maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/private-memory-r600.ll

302 lines
11 KiB
LLVM
Raw Normal View History

AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck %s -check-prefix=R600 -check-prefix=FUNC
; RUN: opt -S -mtriple=r600-unknown-unknown -mcpu=redwood -amdgpu-promote-alloca < %s | FileCheck -check-prefix=OPT %s
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
; FUNC-LABEL: {{^}}mova_same_clause:
; R600: LDS_WRITE
; R600: LDS_WRITE
; R600: LDS_READ
; R600: LDS_READ
; OPT: call i32 @llvm.r600.read.local.size.y(), !range !0
; OPT: call i32 @llvm.r600.read.local.size.z(), !range !0
[AMDGPU] Generate range metadata for workitem id If workgroup size is known inform llvm about range returned by local id and local size queries. Differential Revision: https://reviews.llvm.org/D31804 llvm-svn: 300102
2017-04-13 04:48:56 +08:00
; OPT: call i32 @llvm.r600.read.tidig.x(), !range !1
; OPT: call i32 @llvm.r600.read.tidig.y(), !range !1
; OPT: call i32 @llvm.r600.read.tidig.z(), !range !1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @mova_same_clause(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%stack = alloca [5 x i32], align 4
%0 = load i32, i32 addrspace(1)* %in, align 4
%arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
store i32 4, i32* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
%1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
store i32 5, i32* %arrayidx3, align 4
%arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
%2 = load i32, i32* %arrayidx10, align 4
store i32 %2, i32 addrspace(1)* %out, align 4
%arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
%3 = load i32, i32* %arrayidx12
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
store i32 %3, i32 addrspace(1)* %arrayidx13
ret void
}
; This test checks that the stack offset is calculated correctly for structs.
; All register loads/stores should be optimized away, so there shouldn't be
; any MOVA instructions.
;
; XXX: This generated code has unnecessary MOVs, we should be able to optimize
; this.
; FUNC-LABEL: {{^}}multiple_structs:
; R600-NOT: MOVA_INT
%struct.point = type { i32, i32 }
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @multiple_structs(i32 addrspace(1)* %out) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%a = alloca %struct.point
%b = alloca %struct.point
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%a.x.ptr = getelementptr inbounds %struct.point, %struct.point* %a, i32 0, i32 0
%a.y.ptr = getelementptr inbounds %struct.point, %struct.point* %a, i32 0, i32 1
%b.x.ptr = getelementptr inbounds %struct.point, %struct.point* %b, i32 0, i32 0
%b.y.ptr = getelementptr inbounds %struct.point, %struct.point* %b, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i32 0, i32* %a.x.ptr
store i32 1, i32* %a.y.ptr
store i32 2, i32* %b.x.ptr
store i32 3, i32* %b.y.ptr
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%a.indirect.ptr = getelementptr inbounds %struct.point, %struct.point* %a, i32 0, i32 0
%b.indirect.ptr = getelementptr inbounds %struct.point, %struct.point* %b, i32 0, i32 0
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%a.indirect = load i32, i32* %a.indirect.ptr
%b.indirect = load i32, i32* %b.indirect.ptr
%0 = add i32 %a.indirect, %b.indirect
store i32 %0, i32 addrspace(1)* %out
ret void
}
; Test direct access of a private array inside a loop. The private array
; loads and stores should be lowered to copies, so there shouldn't be any
; MOVA instructions.
; FUNC-LABEL: {{^}}direct_loop:
; R600-NOT: MOVA_INT
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @direct_loop(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%prv_array_const = alloca [2 x i32]
%prv_array = alloca [2 x i32]
%a = load i32, i32 addrspace(1)* %in
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%b_src_ptr = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%b = load i32, i32 addrspace(1)* %b_src_ptr
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%a_dst_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array_const, i32 0, i32 0
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i32 %a, i32* %a_dst_ptr
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%b_dst_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array_const, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i32 %b, i32* %b_dst_ptr
br label %for.body
for.body:
%inc = phi i32 [0, %entry], [%count, %for.body]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%x_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array_const, i32 0, i32 0
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%x = load i32, i32* %x_ptr
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%y_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array, i32 0, i32 0
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%y = load i32, i32* %y_ptr
%xy = add i32 %x, %y
store i32 %xy, i32* %y_ptr
%count = add i32 %inc, 1
%done = icmp eq i32 %count, 4095
br i1 %done, label %for.end, label %for.body
for.end:
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%value_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array, i32 0, i32 0
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%value = load i32, i32* %value_ptr
store i32 %value, i32 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}short_array:
; R600: MOVA_INT
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @short_array(i32 addrspace(1)* %out, i32 %index) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%0 = alloca [2 x i16]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%1 = getelementptr inbounds [2 x i16], [2 x i16]* %0, i32 0, i32 0
%2 = getelementptr inbounds [2 x i16], [2 x i16]* %0, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i16 0, i16* %1
store i16 1, i16* %2
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%3 = getelementptr inbounds [2 x i16], [2 x i16]* %0, i32 0, i32 %index
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%4 = load i16, i16* %3
%5 = sext i16 %4 to i32
store i32 %5, i32 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}char_array:
; R600: MOVA_INT
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @char_array(i32 addrspace(1)* %out, i32 %index) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%0 = alloca [2 x i8]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%1 = getelementptr inbounds [2 x i8], [2 x i8]* %0, i32 0, i32 0
%2 = getelementptr inbounds [2 x i8], [2 x i8]* %0, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i8 0, i8* %1
store i8 1, i8* %2
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%3 = getelementptr inbounds [2 x i8], [2 x i8]* %0, i32 0, i32 %index
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%4 = load i8, i8* %3
%5 = sext i8 %4 to i32
store i32 %5, i32 addrspace(1)* %out
ret void
}
; Make sure we don't overwrite workitem information with private memory
; FUNC-LABEL: {{^}}work_item_info:
; R600-NOT: MOV T0.X
; Additional check in case the move ends up in the last slot
; R600-NOT: MOV * TO.X
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @work_item_info(i32 addrspace(1)* %out, i32 %in) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%0 = alloca [2 x i32]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%1 = getelementptr inbounds [2 x i32], [2 x i32]* %0, i32 0, i32 0
%2 = getelementptr inbounds [2 x i32], [2 x i32]* %0, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i32 0, i32* %1
store i32 1, i32* %2
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%3 = getelementptr inbounds [2 x i32], [2 x i32]* %0, i32 0, i32 %in
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%4 = load i32, i32* %3
%5 = call i32 @llvm.r600.read.tidig.x()
%6 = add i32 %4, %5
store i32 %6, i32 addrspace(1)* %out
ret void
}
; Test that two stack objects are not stored in the same register
; The second stack object should be in T3.X
; FUNC-LABEL: {{^}}no_overlap:
; R600_CHECK: MOV
; R600_CHECK: [[CHAN:[XYZW]]]+
; R600-NOT: [[CHAN]]+
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @no_overlap(i32 addrspace(1)* %out, i32 %in) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%0 = alloca [3 x i8], align 1
%1 = alloca [2 x i8], align 1
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%2 = getelementptr inbounds [3 x i8], [3 x i8]* %0, i32 0, i32 0
%3 = getelementptr inbounds [3 x i8], [3 x i8]* %0, i32 0, i32 1
%4 = getelementptr inbounds [3 x i8], [3 x i8]* %0, i32 0, i32 2
%5 = getelementptr inbounds [2 x i8], [2 x i8]* %1, i32 0, i32 0
%6 = getelementptr inbounds [2 x i8], [2 x i8]* %1, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i8 0, i8* %2
store i8 1, i8* %3
store i8 2, i8* %4
store i8 1, i8* %5
store i8 0, i8* %6
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%7 = getelementptr inbounds [3 x i8], [3 x i8]* %0, i32 0, i32 %in
%8 = getelementptr inbounds [2 x i8], [2 x i8]* %1, i32 0, i32 %in
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%9 = load i8, i8* %7
%10 = load i8, i8* %8
%11 = add i8 %9, %10
%12 = sext i8 %11 to i32
store i32 %12, i32 addrspace(1)* %out
ret void
}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @char_array_array(i32 addrspace(1)* %out, i32 %index) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%alloca = alloca [2 x [2 x i8]]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep0 = getelementptr inbounds [2 x [2 x i8]], [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x [2 x i8]], [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i8 0, i8* %gep0
store i8 1, i8* %gep1
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep2 = getelementptr inbounds [2 x [2 x i8]], [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 %index
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%load = load i8, i8* %gep2
%sext = sext i8 %load to i32
store i32 %sext, i32 addrspace(1)* %out
ret void
}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @i32_array_array(i32 addrspace(1)* %out, i32 %index) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%alloca = alloca [2 x [2 x i32]]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep0 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i32 0, i32* %gep0
store i32 1, i32* %gep1
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep2 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 %index
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%load = load i32, i32* %gep2
store i32 %load, i32 addrspace(1)* %out
ret void
}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @i64_array_array(i64 addrspace(1)* %out, i32 %index) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%alloca = alloca [2 x [2 x i64]]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep0 = getelementptr inbounds [2 x [2 x i64]], [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x [2 x i64]], [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i64 0, i64* %gep0
store i64 1, i64* %gep1
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep2 = getelementptr inbounds [2 x [2 x i64]], [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 %index
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%load = load i64, i64* %gep2
store i64 %load, i64 addrspace(1)* %out
ret void
}
%struct.pair32 = type { i32, i32 }
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @struct_array_array(i32 addrspace(1)* %out, i32 %index) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%alloca = alloca [2 x [2 x %struct.pair32]]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep0 = getelementptr inbounds [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 0, i32 1
%gep1 = getelementptr inbounds [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 1, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i32 0, i32* %gep0
store i32 1, i32* %gep1
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep2 = getelementptr inbounds [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 %index, i32 0
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%load = load i32, i32* %gep2
store i32 %load, i32 addrspace(1)* %out
ret void
}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @struct_pair32_array(i32 addrspace(1)* %out, i32 %index) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%alloca = alloca [2 x %struct.pair32]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep0 = getelementptr inbounds [2 x %struct.pair32], [2 x %struct.pair32]* %alloca, i32 0, i32 0, i32 1
%gep1 = getelementptr inbounds [2 x %struct.pair32], [2 x %struct.pair32]* %alloca, i32 0, i32 1, i32 0
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i32 0, i32* %gep0
store i32 1, i32* %gep1
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%gep2 = getelementptr inbounds [2 x %struct.pair32], [2 x %struct.pair32]* %alloca, i32 0, i32 %index, i32 0
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%load = load i32, i32* %gep2
store i32 %load, i32 addrspace(1)* %out
ret void
}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @select_private(i32 addrspace(1)* %out, i32 %in) nounwind {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
entry:
%tmp = alloca [2 x i32]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%tmp1 = getelementptr inbounds [2 x i32], [2 x i32]* %tmp, i32 0, i32 0
%tmp2 = getelementptr inbounds [2 x i32], [2 x i32]* %tmp, i32 0, i32 1
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i32 0, i32* %tmp1
store i32 1, i32* %tmp2
%cmp = icmp eq i32 %in, 0
%sel = select i1 %cmp, i32* %tmp1, i32* %tmp2
%load = load i32, i32* %sel
store i32 %load, i32 addrspace(1)* %out
ret void
}
; AMDGPUPromoteAlloca does not know how to handle ptrtoint. When it
; finds one, it should stop trying to promote.
; FUNC-LABEL: ptrtoint:
; SI-NOT: ds_write
; SI: buffer_store_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen
; SI: buffer_load_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen ;
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @ptrtoint(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 {
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%alloca = alloca [16 x i32]
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%tmp0 = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 %a
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
store i32 5, i32* %tmp0
%tmp1 = ptrtoint [16 x i32]* %alloca to i32
%tmp2 = add i32 %tmp1, 5
%tmp3 = inttoptr i32 %tmp2 to i32*
AMDGPU: Do not promote allocas with non-inbounds GEPs If we can't assume the pointer value isn't within the bounds of the object, it seems risky to try to replace the pointer calculations. llvm-svn: 259573
2016-02-03 05:16:12 +08:00
%tmp4 = getelementptr inbounds i32, i32* %tmp3, i32 %b
AMDGPU: Fix emitting invalid workitem intrinsics for HSA The AMDGPUPromoteAlloca pass was emitting the read.local.size calls, which with HSA was incorrectly selected to reading from the offset mesa uses off of the kernarg pointer. Error on intrinsics which aren't supported by HSA, and start emitting the correct IR to read the workgroup size out of the dispatch pointer. Also initialize the pass so it can be tested with opt, and start moving towards not depending on the subtarget as an argument. Start emitting errors for the intrinsics not handled with HSA. llvm-svn: 259297
2016-01-30 13:19:45 +08:00
%tmp5 = load i32, i32* %tmp4
store i32 %tmp5, i32 addrspace(1)* %out
ret void
}
[AMDGPU] Generate range metadata for workitem id If workgroup size is known inform llvm about range returned by local id and local size queries. Differential Revision: https://reviews.llvm.org/D31804 llvm-svn: 300102
2017-04-13 04:48:56 +08:00
; OPT: !0 = !{i32 0, i32 257}
; OPT: !1 = !{i32 0, i32 256}
AMDGPU: Fix promote alloca pass creating huge arrays This was assuming it could use all memory before, which is a bad decision because it restricts occupancy. By default, only try to use enough space that could reduce occupancy to 7, an arbitrarily chosen limit. Based on the exist LDS usage, try to round up to the limit in the current tier instead of further hurting occupancy. This isn't ideal, because it doesn't accurately know how much space is going to be used for alignment padding. llvm-svn: 269708
2016-05-17 05:19:59 +08:00
[AMDGPU] Wave and register controls - Implemented amdgpu-flat-work-group-size attribute - Implemented amdgpu-num-active-waves-per-eu attribute - Implemented amdgpu-num-sgpr attribute - Implemented amdgpu-num-vgpr attribute - Dynamic LDS constraints are in a separate patch Patch by Tom Stellard and Konstantin Zhuravlyov Differential Revision: https://reviews.llvm.org/D21562 llvm-svn: 280747
2016-09-07 04:22:28 +08:00
attributes #0 = { nounwind "amdgpu-waves-per-eu"="1,2" }