso_local <2 x half> @test_atomic_fadd_v2f16( +// CHECK-SAME: ptr addrspace(8) captures(none) [[RSRC:%.*]], <2 x half> noundef [[X:%.*]], i32 noundef [[OFFSET:%.*]], i32 noundef [[SOFFSET:%.*]]) local_unnamed_addr #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[TMP0:%.*]] = tail call <2 x half> @llvm.amdgcn.raw.ptr.buffer.atomic.fadd.v2f16(<2 x half> [[X]], ptr addrspace(8) [[RSRC]], i32 [[OFFSET]], i32 [[SOFFSET]], i32 0) +// CHECK-NEXT: ret <2 x half> [[TMP0]] +// +float16x2_t test_atomic_fadd_v2f16(__amdgpu_buffer_rsrc_t rsrc, float16x2_t x, int offset, int soffset) { + return __builtin_amdgcn_raw_ptr_buffer_atomic_fadd_v2f16(x, rsrc, offset, soffset, 0); +} diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-raw-buffer-atomic-max.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn-raw-buffer-atomic-max.cl new file mode 100644 index 0000000000000..5cfb099bf8acc --- /dev/null +++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-raw-buffer-atomic-max.cl @@ -0,0 +1,25 @@ +// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5 +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx10-1-generic -emit-llvm -o - %s | FileCheck %s +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx10-3-generic -emit-llvm -o - %s | FileCheck %s +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1250 -emit-llvm -o - %s | FileCheck %s +// REQUIRES: amdgpu-registered-target + +// CHECK-LABEL: define dso_local float @test_atomic_fmax_f32( +// CHECK-SAME: ptr addrspace(8) captures(none) [[RSRC:%.*]], float noundef [[X:%.*]], i32 noundef [[OFFSET:%.*]], i32 noundef [[SOFFSET:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[TMP0:%.*]] = tail call float @llvm.amdgcn.raw.ptr.buffer.atomic.fmax.f32(float [[X]], ptr addrspace(8) [[RSRC]], i32 [[OFFSET]], i32 [[SOFFSET]], i32 0) +// CHECK-NEXT: ret float [[TMP0]] +// +float test_atomic_fmax_f32(__amdgpu_buffer_rsrc_t rsrc, float x, int offset, int soffset) { + return __builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f32(x, rsrc, offset, soffset, 0); +} + +// CHECK-LABEL: define dso_local double @test_atomic_fmax_f64( +// CHECK-SAME: ptr addrspace(8) captures(none) [[RSRC:%.*]], double noundef [[X:%.*]], i32 noundef [[OFFSET:%.*]], i32 noundef [[SOFFSET:%.*]]) local_unnamed_addr #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[TMP0:%.*]] = tail call double @llvm.amdgcn.raw.ptr.buffer.atomic.fmax.f64(double [[X]], ptr addrspace(8) [[RSRC]], i32 [[OFFSET]], i32 [[SOFFSET]], i32 0) +// CHECK-NEXT: ret double [[TMP0]] +// +double test_atomic_fmax_f64(__amdgpu_buffer_rsrc_t rsrc, double x, int offset, int soffset) { + return __builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f64(x, rsrc, offset, soffset, 0); +} diff --git a/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-add-err.cl b/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-add-err.cl new file mode 100644 index 0000000000000..5c5ae937797e8 --- /dev/null +++ b/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-add-err.cl @@ -0,0 +1,10 @@ +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx90a -S -verify=gfx90a,expected -o - %s +// REQUIRES: amdgpu-registered-target + +typedef half __attribute__((ext_vector_type(2))) float16x2_t; + +void test_raw_ptr_atomics(__amdgpu_buffer_rsrc_t rsrc, int i32, float f32, float16x2_t v2f16, int offset, int soffset, int x) { + i32 = __builtin_amdgcn_raw_ptr_buffer_atomic_add_i32(i32, rsrc, offset, soffset, x); // expected-error{{argument to '__builtin_amdgcn_raw_ptr_buffer_atomic_add_i32' must be a constant integer}} + f32 = __builtin_amdgcn_raw_ptr_buffer_atomic_fadd_f32(f32, rsrc, offset, soffset, x); // expected-error{{argument to '__builtin_amdgcn_raw_ptr_buffer_atomic_fadd_f32' must be a constant integer}} + v2f16 = __builtin_amdgcn_raw_ptr_buffer_atomic_fadd_v2f16(v2f16, rsrc, offset, soffset, x); // expected-error{{argument to '__builtin_amdgcn_raw_ptr_buffer_atomic_fadd_v2f16' must be a constant integer}} +} diff --git a/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-add-target-err.cl b/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-add-target-err.cl new file mode 100644 index 0000000000000..509a498af5efa --- /dev/null +++ b/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-add-target-err.cl @@ -0,0 +1,9 @@ +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx908 -S -verify=gfx908,expected -o - %s +// REQUIRES: amdgpu-registered-target + +typedef half __attribute__((ext_vector_type(2))) float16x2_t; + +void test_raw_ptr_atomics(__amdgpu_buffer_rsrc_t rsrc, float f32, float16x2_t v2f16, int offset, int soffset) { + f32 = __builtin_amdgcn_raw_ptr_buffer_atomic_fadd_f32(f32, rsrc, offset, soffset, 0); // expected-error{{'__builtin_amdgcn_raw_ptr_buffer_atomic_fadd_f32' needs target feature atomic-fadd-rtn-insts}} + v2f16 = __builtin_amdgcn_raw_ptr_buffer_atomic_fadd_v2f16(v2f16, rsrc, offset, soffset, 0); // expected-error{{'__builtin_amdgcn_raw_ptr_buffer_atomic_fadd_v2f16' needs target feature atomic-buffer-global-pk-add-f16-insts}} +} diff --git a/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-max-err.cl b/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-max-err.cl new file mode 100644 index 0000000000000..4ad4eb50dbbd4 --- /dev/null +++ b/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-max-err.cl @@ -0,0 +1,9 @@ +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx90a -target-feature +atomic-fmin-fmax-global-f32 -target-feature +atomic-fmin-fmax-global-f64 -S -verify=expected -o - %s +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx942 -target-feature +atomic-fmin-fmax-global-f32 -target-feature +atomic-fmin-fmax-global-f64 -S -verify=expected -o - %s +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx950 -target-feature +atomic-fmin-fmax-global-f32 -target-feature +atomic-fmin-fmax-global-f64 -S -verify=expected -o - %s +// REQUIRES: amdgpu-registered-target + +void test_raw_ptr_atomics(__amdgpu_buffer_rsrc_t rsrc, float f32, double f64, int offset, int soffset, int x) { + f32 = __builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f32(f32, rsrc, offset, soffset, x); // expected-error{{argument to '__builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f32' must be a constant integer}} + f64 = __builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f64(f64, rsrc, offset, soffset, x); // expected-error{{argument to '__builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f64' must be a constant integer}} +} diff --git a/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-max-target-err.cl b/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-max-target-err.cl new file mode 100644 index 0000000000000..3f1ad416d132f --- /dev/null +++ b/clang/test/SemaOpenCL/builtins-amdgcn-raw-buffer-atomic-max-target-err.cl @@ -0,0 +1,7 @@ +// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -verify=expected -o - %s +// REQUIRES: amdgpu-registered-target + +void test_raw_ptr_atomics(__amdgpu_buffer_rsrc_t rsrc, float f32, double f64, int offset, int soffset) { + f32 = __builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f32(f32, rsrc, offset, soffset, 0); // expected-error{{'__builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f32' needs target feature atomic-fmin-fmax-global-f32}} + f64 = __builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f64(f64, rsrc, offset, soffset, 0); // expected-error{{'__builtin_amdgcn_raw_ptr_buffer_atomic_fmax_f64' needs target feature atomic-fmin-fmax-global-f64}} +} diff --git a/llvm/lib/TargetParser/TargetParser.cpp b/llvm/lib/TargetParser/TargetParser.cpp index 126be71a4cda5..c80bca6b5f256 100644 --- a/llvm/lib/TargetParser/TargetParser.cpp +++ b/llvm/lib/TargetParser/TargetParser.cpp @@ -459,6 +459,8 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T, Features["atomic-global-pk-add-bf16-inst"] = true; Features["atomic-ds-pk-add-16-insts"] = true; Features["setprio-inc-wg-inst"] = true; + Features["atomic-fmin-fmax-global-f32"] = true; + Features["atomic-fmin-fmax-global-f64"] = true; break; case GK_GFX1201: case GK_GFX1200: @@ -487,6 +489,7 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T, Features["atomic-fadd-rtn-insts"] = true; Features["image-insts"] = true; Features["fp8-conversion-insts"] = true; + Features["atomic-fmin-fmax-global-f32"] = true; break; case GK_GFX1153: case GK_GFX1152: @@ -515,6 +518,7 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T, Features["atomic-fadd-rtn-insts"] = true; Features["image-insts"] = true; Features["gws"] = true; + Features["atomic-fmin-fmax-global-f32"] = true; break; case GK_GFX1036: case GK_GFX1035: @@ -543,6 +547,8 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T, Features["s-memtime-inst"] = true; Features["gws"] = true; Features["vmem-to-lds-load-insts"] = true; + Features["atomic-fmin-fmax-global-f32"] = true; + Features["atomic-fmin-fmax-global-f64"] = true; break; case GK_GFX1012: case GK_GFX1011: @@ -568,6 +574,8 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T, Features["s-memtime-inst"] = true; Features["gws"] = true; Features["vmem-to-lds-load-insts"] = true; + Features["atomic-fmin-fmax-global-f32"] = true; + Features["atomic-fmin-fmax-global-f64"] = true; break; case GK_GFX950: Features["bitop3-insts"] = true; @@ -619,11 +627,13 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T, Features["s-memtime-inst"] = true; Features["gws"] = true; Features["vmem-to-lds-load-insts"] = true; + Features["atomic-fmin-fmax-global-f64"] = true; break; case GK_GFX90A: Features["gfx90a-insts"] = true; Features["atomic-buffer-global-pk-add-f16-insts"] = true; Features["atomic-fadd-rtn-insts"] = true; + Features["atomic-fmin-fmax-global-f64"] = true; [[fallthrough]]; case GK_GFX908: Features["dot3-insts"] = true;