6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-28 04:33:05 +00:00
Code Issues Projects Releases Wiki Activity
9836c47ea6
llvm-6502/test/CodeGen/R600/local-memory-two-objects.ll

60 lines
2.6 KiB
LLVM
Raw Normal View History

R600/SI: Enable local-memory-two-objects lit test Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189334 91177308-0d34-0410-b5e6-96231b3b80d8
2013-08-27 10:28:26 +00:00
; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG-CHECK %s
R600/SI: Use -verify-machineinstrs for most tests We can't enable the verifier for tests with SI_IF and SI_ELSE, because these instructions are always followed by a COPY which copies their result to the next basic block. This violates the machine verifier's rule that non-terminators can not folow terminators. Reviewed-by: Vincent Lejeune<vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192366 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-10 17:11:46 +00:00
; RUN: llc < %s -march=r600 -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=SI-CHECK %s
R600/SI: Initial local memory support Enough for the radeonsi driver to use it for calculating derivatives. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186012 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-10 16:37:07 +00:00
@local_memory_two_objects.local_mem0 = internal addrspace(3) unnamed_addr global [4 x i32] zeroinitializer, align 4
@local_memory_two_objects.local_mem1 = internal addrspace(3) unnamed_addr global [4 x i32] zeroinitializer, align 4
R600/SI: Enable local-memory-two-objects lit test Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189334 91177308-0d34-0410-b5e6-96231b3b80d8
2013-08-27 10:28:26 +00:00
; EG-CHECK: @local_memory_two_objects
R600/SI: Initial local memory support Enough for the radeonsi driver to use it for calculating derivatives. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186012 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-10 16:37:07 +00:00
; Check that the LDS size emitted correctly
R600/SI: Enable local-memory-two-objects lit test Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189334 91177308-0d34-0410-b5e6-96231b3b80d8
2013-08-27 10:28:26 +00:00
; EG-CHECK: .long 166120
; EG-CHECK-NEXT: .long 8
; SI-CHECK: .long 47180
; SI-CHECK-NEXT: .long 32768
R600/SI: Initial local memory support Enough for the radeonsi driver to use it for calculating derivatives. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186012 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-10 16:37:07 +00:00
R600: Fix scheduling of instructions that use the LDS output queue The LDS output queue is accessed via the OQAP register. The OQAP register cannot be live across clauses, so if value is written to the output queue, it must be retrieved before the end of the clause. With the machine scheduler, we cannot statisfy this constraint, because it lacks proper alias analysis and it will mark some LDS accesses as having a chain dependency on vertex fetches. Since vertex fetches require a new clauses, the dependency may end up spiltting OQAP uses and defs so the end up in different clauses. See the lds-output-queue.ll test for a more detailed explanation. To work around this issue, we now combine the LDS read and the OQAP copy into one instruction and expand it after register allocation. This patch also adds some checks to the EmitClauseMarker pass, so that it doesn't end a clause with a value still in the output queue and removes AR.X and OQAP handling from the scheduler (AR.X uses and defs were already being expanded post-RA, so the scheduler will never see them). Reviewed-by: Vincent Lejeune <vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194755 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-15 00:12:45 +00:00
; We would like to check the the lds writes are using different
; addresses, but due to variations in the scheduler, we can't do
; this consistently on evergreen GPUs.
; EG-CHECK: LDS_WRITE
; EG-CHECK: LDS_WRITE
R600/SI: Don't display the GDS bit. It isn't actually used now, and probably never will be, plus it makes tests less annoying. I also think SC prints GDS instructions as a separate instruction name. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204270 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-19 22:19:43 +00:00
; SI-CHECK: DS_WRITE_B32 {{v[0-9]*}}, v[[ADDRW:[0-9]*]]
; SI-CHECK-NOT: DS_WRITE_B32 {{v[0-9]*}}, v[[ADDRW]]
R600/SI: Initial local memory support Enough for the radeonsi driver to use it for calculating derivatives. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186012 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-10 16:37:07 +00:00
; GROUP_BARRIER must be the last instruction in a clause
R600/SI: Enable local-memory-two-objects lit test Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189334 91177308-0d34-0410-b5e6-96231b3b80d8
2013-08-27 10:28:26 +00:00
; EG-CHECK: GROUP_BARRIER
; EG-CHECK-NEXT: ALU clause
R600/SI: Initial local memory support Enough for the radeonsi driver to use it for calculating derivatives. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186012 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-10 16:37:07 +00:00
R600/SI: Match i16 immediate offset of LDS instructions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204272 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-19 22:19:49 +00:00
; Make sure the lds reads are using different addresses, at different
; constant offsets.
R600/SI: Enable local-memory-two-objects lit test Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189334 91177308-0d34-0410-b5e6-96231b3b80d8
2013-08-27 10:28:26 +00:00
; EG-CHECK: LDS_READ_RET {{[*]*}} OQAP, {{PV|T}}[[ADDRR:[0-9]*\.[XYZW]]]
; EG-CHECK-NOT: LDS_READ_RET {{[*]*}} OQAP, T[[ADDRR]]
R600/SI: Print more immediates in hex format Print in decimal for inline immediates, and hex otherwise. Use hex always for offsets in addressing offsets. This approximately matches what the shader compiler does. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@206335 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-15 22:32:49 +00:00
; SI-CHECK: DS_READ_B32 {{v[0-9]+}}, [[ADDRR:v[0-9]+]], 0x10
; SI-CHECK: DS_READ_B32 {{v[0-9]+}}, [[ADDRR]], 0x0,
R600/SI: Initial local memory support Enough for the radeonsi driver to use it for calculating derivatives. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186012 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-10 16:37:07 +00:00
define void @local_memory_two_objects(i32 addrspace(1)* %out) {
entry:
%x.i = call i32 @llvm.r600.read.tidig.x() #0
%arrayidx = getelementptr inbounds [4 x i32] addrspace(3)* @local_memory_two_objects.local_mem0, i32 0, i32 %x.i
store i32 %x.i, i32 addrspace(3)* %arrayidx, align 4
%mul = shl nsw i32 %x.i, 1
%arrayidx1 = getelementptr inbounds [4 x i32] addrspace(3)* @local_memory_two_objects.local_mem1, i32 0, i32 %x.i
store i32 %mul, i32 addrspace(3)* %arrayidx1, align 4
%sub = sub nsw i32 3, %x.i
call void @llvm.AMDGPU.barrier.local()
%arrayidx2 = getelementptr inbounds [4 x i32] addrspace(3)* @local_memory_two_objects.local_mem0, i32 0, i32 %sub
%0 = load i32 addrspace(3)* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32 addrspace(1)* %out, i32 %x.i
store i32 %0, i32 addrspace(1)* %arrayidx3, align 4
%arrayidx4 = getelementptr inbounds [4 x i32] addrspace(3)* @local_memory_two_objects.local_mem1, i32 0, i32 %sub
%1 = load i32 addrspace(3)* %arrayidx4, align 4
%add = add nsw i32 %x.i, 4
%arrayidx5 = getelementptr inbounds i32 addrspace(1)* %out, i32 %add
store i32 %1, i32 addrspace(1)* %arrayidx5, align 4
ret void
}
declare i32 @llvm.r600.read.tidig.x() #0
declare void @llvm.AMDGPU.barrier.local()
attributes #0 = { readnone }
Reference in New Issue Copy Permalink