llvm/test/CodeGen/AMDGPU/sdwa-peephole.ll
Matt Arsenault a038a8340c AMDGPU: Allow SIShrinkInstructions to work in non-SSA
Immediates can be folded as long as the immediate is a vreg.

Also undo commuting instructions if it didn't fold an immediate.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@307575 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-10 19:53:57 +00:00

499 lines
24 KiB
LLVM

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -amdgpu-sdwa-peephole=0 -mattr=-fp64-fp16-denormals -verify-machineinstrs < %s | FileCheck -check-prefix=NOSDWA -check-prefix=GCN %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -amdgpu-sdwa-peephole -mattr=-fp64-fp16-denormals -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=SDWA -check-prefix=GCN %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -amdgpu-sdwa-peephole -mattr=-fp64-fp16-denormals -verify-machineinstrs < %s | FileCheck -check-prefix=GFX9 -check-prefix=SDWA -check-prefix=GCN %s
; GCN-LABEL: {{^}}add_shr_i32:
; NOSDWA: v_lshrrev_b32_e32 v[[DST:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_add_i32_e32 v{{[0-9]+}}, vcc, v{{[0-9]+}}, v[[DST]]
; NOSDWA-NOT: v_add_i32_sdwa
; SDWA: v_add_i32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:WORD_1
define amdgpu_kernel void @add_shr_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
%a = load i32, i32 addrspace(1)* %in, align 4
%shr = lshr i32 %a, 16
%add = add i32 %a, %shr
store i32 %add, i32 addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}sub_shr_i32:
; NOSDWA: v_lshrrev_b32_e32 v[[DST:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_subrev_i32_e32 v{{[0-9]+}}, vcc, v{{[0-9]+}}, v[[DST]]
; NOSDWA-NOT: v_subrev_i32_sdwa
; SDWA: v_subrev_i32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:WORD_1
define amdgpu_kernel void @sub_shr_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
%a = load i32, i32 addrspace(1)* %in, align 4
%shr = lshr i32 %a, 16
%sub = sub i32 %shr, %a
store i32 %sub, i32 addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_shr_i32:
; NOSDWA: v_lshrrev_b32_e32 v[[DST0:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b32_e32 v[[DST1:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_mul_u32_u24_e32 v{{[0-9]+}}, v[[DST0]], v[[DST1]]
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; SDWA: v_mul_u32_u24_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
define amdgpu_kernel void @mul_shr_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in1, i32 addrspace(1)* %in2) {
%a = load i32, i32 addrspace(1)* %in1, align 4
%b = load i32, i32 addrspace(1)* %in2, align 4
%shra = lshr i32 %a, 16
%shrb = lshr i32 %b, 16
%mul = mul i32 %shra, %shrb
store i32 %mul, i32 addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_i16:
; NOSDWA: v_mul_lo_i32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; SDWA: v_mul_lo_i32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; SDWA-NOT: v_mul_u32_u24_sdwa
define amdgpu_kernel void @mul_i16(i16 addrspace(1)* %out, i16 addrspace(1)* %ina, i16 addrspace(1)* %inb) {
entry:
%a = load i16, i16 addrspace(1)* %ina, align 4
%b = load i16, i16 addrspace(1)* %inb, align 4
%mul = mul i16 %a, %b
store i16 %mul, i16 addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_v2i16:
; NOSDWA: v_lshrrev_b32_e32 v[[DST0:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b32_e32 v[[DST1:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_mul_u32_u24_e32 v[[DST_MUL:[0-9]+]], v[[DST0]], v[[DST1]]
; NOSDWA: v_lshlrev_b32_e32 v[[DST_SHL:[0-9]+]], 16, v[[DST_MUL]]
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v[[DST_SHL]]
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL_LO:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:WORD_0
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL_HI:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI: v_or_b32_sdwa v{{[0-9]+}}, v[[DST_MUL_LO]], v[[DST_MUL_HI]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX9: v_pk_mul_lo_u16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @mul_v2i16(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %ina, <2 x i16> addrspace(1)* %inb) {
entry:
%a = load <2 x i16>, <2 x i16> addrspace(1)* %ina, align 4
%b = load <2 x i16>, <2 x i16> addrspace(1)* %inb, align 4
%mul = mul <2 x i16> %a, %b
store <2 x i16> %mul, <2 x i16> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_v4i16:
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_mul_u32_u24_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA: v_lshlrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL0:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:WORD_0
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL1:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL2:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:WORD_0
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL3:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_or_b32_sdwa v{{[0-9]+}}, v[[DST_MUL2]], v[[DST_MUL3]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; VI-DAG: v_or_b32_sdwa v{{[0-9]+}}, v[[DST_MUL0]], v[[DST_MUL1]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX9-DAG: v_pk_mul_lo_u16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_lo_u16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @mul_v4i16(<4 x i16> addrspace(1)* %out, <4 x i16> addrspace(1)* %ina, <4 x i16> addrspace(1)* %inb) {
entry:
%a = load <4 x i16>, <4 x i16> addrspace(1)* %ina, align 4
%b = load <4 x i16>, <4 x i16> addrspace(1)* %inb, align 4
%mul = mul <4 x i16> %a, %b
store <4 x i16> %mul, <4 x i16> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_v8i16:
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_mul_u32_u24_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA: v_lshlrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL0:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:WORD_0
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL1:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL2:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:WORD_0
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL3:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL4:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:WORD_0
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL5:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL6:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:WORD_0
; VI-DAG: v_mul_u32_u24_sdwa v[[DST_MUL7:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_or_b32_sdwa v{{[0-9]+}}, v[[DST_MUL6]], v[[DST_MUL7]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; VI-DAG: v_or_b32_sdwa v{{[0-9]+}}, v[[DST_MUL4]], v[[DST_MUL5]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; VI-DAG: v_or_b32_sdwa v{{[0-9]+}}, v[[DST_MUL2]], v[[DST_MUL3]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; VI-DAG: v_or_b32_sdwa v{{[0-9]+}}, v[[DST_MUL0]], v[[DST_MUL1]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX9-DAG: v_pk_mul_lo_u16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_lo_u16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_lo_u16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_lo_u16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @mul_v8i16(<8 x i16> addrspace(1)* %out, <8 x i16> addrspace(1)* %ina, <8 x i16> addrspace(1)* %inb) {
entry:
%a = load <8 x i16>, <8 x i16> addrspace(1)* %ina, align 4
%b = load <8 x i16>, <8 x i16> addrspace(1)* %inb, align 4
%mul = mul <8 x i16> %a, %b
store <8 x i16> %mul, <8 x i16> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_half:
; NOSDWA: v_mul_f16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_f16_sdwa
; SDWA: v_mul_f16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; SDWA-NOT: v_mul_f16_sdwa
define amdgpu_kernel void @mul_half(half addrspace(1)* %out, half addrspace(1)* %ina, half addrspace(1)* %inb) {
entry:
%a = load half, half addrspace(1)* %ina, align 4
%b = load half, half addrspace(1)* %inb, align 4
%mul = fmul half %a, %b
store half %mul, half addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_v2half:
; NOSDWA: v_lshrrev_b32_e32 v[[DST0:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b32_e32 v[[DST1:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_mul_f16_e32 v[[DST_MUL:[0-9]+]], v[[DST0]], v[[DST1]]
; NOSDWA: v_lshlrev_b32_e32 v[[DST_SHL:[0-9]+]], 16, v[[DST_MUL]]
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v[[DST_SHL]]
; NOSDWA-NOT: v_mul_f16_sdwa
; VI-DAG: v_mul_f16_sdwa v[[DST_MUL_HI:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_mul_f16_e32 v[[DST_MUL_LO:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}}
; VI: v_or_b32_e32 v{{[0-9]+}}, v[[DST_MUL_LO]], v[[DST_MUL_HI]]
; GFX9: v_pk_mul_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @mul_v2half(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %ina, <2 x half> addrspace(1)* %inb) {
entry:
%a = load <2 x half>, <2 x half> addrspace(1)* %ina, align 4
%b = load <2 x half>, <2 x half> addrspace(1)* %inb, align 4
%mul = fmul <2 x half> %a, %b
store <2 x half> %mul, <2 x half> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_v4half:
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_mul_f16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA: v_lshlrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_f16_sdwa
; VI-DAG: v_mul_f16_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_mul_f16_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; VI-DAG: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @mul_v4half(<4 x half> addrspace(1)* %out, <4 x half> addrspace(1)* %ina, <4 x half> addrspace(1)* %inb) {
entry:
%a = load <4 x half>, <4 x half> addrspace(1)* %ina, align 4
%b = load <4 x half>, <4 x half> addrspace(1)* %inb, align 4
%mul = fmul <4 x half> %a, %b
store <4 x half> %mul, <4 x half> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_v8half:
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_mul_f16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA: v_lshlrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_f16_sdwa
; VI-DAG: v_mul_f16_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_mul_f16_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_mul_f16_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_mul_f16_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI-DAG: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; VI-DAG: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; VI-DAG: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; VI-DAG: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9-DAG: v_pk_mul_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @mul_v8half(<8 x half> addrspace(1)* %out, <8 x half> addrspace(1)* %ina, <8 x half> addrspace(1)* %inb) {
entry:
%a = load <8 x half>, <8 x half> addrspace(1)* %ina, align 4
%b = load <8 x half>, <8 x half> addrspace(1)* %inb, align 4
%mul = fmul <8 x half> %a, %b
store <8 x half> %mul, <8 x half> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_i8:
; NOSDWA: v_mul_lo_i32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; SDWA: v_mul_lo_i32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; SDWA-NOT: v_mul_u32_u24_sdwa
define amdgpu_kernel void @mul_i8(i8 addrspace(1)* %out, i8 addrspace(1)* %ina, i8 addrspace(1)* %inb) {
entry:
%a = load i8, i8 addrspace(1)* %ina, align 4
%b = load i8, i8 addrspace(1)* %inb, align 4
%mul = mul i8 %a, %b
store i8 %mul, i8 addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_v2i8:
; NOSDWA: v_lshrrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_mul_u32_u24_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA: v_lshlrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; VI: v_mul_u32_u24_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:BYTE_1 dst_unused:UNUSED_PAD src0_sel:BYTE_1 src1_sel:BYTE_1
; GFX9-DAG: v_mul_lo_u16_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:BYTE_1 dst_unused:UNUSED_PAD src0_sel:BYTE_1 src1_sel:BYTE_1
; GFX9-DAG: v_mul_lo_u16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GFX9: v_or_b32_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:BYTE_0 src1_sel:DWORD
define amdgpu_kernel void @mul_v2i8(<2 x i8> addrspace(1)* %out, <2 x i8> addrspace(1)* %ina, <2 x i8> addrspace(1)* %inb) {
entry:
%a = load <2 x i8>, <2 x i8> addrspace(1)* %ina, align 4
%b = load <2 x i8>, <2 x i8> addrspace(1)* %inb, align 4
%mul = mul <2 x i8> %a, %b
store <2 x i8> %mul, <2 x i8> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_v4i8:
; NOSDWA: v_lshrrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_mul_u32_u24_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA: v_lshlrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa
; GFX9-DAG: v_mul_lo_u16_sdwa
; GFX9-DAG: v_mul_lo_u16_sdwa
; GFX9-DAG: v_mul_lo_u16_sdwa
define amdgpu_kernel void @mul_v4i8(<4 x i8> addrspace(1)* %out, <4 x i8> addrspace(1)* %ina, <4 x i8> addrspace(1)* %inb) {
entry:
%a = load <4 x i8>, <4 x i8> addrspace(1)* %ina, align 4
%b = load <4 x i8>, <4 x i8> addrspace(1)* %inb, align 4
%mul = mul <4 x i8> %a, %b
store <4 x i8> %mul, <4 x i8> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}mul_v8i8:
; NOSDWA: v_lshrrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_mul_u32_u24_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA: v_lshlrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa
; VI-DAG: v_mul_u32_u24_sdwa
; GFX9-DAG: v_mul_lo_u16_sdwa
; GFX9-DAG: v_mul_lo_u16_sdwa
; GFX9-DAG: v_mul_lo_u16_sdwa
; GFX9-DAG: v_mul_lo_u16_sdwa
; GFX9-DAG: v_mul_lo_u16_sdwa
; GFX9-DAG: v_mul_lo_u16_sdwa
define amdgpu_kernel void @mul_v8i8(<8 x i8> addrspace(1)* %out, <8 x i8> addrspace(1)* %ina, <8 x i8> addrspace(1)* %inb) {
entry:
%a = load <8 x i8>, <8 x i8> addrspace(1)* %ina, align 4
%b = load <8 x i8>, <8 x i8> addrspace(1)* %inb, align 4
%mul = mul <8 x i8> %a, %b
store <8 x i8> %mul, <8 x i8> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}sitofp_v2i16_to_v2f16:
; NOSDWA-DAG: v_bfe_i32 v{{[0-9]+}}, v{{[0-9]+}}, 0, 16
; NOSDWA-DAG: v_ashrrev_i32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA-DAG: v_cvt_f32_i32_e32 v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-DAG: v_cvt_f32_i32_e32 v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_cvt_f32_i32_sdwa
; SDWA-DAG: v_cvt_f32_i32_sdwa v{{[0-9]+}}, sext(v{{[0-9]+}}) dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0
; SDWA-DAG: v_cvt_f32_i32_sdwa v{{[0-9]+}}, sext(v{{[0-9]+}}) dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
define amdgpu_kernel void @sitofp_v2i16_to_v2f16(
<2 x half> addrspace(1)* %r,
<2 x i16> addrspace(1)* %a) {
entry:
%a.val = load <2 x i16>, <2 x i16> addrspace(1)* %a
%r.val = sitofp <2 x i16> %a.val to <2 x half>
store <2 x half> %r.val, <2 x half> addrspace(1)* %r
ret void
}
; GCN-LABEL: {{^}}mac_v2half:
; NOSDWA: v_lshrrev_b32_e32 v[[DST0:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b32_e32 v[[DST1:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_mac_f16_e32 v[[DST_MAC:[0-9]+]], v[[DST0]], v[[DST1]]
; NOSDWA: v_lshlrev_b32_e32 v[[DST_SHL:[0-9]+]], 16, v[[DST_MAC]]
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v[[DST_SHL]]
; NOSDWA-NOT: v_mac_f16_sdwa
; VI: v_mac_f16_sdwa v[[DST_MAC:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; VI: v_lshlrev_b32_e32 v[[DST_SHL:[0-9]+]], 16, v[[DST_MAC]]
; GFX9: v_pk_mul_f16 v[[DST_MUL:[0-9]+]], v{{[0-9]+}}, v[[SRC:[0-9]+]]
; GFX9: v_pk_add_f16 v{{[0-9]+}}, v[[DST_MUL]], v[[SRC]]
define amdgpu_kernel void @mac_v2half(<2 x half> addrspace(1)* %out, <2 x half> addrspace(1)* %ina, <2 x half> addrspace(1)* %inb) {
entry:
%a = load <2 x half>, <2 x half> addrspace(1)* %ina, align 4
%b = load <2 x half>, <2 x half> addrspace(1)* %inb, align 4
%mul = fmul <2 x half> %a, %b
%mac = fadd <2 x half> %mul, %b
store <2 x half> %mac, <2 x half> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}immediate_mul_v2i16:
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; VI-DAG: v_mov_b32_e32 v[[M321:[0-9]+]], 0x141
; VI-DAG: v_mov_b32_e32 v[[M123:[0-9]+]], 0x7b
; VI-DAG: v_mul_u32_u24_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v[[M123]] dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; VI-DAG: v_mul_u32_u24_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v[[M321]] dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
; GFX9: s_mov_b32 s[[IMM:[0-9]+]], 0x141007b
; GFX9: v_pk_mul_lo_u16 v{{[0-9]+}}, v{{[0-9]+}}, s[[IMM]]
define amdgpu_kernel void @immediate_mul_v2i16(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) {
entry:
%a = load <2 x i16>, <2 x i16> addrspace(1)* %in, align 4
%mul = mul <2 x i16> %a, <i16 123, i16 321>
store <2 x i16> %mul, <2 x i16> addrspace(1)* %out, align 4
ret void
}
; Double use of same src - should not convert it
; GCN-LABEL: {{^}}mulmul_v2i16:
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_mul_u32_u24_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA: v_lshlrev_b32_e32 v{{[0-9]+}}, 16, v{{[0-9]+}}
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_mul_u32_u24_sdwa
; VI: v_mul_u32_u24_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
; GFX9: v_pk_mul_lo_u16 v[[DST1:[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}}
; GFX9: v_pk_mul_lo_u16 v{{[0-9]+}}, v[[DST1]], v{{[0-9]+}}
define amdgpu_kernel void @mulmul_v2i16(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %ina, <2 x i16> addrspace(1)* %inb) {
entry:
%a = load <2 x i16>, <2 x i16> addrspace(1)* %ina, align 4
%b = load <2 x i16>, <2 x i16> addrspace(1)* %inb, align 4
%mul = mul <2 x i16> %a, %b
%mul2 = mul <2 x i16> %mul, %b
store <2 x i16> %mul2, <2 x i16> addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}add_bb_v2i16:
; NOSDWA-NOT: v_add_i32_sdwa
; VI: v_add_i32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
; GFX9: v_pk_add_u16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define amdgpu_kernel void @add_bb_v2i16(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %ina, <2 x i16> addrspace(1)* %inb) {
entry:
%a = load <2 x i16>, <2 x i16> addrspace(1)* %ina, align 4
%b = load <2 x i16>, <2 x i16> addrspace(1)* %inb, align 4
br label %add_label
add_label:
%add = add <2 x i16> %a, %b
br label %store_label
store_label:
store <2 x i16> %add, <2 x i16> addrspace(1)* %out, align 4
ret void
}
; Check that "pulling out" SDWA operands works correctly.
; GCN-LABEL: {{^}}pulled_out_test:
; NOSDWA-DAG: v_and_b32_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-DAG: v_lshlrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA-DAG: v_and_b32_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-DAG: v_lshlrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; NOSDWA: v_or_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; NOSDWA-NOT: v_and_b32_sdwa
; NOSDWA-NOT: v_or_b32_sdwa
; VI-DAG: v_and_b32_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
; GFX9-DAG: v_and_b32_sdwa v{{[0-9]+}}, v{{[0-9]+}}, s{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
; SDWA-DAG: v_lshlrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; VI-DAG: v_and_b32_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
; GFX9-DAG: v_and_b32_sdwa v{{[0-9]+}}, v{{[0-9]+}}, s{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
; SDWA-DAG: v_lshlrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
; SDWA: v_or_b32_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
define amdgpu_kernel void @pulled_out_test(<8 x i8> addrspace(1)* %sourceA, <8 x i8> addrspace(1)* %destValues) {
entry:
%idxprom = ashr exact i64 15, 32
%arrayidx = getelementptr inbounds <8 x i8>, <8 x i8> addrspace(1)* %sourceA, i64 %idxprom
%tmp = load <8 x i8>, <8 x i8> addrspace(1)* %arrayidx, align 8
%tmp1 = extractelement <8 x i8> %tmp, i32 0
%tmp2 = extractelement <8 x i8> %tmp, i32 1
%tmp3 = extractelement <8 x i8> %tmp, i32 2
%tmp4 = extractelement <8 x i8> %tmp, i32 3
%tmp5 = extractelement <8 x i8> %tmp, i32 4
%tmp6 = extractelement <8 x i8> %tmp, i32 5
%tmp7 = extractelement <8 x i8> %tmp, i32 6
%tmp8 = extractelement <8 x i8> %tmp, i32 7
%tmp9 = insertelement <2 x i8> undef, i8 %tmp1, i32 0
%tmp10 = insertelement <2 x i8> %tmp9, i8 %tmp2, i32 1
%tmp11 = insertelement <2 x i8> undef, i8 %tmp3, i32 0
%tmp12 = insertelement <2 x i8> %tmp11, i8 %tmp4, i32 1
%tmp13 = insertelement <2 x i8> undef, i8 %tmp5, i32 0
%tmp14 = insertelement <2 x i8> %tmp13, i8 %tmp6, i32 1
%tmp15 = insertelement <2 x i8> undef, i8 %tmp7, i32 0
%tmp16 = insertelement <2 x i8> %tmp15, i8 %tmp8, i32 1
%tmp17 = shufflevector <2 x i8> %tmp10, <2 x i8> %tmp12, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%tmp18 = shufflevector <2 x i8> %tmp14, <2 x i8> %tmp16, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%tmp19 = shufflevector <4 x i8> %tmp17, <4 x i8> %tmp18, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%arrayidx5 = getelementptr inbounds <8 x i8>, <8 x i8> addrspace(1)* %destValues, i64 %idxprom
store <8 x i8> %tmp19, <8 x i8> addrspace(1)* %arrayidx5, align 8
ret void
}