The AMDGPUAnnotateKernelFeatures pass infers the "amdgpu-calls" and
"amdgpu-stack-objects" attributes, which are used to infer whether we
need to initialize flat scratch. This is, however, not precise. Instead,
we should use AMDGPUAttributor and infer amdgpu-no-flat-scratch-init on
kernels. Refer to https://github.com/llvm/llvm-project/issues/63586 .
This commit ensures than noundef (which is frequently a prerequisite for
other annotations) and range() annotations on kernel arguments are
copied onto their corresponding load from the kernel argument structure.
New register bank select for AMDGPU will be split in two passes:
- AMDGPURegBankSelect: select banks based on machine uniformity analysis
- AMDGPURegBankLegalize: lower instructions that can't be inst-selected
with register banks assigned by AMDGPURegBankSelect.
AMDGPURegBankLegalize is similar to legalizer but with context of
uniformity analysis. Does not change already assigned banks.
Main goal of AMDGPURegBankLegalize is to provide high level table-like
overview of how to lower generic instructions based on available target
features and uniformity info (uniform vs divergent).
See RegBankLegalizeRules.
Summary of new features:
At the moment register bank select assigns register bank to output
register using simple algorithm:
- one of the inputs is vgpr output is vgpr
- all inputs are sgpr output is sgpr.
When function does not contain divergent control flow propagating
register banks like this works. In general, first point is still correct
but second is not when function contains divergent control flow.
Examples:
- Phi with uniform inputs that go through divergent branch
- Instruction with temporal divergent use.
To fix this AMDGPURegBankSelect will use machine uniformity analysis
to assign vgpr to each divergent and sgpr to each uniform instruction.
But some instructions are only available on VALU (for example floating
point instructions before gfx1150) and we need to assign vgpr to them.
Since we are no longer propagating register banks we need to ensure that
uniform instructions get their inputs in sgpr in some way.
In AMDGPURegBankLegalize uniform instructions that are only available on
VALU will be reassigned to vgpr on all operands and read-any-lane vgpr
output to original sgpr output.
Alternative for https://github.com/llvm/llvm-project/pull/113764
It builds on a minimalistic approach with the legality check in match
and a blind apply. The precise patterns are used for better compile-time
and modularity. It also moves the pattern check into combiner. While
unary_undef_to_zero and propagate_undef_any_op rely on custom C++ code
for pattern matching.
Is there a limit on the number of patterns?
G_ANYEXT of undef -> undef
G_SEXT of undef -> 0
G_ZEXT of undef -> 0
The combine is not a member of the post legalizer combiner for AArch64.
Test:
llvm/test/CodeGen/AArch64/GlobalISel/combine-cast.mir
gfx950 SP changes doc says:
No 4 clk forwarding on opcodes that convert from
F32/F16->F8 or F32/F16->F4. Must insert a NOP or
instruction writing some other destination VREG
after a conversion to F4/F8 since it writes either
low/high half or bytes.
Co-authored-by: Pravin Jagtap <Pravin.Jagtap@amd.com>
Co-authored-by: Jeffrey Byrnes <Jeffrey.Byrnes@amd.com>
This reverts commit e9c49901a43f5b16c3df416460b7e4dbdd24ce03.
Current AMDGPURegBankSelect does nothing different then RegBankSelect.
Revert to using generic RegBankSelect in preparation for adding new
regbankselect passes. New AMDGPURegBankSelect, that will use uniformity
analysis for regbank select decisions, will not subclass RegBankSelect.
Revert regression tests to use regbankselect since amdgpu-regbankselect
will be used by new pass and behavior will be different.
For multipass instructions, overlap on VDST and SRC’s
would result in HW race & undefined results.
Co-authored-by: Pravin Jagtap <Pravin.Jagtap@amd.com>
These instructions have non-standard use of OPSEL bits to select
dest write byte. The src2_modifiers operand is used without having
its corresponding src2 operand by introducing dummy src2.
OPSEL ASM OPSEL Syntax: opsel:[a,b,c,d]
a & b are meaningless, c & d together decides byte to write in dst reg.
Co-authored-by: Pravin Jagtap <Pravin.Jagtap@amd.com>
OPSEL ASM Syntax for v_cvt_scalef32_pk_{f|bf}16_fp4 : opsel:[x,y,z]
where, x & y i.e. OPSEL[1 : 0] selects which src_byte to read.
Note: Conventional Inst{13} i.e. OPSEL[2] is ignored in asm syntax.
Co-authored-by: Pravin Jagtap <Pravin.Jagtap@amd.com>
OPSEL ASM Syntax for v_cvt_scalef32_pk_f32_fp4 : opsel:[x,y,z]
where, x & y i.e. OPSEL[1 : 0] selects which src_byte to read.
OPSEL ASM Syntax for v_cvt_scalef32_pk_fp4_f32 : opsel:[a,b,c,d]
where, c & d i.e. OPSEL[3 : 2] selects which dst_byte to write.
Co-authored-by: Pravin Jagtap <Pravin.Jagtap@amd.com>
OPSEL[1:0] collectively decide which byte to read
from src input.
Builtin takes additional imm argument which
represents index (with valid values:[0:3]) of src
byte read. Out of bounds checks will added in next
patch.
OPSEL ASM Syntax: opsel:[x,y,z]
where,
opsel[x] = Inst{11} = src0_modifier{2}
opsel[y] = Inst{12} = src1_modifier{2}
opsel[z] = Inst{14} = src0_modifier{3}
Note: Inst{13} i.e. OPSEL[2] is ignored in
asm syntax and opsel[z] is meaningless
for v_cvt_scalef32_f32_{fp|bf}8
Co-authored-by: Pravin Jagtap <Pravin.Jagtap@amd.com>
Extend the optimization that converts s_barrier to wave_barrier (nop)
when the number of work items is not larger than wave size.
This handles the "split barrier" form of s_barrier where the barrier
is represented by separate intrinsics (s_barrier_signal/s_barrier_wait).
Note: the version where s_barrier is used in gfx12 (and later split)
has the optimization already, but some front-ends may prefer to use
split intrinsics and this is being addressed by the patch.
The encoding of v_dot2c_f32_bf16 opcode is same as v_mac_f32 in gfx90a,
both from gfx9 series. This required a new decoderNameSpace GFX950_DOT.
Co-authored-by: Sirish Pande <Sirish.Pande@amd.com>
v_dot2_f32_bf16 was added in gfx11 along with v_dot2_f16_f16 and v_dot2_bf16_bf16.
All three instructions were part of Dot9 instructions in the compiler.
This patch will split existing dot9 (v_dot2_f16_f16, v_dot2_bf16_bf16, v_dot2_f32_bf16)
into new dot9 (v_dot2_f16_f16 and v_dot2_bf16_bf16), and dot12 (v_dot2_f32_bf16).
All necessary changes to gfx11 and gfx12 are updated to reflect this change.
Co-authored-by: Sirish Pande <Sirish.Pande@amd.com>
Scale packed 16-component single-precision float vectors from
two source inputs using the exponent provided by the third
single-precision float input, then convert the values to a packed
32-component FP6 float value.
Co-authored-by: Pravin Jagtap <Pravin.Jagtap@amd.com>
This adds the f32/f64/f16/bf16 test cases for below pattern :
`fmul x, select(y, A, B)`
with just one use of select Inst above.
It acts as pre-commit tests for dagCombining above pattern into cheaper
ldexp in case of non-inlline 32 bit-constants. (#111109)
