[llvm] [X86][PartialReduction] Lower zext-byte add reductions to vpsadbw (PR #201076)
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Thu Jun 4 03:04:12 PDT 2026
================
@@ -0,0 +1,478 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefixes=AVX512BW
+
+; Positive CodeGen tests for X86PartialReduction::tryByteSumReplacement.
+
+ at a = dso_local global [1024 x i8] zeroinitializer, align 16
+
+define dso_local i32 @byte_sum_v16_i32() nounwind {
+; SSE2-LABEL: byte_sum_v16_i32:
+; SSE2: # %bb.0: # %entry
+; SSE2-NEXT: pxor %xmm0, %xmm0
+; SSE2-NEXT: movq $-1024, %rax # imm = 0xFC00
+; SSE2-NEXT: pxor %xmm1, %xmm1
+; SSE2-NEXT: .p2align 4
+; SSE2-NEXT: .LBB0_1: # %vector.body
+; SSE2-NEXT: # =>This Inner Loop Header: Depth=1
+; SSE2-NEXT: movdqa a+1024(%rax), %xmm2
+; SSE2-NEXT: psadbw %xmm0, %xmm2
+; SSE2-NEXT: paddd %xmm2, %xmm1
+; SSE2-NEXT: addq $16, %rax
+; SSE2-NEXT: jne .LBB0_1
+; SSE2-NEXT: # %bb.2: # %middle.block
+; SSE2-NEXT: paddd %xmm0, %xmm1
+; SSE2-NEXT: paddd %xmm0, %xmm0
+; SSE2-NEXT: paddd %xmm1, %xmm0
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
+; SSE2-NEXT: paddd %xmm0, %xmm1
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,1,1]
+; SSE2-NEXT: paddd %xmm1, %xmm0
+; SSE2-NEXT: movd %xmm0, %eax
+; SSE2-NEXT: retq
+;
+; AVX2-LABEL: byte_sum_v16_i32:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vpxor %xmm0, %xmm0, %xmm0
+; AVX2-NEXT: movq $-1024, %rax # imm = 0xFC00
+; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
+; AVX2-NEXT: .p2align 4
+; AVX2-NEXT: .LBB0_1: # %vector.body
+; AVX2-NEXT: # =>This Inner Loop Header: Depth=1
+; AVX2-NEXT: vpsadbw a+1024(%rax), %xmm1, %xmm3
+; AVX2-NEXT: vpaddd %ymm2, %ymm3, %ymm2
+; AVX2-NEXT: addq $16, %rax
+; AVX2-NEXT: jne .LBB0_1
+; AVX2-NEXT: # %bb.2: # %middle.block
+; AVX2-NEXT: vpaddd %ymm0, %ymm2, %ymm0
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
+; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
+; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT: vmovd %xmm0, %eax
+; AVX2-NEXT: vzeroupper
+; AVX2-NEXT: retq
+;
+; AVX512BW-LABEL: byte_sum_v16_i32:
+; AVX512BW: # %bb.0: # %entry
+; AVX512BW-NEXT: vpxor %xmm0, %xmm0, %xmm0
+; AVX512BW-NEXT: movq $-1024, %rax # imm = 0xFC00
+; AVX512BW-NEXT: vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT: .p2align 4
+; AVX512BW-NEXT: .LBB0_1: # %vector.body
+; AVX512BW-NEXT: # =>This Inner Loop Header: Depth=1
+; AVX512BW-NEXT: vpsadbw a+1024(%rax), %xmm1, %xmm2
+; AVX512BW-NEXT: vpaddd %zmm0, %zmm2, %zmm0
+; AVX512BW-NEXT: addq $16, %rax
+; AVX512BW-NEXT: jne .LBB0_1
+; AVX512BW-NEXT: # %bb.2: # %middle.block
+; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
+; AVX512BW-NEXT: vpaddd %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX512BW-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
+; AVX512BW-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
+; AVX512BW-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT: vmovd %xmm0, %eax
+; AVX512BW-NEXT: vzeroupper
+; AVX512BW-NEXT: retq
+entry:
+ br label %vector.body
+
+vector.body:
+ %index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
+ %vec.phi = phi <16 x i32> [ zeroinitializer, %entry ], [ %add, %vector.body ]
+ %p = getelementptr inbounds [1024 x i8], ptr @a, i64 0, i64 %index
+ %wide.load = load <16 x i8>, ptr %p, align 16
+ %z = zext <16 x i8> %wide.load to <16 x i32>
+ %add = add nsw <16 x i32> %z, %vec.phi
+ %index.next = add i64 %index, 16
+ %cmp = icmp eq i64 %index.next, 1024
+ br i1 %cmp, label %middle.block, label %vector.body
+
+middle.block:
+ %s1 = shufflevector <16 x i32> %add, <16 x i32> poison, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+ %r1 = add <16 x i32> %add, %s1
+ %s2 = shufflevector <16 x i32> %r1, <16 x i32> poison, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+ %r2 = add <16 x i32> %r1, %s2
+ %s3 = shufflevector <16 x i32> %r2, <16 x i32> poison, <16 x i32> <i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+ %r3 = add <16 x i32> %r2, %s3
+ %s4 = shufflevector <16 x i32> %r3, <16 x i32> poison, <16 x i32> <i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+ %r4 = add <16 x i32> %r3, %s4
+ %ext = extractelement <16 x i32> %r4, i32 0
+ ret i32 %ext
+}
+
+;----------------------------------------------------------------------------
+; POSITIVE: i32 accumulator, VF = 32.
+; SSE2 splits into two 128-bit psadbw per iteration; AVX2 and AVX-512BW
+; emit a single 256-bit vpsadbw (AVX-512BW takes the 256-bit path because
+; NumElts < 64).
+;----------------------------------------------------------------------------
+define dso_local i32 @byte_sum_v32_i32() nounwind {
+; SSE2-LABEL: byte_sum_v32_i32:
+; SSE2: # %bb.0: # %entry
+; SSE2-NEXT: pxor %xmm0, %xmm0
+; SSE2-NEXT: movq $-1024, %rax # imm = 0xFC00
+; SSE2-NEXT: pxor %xmm1, %xmm1
+; SSE2-NEXT: pxor %xmm2, %xmm2
+; SSE2-NEXT: .p2align 4
+; SSE2-NEXT: .LBB1_1: # %vector.body
+; SSE2-NEXT: # =>This Inner Loop Header: Depth=1
+; SSE2-NEXT: movdqa a+1024(%rax), %xmm3
+; SSE2-NEXT: psadbw %xmm0, %xmm3
+; SSE2-NEXT: paddd %xmm3, %xmm1
+; SSE2-NEXT: movdqa a+1040(%rax), %xmm3
+; SSE2-NEXT: psadbw %xmm0, %xmm3
+; SSE2-NEXT: paddd %xmm3, %xmm2
+; SSE2-NEXT: addq $32, %rax
+; SSE2-NEXT: jne .LBB1_1
+; SSE2-NEXT: # %bb.2: # %middle.block
+; SSE2-NEXT: paddd %xmm0, %xmm2
+; SSE2-NEXT: paddd %xmm0, %xmm1
+; SSE2-NEXT: paddd %xmm0, %xmm0
+; SSE2-NEXT: paddd %xmm0, %xmm1
+; SSE2-NEXT: paddd %xmm2, %xmm0
+; SSE2-NEXT: paddd %xmm1, %xmm0
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
+; SSE2-NEXT: paddd %xmm0, %xmm1
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,1,1]
+; SSE2-NEXT: paddd %xmm1, %xmm0
+; SSE2-NEXT: movd %xmm0, %eax
+; SSE2-NEXT: retq
+;
+; AVX2-LABEL: byte_sum_v32_i32:
+; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vpxor %xmm0, %xmm0, %xmm0
+; AVX2-NEXT: movq $-1024, %rax # imm = 0xFC00
+; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT: .p2align 4
+; AVX2-NEXT: .LBB1_1: # %vector.body
+; AVX2-NEXT: # =>This Inner Loop Header: Depth=1
+; AVX2-NEXT: vpsadbw a+1024(%rax), %ymm0, %ymm2
+; AVX2-NEXT: vpaddd %ymm1, %ymm2, %ymm1
+; AVX2-NEXT: addq $32, %rax
+; AVX2-NEXT: jne .LBB1_1
+; AVX2-NEXT: # %bb.2: # %middle.block
+; AVX2-NEXT: vpaddd %ymm0, %ymm1, %ymm1
+; AVX2-NEXT: vpaddd %ymm0, %ymm0, %ymm0
+; AVX2-NEXT: vpaddd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
+; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
+; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT: vmovd %xmm0, %eax
+; AVX2-NEXT: vzeroupper
+; AVX2-NEXT: retq
+;
+; AVX512BW-LABEL: byte_sum_v32_i32:
+; AVX512BW: # %bb.0: # %entry
+; AVX512BW-NEXT: vpxor %xmm0, %xmm0, %xmm0
+; AVX512BW-NEXT: movq $-1024, %rax # imm = 0xFC00
+; AVX512BW-NEXT: vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT: vpxor %xmm2, %xmm2, %xmm2
+; AVX512BW-NEXT: .p2align 4
+; AVX512BW-NEXT: .LBB1_1: # %vector.body
+; AVX512BW-NEXT: # =>This Inner Loop Header: Depth=1
+; AVX512BW-NEXT: vpsadbw a+1024(%rax), %ymm1, %ymm3
+; AVX512BW-NEXT: vpaddd %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT: addq $32, %rax
+; AVX512BW-NEXT: jne .LBB1_1
+; AVX512BW-NEXT: # %bb.2: # %middle.block
+; AVX512BW-NEXT: vpaddd %zmm0, %zmm2, %zmm0
+; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
+; AVX512BW-NEXT: vpaddd %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX512BW-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
+; AVX512BW-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,1,1]
+; AVX512BW-NEXT: vpaddd %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT: vmovd %xmm0, %eax
+; AVX512BW-NEXT: vzeroupper
+; AVX512BW-NEXT: retq
+entry:
+ br label %vector.body
+
+vector.body:
+ %index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
+ %vec.phi = phi <32 x i32> [ zeroinitializer, %entry ], [ %add, %vector.body ]
+ %p = getelementptr inbounds [1024 x i8], ptr @a, i64 0, i64 %index
+ %wide.load = load <32 x i8>, ptr %p, align 16
+ %z = zext <32 x i8> %wide.load to <32 x i32>
+ %add = add nsw <32 x i32> %z, %vec.phi
+ %index.next = add i64 %index, 32
+ %cmp = icmp eq i64 %index.next, 1024
+ br i1 %cmp, label %middle.block, label %vector.body
+
+middle.block:
+ %s1 = shufflevector <32 x i32> %add, <32 x i32> poison, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+ %r1 = add <32 x i32> %add, %s1
+ %s2 = shufflevector <32 x i32> %r1, <32 x i32> poison, <32 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+ %r2 = add <32 x i32> %r1, %s2
+ %s3 = shufflevector <32 x i32> %r2, <32 x i32> poison, <32 x i32> <i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+ %r3 = add <32 x i32> %r2, %s3
+ %s4 = shufflevector <32 x i32> %r3, <32 x i32> poison, <32 x i32> <i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+ %r4 = add <32 x i32> %r3, %s4
+ %s5 = shufflevector <32 x i32> %r4, <32 x i32> poison, <32 x i32> <i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+ %r5 = add <32 x i32> %r4, %s5
+ %ext = extractelement <32 x i32> %r5, i32 0
----------------
RKSimon wrote:
use a vector.reduce.add.v32i32 call here instead of the expanded codegen
https://github.com/llvm/llvm-project/pull/201076
More information about the llvm-commits
mailing list