mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 10:42:39 +01:00
63f261dc1c
Summary: Add some optional code to validate getInstSizeInBytes for emitted instructions. This flushed out some issues which are fixed by this patch: - Streamline getInstSizeInBytes - Properly define the VI readlane/writelane instruction as VOP3 - Fix the inline constant determination. Specifically, this change fixes an issue where a 32-bit value of 0xffffffff was recorded as unsigned. This is equal to -1 when restricting to a 32-bit comparison, and an inline constant can be used. Reviewers: arsenm, rampitec Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D50629 Change-Id: Id87c3b7975839da0de8156a124b0ce98c5fb47f2 llvm-svn: 340903
83 lines
3.5 KiB
LLVM
83 lines
3.5 KiB
LLVM
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx700 -verify-machineinstrs < %s | FileCheck %s
|
|
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx802 -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
declare i32 @llvm.amdgcn.writelane(i32, i32, i32) #0
|
|
|
|
; CHECK-LABEL: {{^}}test_writelane_sreg:
|
|
; CHECK: v_writelane_b32 v{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
|
|
define amdgpu_kernel void @test_writelane_sreg(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #1 {
|
|
%oldval = load i32, i32 addrspace(1)* %out
|
|
%writelane = call i32 @llvm.amdgcn.writelane(i32 %src0, i32 %src1, i32 %oldval)
|
|
store i32 %writelane, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}test_writelane_imm_sreg:
|
|
; CHECK: v_writelane_b32 v{{[0-9]+}}, 32, s{{[0-9]+}}
|
|
define amdgpu_kernel void @test_writelane_imm_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
|
|
%oldval = load i32, i32 addrspace(1)* %out
|
|
%writelane = call i32 @llvm.amdgcn.writelane(i32 32, i32 %src1, i32 %oldval)
|
|
store i32 %writelane, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}test_writelane_vreg_lane:
|
|
; CHECK: v_readfirstlane_b32 [[LANE:s[0-9]+]], v{{[0-9]+}}
|
|
; CHECK: v_writelane_b32 v{{[0-9]+}}, 12, [[LANE]]
|
|
define amdgpu_kernel void @test_writelane_vreg_lane(i32 addrspace(1)* %out, <2 x i32> addrspace(1)* %in) #1 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%gep.in = getelementptr <2 x i32>, <2 x i32> addrspace(1)* %in, i32 %tid
|
|
%args = load <2 x i32>, <2 x i32> addrspace(1)* %gep.in
|
|
%oldval = load i32, i32 addrspace(1)* %out
|
|
%lane = extractelement <2 x i32> %args, i32 1
|
|
%writelane = call i32 @llvm.amdgcn.writelane(i32 12, i32 %lane, i32 %oldval)
|
|
store i32 %writelane, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; TODO: m0 should be folded.
|
|
; CHECK-LABEL: {{^}}test_writelane_m0_sreg:
|
|
; CHECK: s_mov_b32 m0, -1
|
|
; CHECK: s_mov_b32 [[COPY_M0:s[0-9]+]], m0
|
|
; CHECK: v_writelane_b32 v{{[0-9]+}}, [[COPY_M0]], s{{[0-9]+}}
|
|
define amdgpu_kernel void @test_writelane_m0_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
|
|
%oldval = load i32, i32 addrspace(1)* %out
|
|
%m0 = call i32 asm "s_mov_b32 m0, -1", "={M0}"()
|
|
%writelane = call i32 @llvm.amdgcn.writelane(i32 %m0, i32 %src1, i32 %oldval)
|
|
store i32 %writelane, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}test_writelane_imm:
|
|
; CHECK: v_writelane_b32 v{{[0-9]+}}, s{{[0-9]+}}, 32
|
|
define amdgpu_kernel void @test_writelane_imm(i32 addrspace(1)* %out, i32 %src0) #1 {
|
|
%oldval = load i32, i32 addrspace(1)* %out
|
|
%writelane = call i32 @llvm.amdgcn.writelane(i32 %src0, i32 32, i32 %oldval) #0
|
|
store i32 %writelane, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}test_writelane_sreg_oldval:
|
|
; CHECK: v_mov_b32_e32 [[OLDVAL:v[0-9]+]], s{{[0-9]+}}
|
|
; CHECK: v_writelane_b32 [[OLDVAL]], s{{[0-9]+}}, s{{[0-9]+}}
|
|
define amdgpu_kernel void @test_writelane_sreg_oldval(i32 inreg %oldval, i32 addrspace(1)* %out, i32 %src0, i32 %src1) #1 {
|
|
%writelane = call i32 @llvm.amdgcn.writelane(i32 %src0, i32 %src1, i32 %oldval)
|
|
store i32 %writelane, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}test_writelane_imm_oldval:
|
|
; CHECK: v_mov_b32_e32 [[OLDVAL:v[0-9]+]], 42
|
|
; CHECK: v_writelane_b32 [[OLDVAL]], s{{[0-9]+}}, s{{[0-9]+}}
|
|
define amdgpu_kernel void @test_writelane_imm_oldval(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #1 {
|
|
%writelane = call i32 @llvm.amdgcn.writelane(i32 %src0, i32 %src1, i32 42)
|
|
store i32 %writelane, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #2
|
|
|
|
attributes #0 = { nounwind readnone convergent }
|
|
attributes #1 = { nounwind }
|
|
attributes #2 = { nounwind readnone }
|